The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index; 4 of the 9 sources its claims cite were checked for support.
Sequence-Level Knowledge Distillation
Open accessAbstract
Neural machine translation (NMT) offers a novel alternative formulation of translation that is potentially simpler than statistical approaches.However to reach competitive performance, NMT models need to be exceedingly large.In this paper we consider applying knowledge distillation approaches (Bucila et al., 2006;Hinton et al., 2015) that have proven successful for reducing the size of neural models in other domains to the problem of NMT.We demonstrate that standard knowledge distillation applied to word-level prediction can be effective for NMT, and also introduce two novel sequence-level versions of knowledge distillation that further improve performance, and somewhat surprisingly, seem to eliminate the need for beam search (even when applied on the original teacher model).Our best student model runs 10 times faster than its state-of-the-art teacher with little loss in performance.It is also significantly better than a baseline model trained without knowledge distillation: by 4.2/1.7 BLEU with greedy decoding/beam search.Applying weight pruning on top of knowledge distillation results in a student model that has 13× fewer parameters than the original teacher model, with a decrease of 0.4 BLEU.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
The paper applies knowledge distillation to neural machine translation, showing word-level distillation helps and introducing sequence-level variants (Seq-KD and Seq-Inter) that train a smaller student on teacher beam-search outputs. The best student runs 10× faster than its teacher with little BLEU loss, and pruning on top yields 13× fewer parameters with a 0.4 BLEU drop.
Key findings
- Word-level knowledge distillation improves over the baseline, but sequence-level knowledge distillation does better on English→German and similarly on Thai→English; combining them gives further gains for the 2×300 and 2×100 models, though not for the 2×500 model. For English→German 2×500, baseline BLEU is 14.7/17.6 (greedy/beam), Seq-KD is 18.9/19.0, and Seq-KD + Seq-Inter is 18.9/19.3, i.e. +4.2/+1.7 BLEU over baseline.
- Sequence-level distillation reduces the need for beam search: greedy decoding with a fine-tuned teacher (Baseline + Seq-Inter) reaches 19.6 BLEU versus 19.5 for beam search with the original teacher. Seq-KD models also assign much more mass to the approximate mode: 16.9% for the 2×500 English→German Seq-KD model versus 0.9% for the baseline.
- The student model can run 10× faster with greedy decoding than the teacher with beam search on GPU: 1051.3 vs 101.9 source words/sec.
- Weight pruning on top of distillation is orthogonal: pruning 80% of weights in the 2×500 Seq-KD + Seq-Inter student gives 13× fewer parameters than the original teacher with only 0.4 BLEU decrease; pruning 90% gives 8m parameters (26× fewer) with a 1.0 BLEU decrease.
Methods
- Uses an attentional encoder-decoder NMT architecture from Luong et al. (2015). Two settings: English→German WMT 2014 (4m sentences, top 50k vocabulary, teacher 4×1000 LSTM, students 2×300 and 2×500) and Thai→English IWSLT 2015 (90k sentences, 25k vocabulary, teacher 2×500, student 2×100). Evaluation is tokenized BLEU with multi-bleu.perl.
- Three distillation variants: Word-KD (cross-entropy with teacher word distribution plus NLL; α tested in {0.5, 0.9}, with 0.5 better); Seq-KD (student trained on teacher beam-search output, beam K=5); and Seq-Inter (student trained on the teacher beam hypothesis with highest smoothed sentence BLEU to gold, beam K=35, fine-tuned from a pretrained model with learning rate 0.1; English→German Seq-Inter data generated on ~50% of the training set). Methods can be combined.
- Weight pruning removes weights with lowest absolute values, then retrains on Seq-KD data with learning rate 0.2 and fine-tunes toward Seq-Inter data with learning rate 0.1. Speed is measured on GPU (GeForce GTX Titan X), CPU, and smartphone (Samsung Galaxy 6).
Limitations
- Stated: the mode approximation for sequence-level distillation is poor because it approximates an exponentially sized distribution with a single sample; Seq-Inter’s two-sequence interpolation is nonideal because it doubles training data and requires training on both teacher-generated and true sequences conditioned on the same source, which are often different. The paper also calls its illustrative noise function “simple (unrealistic).”
