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 401–500 of 841
Accelerating Multiple Intent Detection and Slot Filling via Targeted Knowledge Distillation
Cheng, X., Zhu, Z., Xu, W., et al. (2023) · doi:10.18653/v1/2023.findings-emnlp.597 · Cited by 9
Limitations of Knowledge Distillation for Zero-shot Transfer Learning
Soltan, S., Khan, H., & Hamza, W. (2021) · Workshop on Simple and Efficient Natural Language Processing (SustaiNLP) · doi:10.18653/v1/2021.sustainlp-1.3 · Cited by 10
Scalable Transformers for Neural Machine TranslationPreprint
Gao, P., Geng, S., Qiao, Y., Wang, X., Dai, J., & Li, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02242 · Cited by 11
metapredict: a fast, accurate, and easy-to-use predictor of consensus disorder and structurePreprint
Emenecker, R. J., Griffith, D., & Holehouse, A. S. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.05.30.446349 · Cited by 10
Distillation of Diffusion Features for Semantic Correspondence
Fundel, F., Schusterbauer, J., Hu, V. T., & Ommer, B. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00658 · Cited by 10
Bayesian teaching enables probabilistic reasoning in large language models
Qiu, L., Sha, F., Allen, K. R., Kim, Y., Linzen, T., & van Steenkiste, S. (2026) · Nature Communications · doi:10.1038/s41467-025-67998-6 · Cited by 14
Self-citationFindings of the Second Workshop on Neural Machine Translation and Generation
Birch, A., Finch, A., Luong, M.-T., Neubig, G., & Oda, Y. (2018) · doi:10.18653/v1/w18-2701 · Cited by 8
Deep Learning Model Compression Techniques: Advances, Opportunities, and Perspective
Msuya, H., & Maiseli, B. J. (2023) · Tanzania Journal of Engineering and Technology · doi:10.52339/tjet.v42i2.853 · Cited by 8
Distilling Calibrated Knowledge for Stance Detection
Li, Y., & Caragea, C. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.393 · Cited by 8
Liu, C., Li, Y., Chen, C., Kuang, H., Ma, X., Zou, X., Liu, J., Lu, Z., Zhang, Z., & Liu, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3550841 · Cited by 9
EDiT: Interpreting Ensemble Models via Compact Soft Decision Trees
Yoo, J., & Sael, L. (2019) · Proceedings · doi:10.1109/icdm.2019.00187 · Cited by 8
Edinburgh’s Submissions to the 2020 Machine Translation Efficiency Task
Bogoychev, N., Grundkiewicz, R., Aji, A. F., et al. (2020) · doi:10.18653/v1/2020.ngt-1.26 · Cited by 8
Ding, H., Chen, K., & Huo, Q. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.3019917 · Cited by 8
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
Zhou, W., Ge, T., Xu, C., Xu, K., & Wei, F. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.45 · Cited by 13
Dynamic Multi-Branch Layers for On-Device Neural Machine Translation
Tan, Z., Yang, Z., Zhang, M., Liu, Q., Sun, M., & Liu, Y. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3153257 · Cited by 11
Collaborative Training of Acoustic Encoders for Speech Recognition
Nagaraja, V., Shi, Y., Venkatesh, G., Kalinli, O., Seltzer, M. L., & Chandra, V. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-354 · Cited by 8
Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor
Wang, X., Jiang, Y., Yan, Z., Jia, Z., Bách, N., Wang, T., Huang, Z., Huang, F., & Tu, K. (2021) · doi:10.18653/v1/2021.acl-long.46 · Cited by 11
GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation
Choubey, P. K., Currey, A., Mathur, P., & Dinu, G. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.123 · Cited by 21
Towards Compact and Fast Neural Machine Translation Using a Combined Method
Zhang, X., Chen, W., Wang, F., Xu, S., & Xu, B. (2017) · Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1154 · Cited by 8
Reinforced Zero-Shot Cross-Lingual Neural Headline Generation
Yana, A., Chen, Y., Yang, C. H., Liu, Z., & Sun, M. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.3009487 · Cited by 8
Efficient and High-Quality Neural Machine Translation with OpenNMT
Klein, G., Zhang, D., Chouteau, C., et al. (2020) · doi:10.18653/v1/2020.ngt-1.25 · Cited by 8
Semi-Supervised End-to-End ASR via Teacher-Student Learning with Conditional Posterior Distribution
Zhang, Z., Song, Y., Zhang, J.-S., et al. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1574 · Cited by 8
The Volctrans Neural Speech Translation System for IWSLT 2021