- Stated: experiments cover only English→German and Thai→English NMT; the 4×1000 model could not be opened on the smartphone; larger beam sizes than K=5 did not improve results; and English→German Seq-Inter data was generated on only ~50% of the training set for efficiency.
- Evident from the text: no statistical significance tests are reported, hyperparameter searches are narrow (τ ∈ {1, 1.5, 2}; α ∈ {0.5, 0.9}), and compression is compared mainly against pruning rather than other compression families.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
4 of 9 cited sources checked · 3 supported · 0 flagged · accuracy not yet measured
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“While both simple and surprisingly accurate, NMT systems typically need to have very high capacity in order to perform well: Sutskever et al. (2014) used a 4-layer LSTM with 1000 hidden units per layer (herein 4×1000) and Zhou et al. (2016) obtained state-of-the-art results on English → French with a 16-layer LSTM with 512 units per layer.”
§ Sequence-Level Knowledge Distillation > 1 Introduction
What the sources say
- Not checked — no full text of the sourcecites Sutskever et al. (2014) source
- Supportedcites Zhou et al. (2016) source
The Model settings section states that every LSTM layer has 512 memory cells. The Introduction and Conclusion report a depth-16 model that achieved state-of-the-art results on WMT’14 English-to-French, supporting the specific example attributed to Zhou et al. (LLM, conf=0.93)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesThe paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Our best student model runs 10 times faster than its state-of-the-art teacher with little loss in performance.”
§ Sequence-Level Knowledge Distillation > Abstract
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Sequence-level interpolation (Seq-Inter), in addition to improving models trained via Word-KD and Seq-KD, also improves upon the original teacher model that was trained on the actual data but finetuned towards Seq-Inter data (Baseline + Seq-Inter).”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In fact, greedy decoding with this fine-tuned model has similar performance (19.6) as beam search with the original model (19.5), allowing for faster decoding even with an identically-sized model.”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our results suggest that this is indeed the case: the probability mass that Seq-KD models assign to the approximate mode is much higher than is the case for baseline models trained on original data (Table 1: p(t = ŷ)).”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Sequence-level interpolation (Seq-Inter), in addition to improving models trained via Word-KD and Seq-KD, also improves upon the original teacher model that was trained on the actual data but finetuned towards Seq-Inter data (Baseline + Seq-Inter).”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find that while word-level knowledge distillation (Word-KD) does improve upon the baseline, sequence-level knowledge distillation (Seq-KD) does better on English → German and performs similarly on Thai → English.”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find that while word-level knowledge distillation (Word-KD) does improve upon the baseline, sequence-level knowledge distillation (Seq-KD) does better on English → German and performs similarly on Thai → English.”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Seq-Inter offers a compromise between the two, with the greedily-decoded sequence accounting for 7.6% of the distribution.”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find that while word-level knowledge distillation (Word-KD) does improve upon the baseline, sequence-level knowledge distillation (Seq-KD) does better on English → German and performs similarly on Thai → English.”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
- It may state two separate claims as one. 15
- Probably not a substantial claim. 6
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Researchers have particularly noted that large networks seem to be necessary for training, but learn redundant representations in the process (Denil et al., 2013).”
§ Sequence-Level Knowledge Distillation > 1 Introduction
What the sources say
- Partly supportedcites Denil et al., 2013 sourceExperimental — accuracy not yet measured
The Abstract (p. 1) reports significant redundancy in model parameters, and the Introduction (p. 2) explains that individual feature weights can be redundant. The paper does not say that large networks are necessary for training; its finding concerns redundant parameterization, not necessarily redundant representations. (LLM, conf=0.85)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In this paper we consider applying knowledge distillation approaches (Bucila et al., 2006;Hinton et al., 2015) that have proven successful for reducing the size of neural models in other domains to the problem of NMT.”
§ Sequence-Level Knowledge Distillation > Abstract
What the sources say
- Not matchedcites Bucila et al., 2006
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites Hinton et al., 2015 source
The Discussion (p. 8) says distillation worked well for transferring knowledge from an ensemble or large model into a smaller model, including in MNIST and acoustic-model experiments. These are successful applications outside NMT, as the citing sentence claims. (LLM, conf=0.94)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
- Not matched
Every source the paper cites for this claim was checked and supports it.
In the paper
“Training on q(y | x; θ T ) is attractive since it gives more information about other classes for a given data point (e.g.similarity between classes) and has less variance in gradients (Hinton et al., 2015).”
§ Sequence-Level Knowledge Distillation > 2.2 Knowledge Distillation
What the sources say
- Supportedcites Hinton et al., 2015 source
The Introduction (p. 2) says that soft targets from a cumbersome model provide more information per training case and less variance in gradients when they have high entropy. It also explains that probabilities assigned to other classes convey a similarity structure. (LLM, conf=0.93)
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Supported
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Applying weight pruning on top of knowledge distillation results in a student model that has 13× fewer parameters than the original teacher model, with a decrease of 0.4 BLEU.”
§ Sequence-Level Knowledge Distillation > Abstract
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Combining them (Seq-KD + Word-KD) results in further gains for the 2 × 300 and 2 × 100 models (although not for the 2 × 500 model)”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“A beam of size 5 captures 2.8% of the distribution for German → English, and 3.8% for Thai → English.”
§ Sequence-Level Knowledge Distillation > 3.2 Sequence-Level Knowledge Distillation
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We found this to give comparable results to standard knowledge distillation and hence did not pursue this further.”
§ Sequence-Level Knowledge Distillation > 5.3 Further Observations
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In fact, in experiments we find that with beam of size 1, q(ŷ | s) (on average) accounts for 1.3% of the distribution for German → English, and 2.3% for Thai → English (Table 1: p(t = ŷ)).”
§ Sequence-Level Knowledge Distillation > 3.2 Sequence-Level Knowledge Distillation
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The perplexity of the baseline 2 × 500 English → German model is 8.2 while the perplexity of the corresponding Seq-KD model is 22.7”
§ Sequence-Level Knowledge Distillation > 7 Conclusion
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We use beam size K = 5 (we did not see improvements with a larger beam).”
§ Sequence-Level Knowledge Distillation > Sequence-Level Knowledge Distillation (Seq-KD)
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“Our student models can even be run efficiently on a standard smartphone.”
§ Sequence-Level Knowledge Distillation > 1 Introduction
What the sources say
- Not matchedcites 1 https://github.com/harvardnlp/nmt-android
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Strength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find that we can run the student model 10 times faster with greedy decoding than the teacher model with beam search on GPU (1051.3vs 101.9 words/sec), with similar performance.”
§ Sequence-Level Knowledge Distillation > 5.1 Decoding Speed
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Seq-KD model does significantly better for both greedy (+4.2 BLEU) and beam search (+1.4 BLEU) decoding.”
§ Sequence-Level Knowledge Distillation > 7 Conclusion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While pruning 90% of the weights results in a more appreciable decrease of 1.0 BLEU, the model is drastically smaller with 8m parameters, which is 26× fewer than the original teacher model.”
§ Sequence-Level Knowledge Distillation > 5.2 Weight Pruning
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“indicating that these methods provide orthogonal means of transferring knowledge from the teacher to the student: Word-KD is transferring knowledge at the the local (i.e.word) level while Seq-KD is transferring knowledge at the global (i.e.sequence) level.”
§ Sequence-Level Knowledge Distillation > 5 Results and Discussion
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“Weight pruning for NMT was recently investigated by See et al. (2016), who found that up to 80 -90% of the parameters in a large NMT model can be pruned with little loss in performance.”
§ Sequence-Level Knowledge Distillation > 5.2 Weight Pruning
What the sources say
- Not matchedcites See et al. (2016)
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, the fact that sequencelevel knowledge distillation allows for greedy decoding is significant, with practical implications for running NMT systems across various devices.”
§ Sequence-Level Knowledge Distillation > 5.1 Decoding Speed
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: Run-time complexity for beam search grows linearly with beam size.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The above methods are complementary and can be combined with each other.”
§ Sequence-Level Knowledge Distillation > Sequence-Level Interpolation (Seq-Inter)
Strength:plain· not yet calibratedCausal:correlational· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The size of word embeddings have little impact on run-time as the word embedding layer is a simple lookup table that only affects the first layer of the model.”
§ Sequence-Level Knowledge Distillation > 5.2 Weight Pruning
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclearIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Despite its intractability, we posit that this sequence-level objective is worthwhile.It gives the teacher the chance to assign probabilities to complete sequences and therefore transfer a broader range of knowledge.”