Zhao, C., Liu, Z., Jian, T., et al. (2021) · International Conference on Spoken Language Translation (IWSLT) · doi:10.18653/v1/2021.iwslt-1.6 · Cited by 8
Building a Multi-Domain Neural Machine Translation Model Using Knowledge Distillation
Mghabbar, I., & Ratnamogan, P. (2020) · Frontiers in artificial intelligence and applications · doi:10.3233/faia200335 · Cited by 9
Shared Growth of Graph Neural Networks via Prompted Free-Direction Knowledge Distillation
Feng, K., Miao, Y., Li, C., Yuan, Y., & Wang, G. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3543211 · Cited by 9
Knowledge Distillation in Object Detection: A Survey from CNN to Transformer
Shehzadi, T., Noor, R., Ifza, I., Liwicki, M., Stricker, D., & Afzal, M. Z. (2026) · Sensors · doi:10.3390/s26010292 · Cited by 10
An Empirical Study of Generation Order for Machine Translation
Chan, W., Stern, M., Kiros, J., & Uszkoreit, J. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.464 · Cited by 7
Zhang, H., Cheng, Y.-C., Kumar, S., et al. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746492 · Cited by 7
Audio-Driven Deformation Flow for Effective Lip Reading
Feng, D., Yang, S., Shan, S., & Chen, X. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956316 · Cited by 7
End-to-End Non-Autoregressive Image Captioning
Yu, H., Liu, Y., Qi, B., Hu, Z.-L., & Liu, H. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095338 · Cited by 7
Nearest Neighbor Non-autoregressive Text Generation
Niwa, A., Takase, S., & Okazaki, N. (2023) · Journal of Information Processing · doi:10.2197/ipsjjip.31.344 · Cited by 10
Calderon, N., Mukherjee, S., Reichart, R., & Kantor, A. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.818 · Cited by 14
What Do Compressed Multilingual Machine Translation Models Forget?
Mohammadshahi, A., Nikoulina, V., Berard, A., Brun, C., Henderson, J., & Besacier, L. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.317 · Cited by 13
LLM aided semi-supervision for efficient Extractive Dialog Summarization
Mishra, N., Sahu, G., Calixto, I., Abu–Hanna, A., & Laradji, I. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.670 · Cited by 13
Text Representation Distillation via Information Bottleneck Principle
Zhang, Y., Long, D., Li, Z., et al. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.888 · Cited by 7
Gowda, T., Kocmi, T., & Junczys-Dowmunt, M. (2023) · Conference on Machine Translation (WMT) · doi:10.18653/v1/2023.wmt-1.62 · Cited by 7
Efficient Deep Learning in Network Compression and Acceleration
Ge, S. (2018) · IntechOpen eBooks · doi:10.5772/intechopen.79562 · Cited by 8
MTSS: Learn from Multiple Domain Teachers and Become a Multi-Domain Dialogue Expert
Peng, S., Ji, F. Q., Lin, Z., Cui, S., Chen, H., & Zhang, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6384 · Cited by 6
Multi-Referenced Training for Dialogue Response Generation
Zhao, T., & Kawahara, T. (2021) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2021.sigdial-1.20 · Cited by 10
Not all parameters are born equal: Attention is mostly what you need
Bogoychev, N. (2021) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2021.blackboxnlp-1.28 · Cited by 7
Personalizing Speech Start Point and End Point Detection in ASR Systems from Speaker Embeddings
Jayasimha, A., & Paramasivam, P. (2021) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt48900.2021.9383516 · Cited by 7
Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer
Ma, Y., Chen, Y., Mao, X., & Li, Q. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.729 · Cited by 7
Efficient Image and Sentence Matching
Huang, Y., Wang, Y., & Wang, L. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3178485 · Cited by 8
Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting
Chen, Y., Liang, Q., Cheng, Z., Pu, S., Niu, Y., & Li, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19815-1_21 · Cited by 7
Attention as a Guide for Simultaneous Speech Translation
Papi, S., Negri, M., & Turchi, M. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.745 · Cited by 9
Better Simultaneous Translation with Monotonic Knowledge Distillation
Wang, S., Wu, J., Fan, K. C., et al. (2023) · Annual Meeting of the Association for Computational Linguistics (ACL) · doi:10.18653/v1/2023.acl-long.131 · Cited by 7