§ Sequence-Level Knowledge Distillation > 3.2 Sequence-Level Knowledge Distillation
Tests✓ Asserted: passes✗ Checkable: fails✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim. It may be too vague to check against evidence.
The authors state this as an assumption.
The teacher has previously been trained, and we are estimating parameters for the student.
“We generally assume that the teacher has previously been trained, and that we are estimating parameters for the student.”
The authors state this as an assumption.
The teacher distribution parameters remain fixed during student training.
“where θ T parameterizes the teacher distribution and remains fixed.”
The paper relies on this without support.
Run-time complexity for beam search grows linearly with beam size.
“Run-time complexity for beam search grows linearly with beam size.”
The paper relies on this without support.
Combining pruning and knowledge distillation has not been investigated before.
“To our knowledge combining pruning and knowledge distillation has not been investigated before.”
The paper relies on this without support.
The translation domain has generally required the largest capacity deep learning models.
“We have chosen to focus on translation as this domain has generally required the largest capacity deep learning models”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Extracting reasoning matters not because output-only distillation is ineffective, but because reasoning yields a substantially more effective form of capability stealing.”
From Stealing Reasoning Traces from Proprietary LLM APIs (2026) · cites this paper as Kim and Rush, 2016
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Word-embedding parameter share does not match the stated counts
MinorThe stated 50m word-embedding parameters out of 84m total amount to about 59.5%, not approximately 63%.
Reported 63 · recomputed 59.52381
“on the 2 × 500 English → German model the word embeddings account for approximately 63% (50m out of 84m) of the parameters.”
Incorrect BLEU improvement for 2 × 500 Baseline + Seq-Inter
MinorThe English→German 2 × 500 Baseline + Seq-Inter greedy BLEU is 18.5, compared with 14.7 for the baseline. The improvement is 3.8 BLEU, not the reported 3.6.
Reported 3.6 · recomputed 3.8
“Student Baseline 2 × 500 (Params: 84m) Word-KD Seq-KD Baseline + Seq-Inter Word-KD + Seq-Inter Seq-KD + Seq-Inter Seq-KD + Word-KD Seq-KD + Seq-Inter + Word-KD | 14.7 15.4 18.9 18.5 18.3 18.9 18.7 18.8 | -+0.7 +4.2 +3.6”
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
Flagged first, then by citations
Research works printed but not linked: 4
- Cristian Bucila, Rich Caruana, and Alexandru Niculescu-Mizil. 2006. Model Compres- sion. In Proceedings of KDD.
- and Blunsom2013] Nal Kalchbrenner and Phil Blunsom. 2013. Recurrent Continuous Transla- tion Models. In Proceedings of EMNLP.
- Jiwei Li, Michael Galley, Chris Brockett, Jianfeg Gao, and Bill Dolan. 2016. A Diversity- Promoting Objective Function for Neural Conversa- tional Models. In Proceedings of NAACL 2016.
- Mariet and Sra2016] Zelda Mariet and Suvrit Sra. 2016. Diversity Networks. In Proceedings of ICLR.
Cited by
Sorted by citations
Items 101–200 of 841
Zero-Shot Cross-Lingual Neural Headline Generation
Yana, A., Shen, S., Chen, Y., Yang, C. H., Liu, Z., & Sun, M. (2018) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2018.2842432 · Cited by 56
From Research to Production and Back: Ludicrously Fast Neural Machine Translation
Kim, Y. J., Junczys-Dowmunt, M., Hassan, H., Aji, A. F., Heafield, K., Grundkiewicz, R., & Bogoychev, N. (2019) · Workshop on Neural Generation and Translation (WNGT) · doi:10.18653/v1/d19-5632 · Cited by 56
Self-citationMinimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation
Shao, C., Zhang, J., Feng, Y., Meng, F., & Zhou, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i01.5351 · Cited by 55
Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning
Guo, L., Liu, J., Zhu, X., He, X., Jiang, J., & Lu, H. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/107 · Cited by 71
Ma, T., Tian, W., & Xie, Y. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108136 · Cited by 54
Kurata, G., & Audhkhasi, K. (2018) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639629 · Cited by 53
Syntactically Supervised Transformers for Faster Neural Machine Translation
Akoury, N., Krishna, K., & Iyyer, M. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1122 · Cited by 55
TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks
Haidar, M. A., & Rezagholizadeh, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-18305-9_9 · Cited by 62
Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT
Bhardwaj, K., Lin, C., Sartor, A. L., & Mărculescu, R. (2019) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3358205 · Cited by 50
Marian: Cost-effective High-Quality Neural Machine Translation in C++
Junczys-Dowmunt, M., Heafield, K., Hoang, H., Grundkiewicz, R., & Aue, A. (2018) · doi:10.18653/v1/w18-2716 · Cited by 52
Automated Knowledge Distillation via Monte Carlo Tree Search
Li, L., Dong, P., Wei, Z., et al. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01597 · Cited by 51
Improved Mask-CTC for Non-Autoregressive End-to-End ASR
Higuchi, Y., Inaguma, H., Watanabe, S., Ogawa, T., & Kobayashi, T. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414198 · Cited by 54
Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation
Behnke, M., & Heafield, K. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.211 · Cited by 54
Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence LabellingPreprint
Liu, H., Zhu, Z., Li, X., & Satheesh, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00096 · Cited by 50
Theory and Experiments on Vector Quantized AutoencodersPreprint
Roy, A., Vaswani, A., Neelakantan, A., & Parmar, N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.11063 · Cited by 50
Recurrent Neural Networks as Weighted Language Recognizers
Chen, Y., Gilroy, S., Maletti, A., May, J., & Knight, K. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1205 · Cited by 49
Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition
Meng, Z., Li, J., Gaur, Y., & Gong, Y. (2019) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru46091.2019.9003776 · Cited by 49
Data Diversification: A Simple Strategy For Neural Machine TranslationPreprint
Nguyen, X.-P., Joty, S., Wu, K., & Aw, A. T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01986 · Cited by 60
Semi-Autoregressive Transformer for Image Captioning
Zhou, Y., Zhang, Y., Hu, Z., & Wang, M. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00350 · Cited by 50
Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine TranslationPreprint
Kasai, J., Pappas, N., Peng, H., Cross, J., & Smith, N. A. (2020) · arXiv (Cornell University) · Cited by 44
Semi-supervised Training for End-to-end Models via Weak Distillation
Li, B., Sainath, T. N., Pang, R., & Wu, Z. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682172 · Cited by 47
Yamamoto, R., Song, E., & Kim, J.-M. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1965 · Cited by 47
Which *BERT? A Survey Organizing Contextualized Encoders
Xia, P., Wu, S., & Durme, B. V. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.608 · Cited by 57
Efficient Sequence Learning with Group Recurrent Networks
Gao, F., Wu, L., Zhao, L., Qin, T., Cheng, X.-Q., & Liu, T.-Y. (2018) · North American Chapter of the Association for Computational Linguistics · doi:10.18653/v1/n18-1073 · Cited by 47
Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion
Sun, H., Tan, X., Gan, J.-W., Liu, H., Zhao, S., Qin, T., & Liu, T. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1208 · Cited by 58
Modeling Teacher-Student Techniques in Deep Neural Networks for Knowledge Distillation
Abbasi, S., Hajabdollahi, M., Karimi, N., et al. (2020) · doi:10.1109/mvip49855.2020.9116923 · Cited by 44
AutoEncoder-Driven Multimodal Collaborative Learning for Medical Image Synthesis
Cao, B., Bi, Z., Hu, Q., Zhang, H., Wang, N., Gao, X., & Shen, D. G. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01791-0 · Cited by 45
OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU
Sénellart, J., Zhang, D., Wang, B., Klein, G., Ramatchandirin, J.-P., Crego, J., & Rush, A. M. (2018) · doi:10.18653/v1/w18-2715 · Cited by 44
Self-citationThe NiuTrans Machine Translation Systems for WMT19
Li, B., Li, Y., Xu, C., Lin, Y., Liu, J., Liu, H., Wang, Z., Zhang, Y., Xu, N., Wang, Z., et al. (2019) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w19-5325 · Cited by 43
Improved Training for Online End-to-end Speech Recognition Systems
Kim, S., Seltzer, M. L., Li, J., & Zhao, R. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-2517 · Cited by 43
Domain specialization: a post-training domain adaptation for Neural Machine TranslationPreprint
Servan, C., Crego, J., & Sénellart, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06141 · Cited by 43
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
Higuchi, Y., Chen, N., Fujita, Y., Inaguma, H., Komatsu, T., Lee, J., Nozaki, J., Wang, T., & Watanabe, S. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688157 · Cited by 43
Diversifying Dialogue Generation with Non-Conversational Text
Su, H., Shen, X., Zhao, S., Zhou, X., Hu, P., Zhong, R., Niu, C., & Zhou, J. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.634 · Cited by 49
Prompt Consistency for Zero-Shot Task Generalization
Zhou, C., He, J., Ma, X., Berg-Kirkpatrick, T., & Neubig, G. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.192 · Cited by 68
A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions
Liu, Z., Yuan, L., Chen, N., Wang, Q., Hooi, B., & He, B. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3549299 · Cited by 66
Better Document-Level Machine Translation with Bayes’ Rule
Yu, L., Sartran, L., Stokowiec, W., Wang, L., Kong, L., Blunsom, P., & Dyer, C. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00319 · Cited by 42
Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction
Tarnavskyi, M., Chernodub, A., & Omelianchuk, K. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.266 · Cited by 44
Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation
Shao, C., Feng, Y., Zhang, J., Meng, F., Chen, X., & Zhou, J. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1288 · Cited by 40
A Compact and Language-Sensitive Multilingual Translation Method
Wang, Y., Zhou, L., Zhang, J., Zhai, F.-F., Xu, J.-F., & Zong, C.-Q. (2019) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1117 · Cited by 42
Sharing Attention Weights for Fast Transformer
Xiao, T., Li, Y.-Q., Zhu, J.-B., Yu, Z.-T., & Liu, T. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/735 · Cited by 65
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference
Kudugunta, S., Huang, Y., Bapna, A., Krikun, M., Lepikhin, D., Luong, M.-T., & Fırat, O. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.304 · Cited by 97
Generate, Annotate, and Learn: NLP with Synthetic Text
He, X., Nassar, I., Kiros, J., Haffari, G., & Norouzi, M. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00492 · Cited by 55
LIT: Learned Intermediate Representation Training for Model Compression
Koratana, A., Kang, D. D., Bailis, P. D., & Zaharia, M. (2019) · International Conference on Machine Learning · Cited by 39
Selective Knowledge Distillation for Neural Machine Translation
Wang, F., Yan, J., Meng, F., et al. (2021) · doi:10.18653/v1/2021.acl-long.504 · Cited by 39
Song, J., Kim, S., & Yoon, S. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.1 · Cited by 50
Knowledge Adaptation: Teaching to AdaptPreprint
Ruder, S., Ghaffari, P., & Breslin, J. G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.02052 · Cited by 53
UniTE: Unified Translation Evaluation
Wan, Y., Liu, D., Yang, B., Zhang, H., Chen, B., Wong, D. F., & Chao, L. S. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.558 · Cited by 48
Feng, K., Li, C., Yuan, Y., & Wang, G. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539320 · Cited by 40
Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation
Ran, Q., Lin, Y., Li, P., & Zhou, J. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.277 · Cited by 38
Lifelong Language Knowledge Distillation
Chuang, Y.-S., Su, S., & Chen, Y.-N. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.233 · Cited by 42
Re-Transformer: A Self-Attention Based Model for Machine Translation
Liu, H.-I., & Chen, W. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.05.065 · Cited by 39
Learning Approximate Inference Networks for Structured PredictionPreprint
Tu, L., & Gimpel, K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.03376 · Cited by 39
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
Tu, L., Pang, R. Y., Wiseman, S., & Gimpel, K. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.251 · Cited by 37
Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation
Liu, J., Ren, Y., Tan, X., Zhang, C., Qin, T., Zhao, Z., & Liu, T. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/534 · Cited by 37
Domain, Translationese and Noise in Synthetic Data for Neural Machine TranslationPreprint
Bogoychev, N., & Sennrich, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.03362 · Cited by 37
Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation
Xia, H., Ge, T., Wang, P., Chen, S.-Q., Wei, F., & Sui, Z. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.257 · Cited by 40
“We apply sequence-level knowledge distillation (Kim and Rush, 2016) by the AR teacher to the Spec-Drafter to align its behavior with the AR model as much as possible.”
BackgroundMethodKaramanolakis, G., Hsu, D., & Gravano, L. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1468 · Cited by 38
Collaborative learning between cloud and end devices
Lu, Y., Shu, Y., Tan, X., Liu, Y., Zhou, M., Chen, Q., & Pei, D. (2019) · ACM/IEEE Symposium on Edge Computing (SEC) · doi:10.1145/3318216.3363304 · Cited by 34
Structure-Level Knowledge Distillation For Multilingual Sequence Labeling
Wang, X., Jiang, Y., Bách, N., Wang, T., Huang, F., & Tu, K. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.304 · Cited by 35
Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation
Inaguma, H., Kawahara, T., & Watanabe, S. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.150 · Cited by 39
An Efficient Transformer Decoder with Compressed Sub-layers
Li, Y., Lin, Y., Xiao, T., & Zhu, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i15.17572 · Cited by 36
Baidu Neural Machine Translation Systems for WMT19
Sun, M., Jiang, B., Xiong, H., He, Z., Wu, H. R., & Wang, H. (2019) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w19-5341 · Cited by 35
Yin, A., Zhao, Z., Liu, J., Jin, W., Zhang, M., Zeng, X., & He, X. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475544 · Cited by 39
CLIPPING: Distilling CLIP-Based Models with a Student Base for Video-Language Retrieval
Pei, R., Liu, J., Li, W., Shao, B., Xu, S., Dai, P., Lu, J., & Yan, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01820 · Cited by 43
Triangular Architecture for Rare Language Translation
Ren, S., Chen, W., Liu, S., et al. (2018) · Annual Meeting of the Association for Computational Linguistics (ACL) · doi:10.18653/v1/p18-1006 · Cited by 35
Automatically Learning Data Augmentation Policies for Dialogue Tasks
Niu, T., & Bansal, M. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1132 · Cited by 33
Future-Aware Knowledge Distillation for Neural Machine Translation
Zhang, B., Xiong, D., Su, J., & Luo, J. (2019) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2019.2946480 · Cited by 32
Improving End-to-End Single-Channel Multi-Talker Speech Recognition
Zhang, W., Chang, X., Qian, Y., & Watanabe, S. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.2988423 · Cited by 35
CTDS: Centralized Teacher With Decentralized Student for Multiagent Reinforcement Learning
Zhao, J., Hu, X., Yang, M., Zhou, W., Zhu, J., & Li, H. (2022) · IEEE Transactions on Games · doi:10.1109/tg.2022.3232390 · Cited by 41
Zeng, S., Wan, H., Shi, S., & Wang, W. (2023) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3580838 · Cited by 35
Mei, T., Zi, Y., Cheng, X., Gao, Z., Wang, Q., & Yang, H. (2024) · IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE) · doi:10.1109/icsece61636.2024.10729518 · Cited by 45
Iterative Dual Domain Adaptation for Neural Machine Translation
Zeng, J., Liu, Y., Su, J., Ge, Y., Lu, Y., Yin, Y., & Luo, J. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1078 · Cited by 33
TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing
Yang, Z., Cui, Y., Chen, Z., Che, W., Liu, T., Wang, S., & Hu, G. (2020) · Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL Demo) · doi:10.18653/v1/2020.acl-demos.2 · Cited by 38
NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application
Wu, C., Wu, F., Yu, Y., Qi, T., Huang, Y., & Liu, Q. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.280 · Cited by 40
Progressive Multi-Granularity Training for Non-Autoregressive Translation
Ding, L., Wang, L., Liu, X., Wong, D. F., Tao, D., & Tu, Z. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.247 · Cited by 38
Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation
Ding, L., Wang, L., Liu, X., Wong, D. F., Tao, D., & Tu, Z. (2021) · doi:10.18653/v1/2021.acl-long.266 · Cited by 41
X-Transformer: A Machine Translation Model Enhanced by the Self-Attention Mechanism
Liu, H.-I., & Chen, W. (2022) · Applied Sciences · doi:10.3390/app12094502 · Cited by 37
Bai, Y., Yi, J., Tao, J., Tian, Z., & Wen, Z. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1554 · Cited by 33
Distilling Spikes: Knowledge Distillation in Spiking Neural Networks
Kushawaha, R. K., Kumar, S., Banerjee, B., et al. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412147 · Cited by 33
EdiT5: Semi-Autoregressive Text Editing with T5 Warm-Start
Mallinson, J., Adamek, J., Malmi, E., & Severyn, A. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.156 · Cited by 41
Knowledge Distillation Using Output Errors for Self-attention End-to-end Models
Kim, H.-G., Na, H., Lee, H., Lee, J.-Y., Kang, T., Lee, M.-J., & Choi, Y.-S. (2019) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.2019.8682775 · Cited by 32
Wang, Z., & Yang, B. (2020) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc-picom-cbdcom-cyberscitech49142.2020.00100 · Cited by 31
An Actor-Critic-Based Transfer Learning Framework for Experience-Driven Networking
Xu, Z., Yang, D., Tang, J., Tang, Y., Yuan, T., Wang, Y., & Xue, G. (2020) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2020.3037231 · Cited by 32
Context-Aware Cross-Attention for Non-Autoregressive Translation
Ding, L., Wang, L., Wu, D., Tao, D., & Tu, Z. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.389 · Cited by 32
Learning Light-Weight Translation Models from Deep Transformer
Li, B., Wang, Z., Liu, H., Du, Q., Xiao, T., Zhang, C., & Zhu, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i15.17561 · Cited by 32
Arabic Machine Translation: A Survey With Challenges and Future Directions
Zakraoui, J., Saleh, M., Al-Maadeed, S. A., & Alja’am, J. M. (2021) · IEEE Access · doi:10.1109/access.2021.3132488 · Cited by 53
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
Gan, Z., Li, C., Chen, C., Pu, Y., Su, Q., & Carin, L. (2017) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p17-1030 · Cited by 35
Distilling Knowledge for Fast Retrieval-based Chat-bots
Tahami, A. V., Ghajar, K., & Shakery, A. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401296 · Cited by 32
Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers
Wu, Y., Passban, P., Rezagholizadeh, M., & Liu, Q. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.74 · Cited by 31
Noisy Self-Knowledge Distillation for Text Summarization
Liu, Y., Shen, S., & Lapata, M. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.56 · Cited by 45
Learning to Rewrite for Non-Autoregressive Neural Machine Translation
Geng, X., Feng, X., & Qin, B. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.265 · Cited by 31
latent-GLAT: Glancing at Latent Variables for Parallel Text Generation
Bao, Y., Zhou, H., Huang, S., Wang, D., Qian, L., Dai, X., Chen, J., & Li, L. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.575 · Cited by 35
Faithfulness-Aware Decoding Strategies for Abstractive Summarization
Wan, D., Liu, M., McKeown, K. R., Dreyer, M., & Bansal, M. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.210 · Cited by 46
An Overview of Neural Network CompressionPreprint
O’Neill, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.03669 · Cited by 149
BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale PretrainingPreprint
Qi, W., Gong, Y., Jiao, J., Yan, Y., Chen, W., Liu, D., Tang, K., Li, H., Chen, J., Zhang, R., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.15525 · Cited by 31
Sharp Models on Dull Hardware: Fast and Accurate Neural Machine Translation Decoding on the CPU
Devlin, J. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1300 · Cited by 30
Unsupervised Neural Machine Translation With Cross-Lingual Language Representation Agreement
Sun, H., Wang, R., Chen, K., Utiyama, M., Sumita, E., & Zhao, T. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.2982282 · Cited by 30
Extremely Small BERT Models from Mixed-Vocabulary Training
Zhao, S., Gupta, R., Song, Y., & Zhou, D. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.238 · Cited by 41
Transferring Inductive Biases through Knowledge Distillation
Abnar, S., Dehghani, M., & Zuidema, W. (2020) · arXiv · doi:10.48550/arxiv.2006.00555 · Cited by 30
Metadata
- Authors
- Kim, Y., & Rush, A. M.
- Affiliations
- Harvard University (US)
- Venue
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Published
- 2016
- Pages
- 1317-1327
- OpenAlex
- W2963736842
- Semantic Scholar
- 57a10537978600fd33dcdd48922c791609a4851a
- Cited by
- 836
- References
- 53
- Citations by year
- 2026: 36 · 2025: 59 · 2024: 52 · 2023: 137 · 2022: 115 · 2021: 157 · 2020: 143 · 2019: 75 · 2018: 42 · 2017: 16 · 2016: 4
- FWCI
- 24.59
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- knowledge distillation, neural machine translation, model compression, weight pruning, teacher-student models, parameter reduction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-23, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-23 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