Better Language Models of Code through Self-Improvement
To, H. Q., Bui, N., Guo, J., & Nguyen, T. N. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.823 · Cited by 18
Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation
Miao, Z., Zhang, W., Su, J., Li, X., Luan, J., Chen, Y., Wang, B., & Zhang, M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.178 · Cited by 7
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
Lu, X., Brahman, F., West, P., Jung, J., Chandu, K. R., Ravichander, A., Ammanabrolu, P., Jiang, L., Ramnath, S., Dziri, N., et al. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.424 · Cited by 30
Improving Autoregressive NMT with Non-Autoregressive Model
Zhou, L., Zhang, J., & Zong, C. (2020) · doi:10.18653/v1/2020.autosimtrans-1.4 · Cited by 7
The NiuTrans System for WNGT 2020 Efficiency Task
Hu, C., Li, B., Li, Y., et al. (2020) · doi:10.18653/v1/2020.ngt-1.24 · Cited by 7
Train Once, and Decode As You Like
Tian, C., Wang, Y., Cheng, H., Lian, Y., & Zhang, Z. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.25 · Cited by 7
Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data
Bai, Y., Yi, J., Tao, J., Wen, Z., Tian, Z., & Zhang, S. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3066274 · Cited by 8
An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation
Woo, H., Lee, H., & Cho, S. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20845 · Cited by 7
Neural Machine Translation from Simplified TranslationsPreprint
Crego, J., & Sénellart, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06139 · Cited by 7
Hint-Based Training for Non-Autoregressive Machine TranslationPreprint
Li, Z., Lin, Z. J., He, D., Tian, F., Qin, T., Wang, L., & Liu, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06708 · Cited by 7
Fast Sequence Generation with Multi-Agent Reinforcement LearningPreprint
Guo, L., Liu, J., Zhu, X., & Lu, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.09698 · Cited by 7
Multi-receptive Field Distillation Network for seismic velocity model building
Lu, J., Wu, C., Huang, J., et al. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108547 · Cited by 6
High fidelity zero shot speaker adaptation in text to speech synthesis with denoising diffusion GAN
Liu, X., Ma, X., Song, W., Zhang, Y., & Zhang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-90507-0 · Cited by 6
Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation
Huang, F., Ke, P., & Huang, M. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00582 · Cited by 7
Pre-Trained Acoustic-and-Textual Modeling for End-To-End Speech-To-Text Translation
Zhang, W., Zhang, H., Liu, C., et al. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446635 · Cited by 6
Auto-DAS: Automated Proxy Discovery for Training-Free Distillation-Aware Architecture Search
Sun, H., Li, L., Dong, P., Wei, Z., & Shao, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72652-1_4 · Cited by 6
Sequence Distillation for Purely Sequence Trained Acoustic Models
Kanda, N., Fujita, Y., & Nagamatsu, K. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462619 · Cited by 7
Ensemble Distillation Approaches for Grammatical Error Correction
Fathullah, Y., Gales, M., & Malinin, A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413385 · Cited by 6
A Student-Teacher Architecture for Dialog Domain Adaptation Under the Meta-Learning Setting
Qian, K., Wei, W., & Zhou, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i15.17614 · Cited by 6
Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability
Huang, K., Liu, J., Huang, D., Xiong, D., Liu, Z., & Su, J. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.383 · Cited by 6
Elastic Knowledge Distillation by Learning From Recollection
Fu, Y., Li, S., Zhao, H., Wang, W., Fang, W., Zhuang, Y., Pan, Z., & Li, X. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3107317 · Cited by 6
Anticipation-Free Training for Simultaneous Machine Translation
Chang, C., Chuang, S.-P., & Lee, H.-Y. (2022) · International Conference on Spoken Language Translation (IWSLT) · doi:10.18653/v1/2022.iwslt-1.5 · Cited by 6
Deep Reinforcement Learning with Sparse Regularized Pruning and Compressing
Su, W., Li, Z., Yang, Z., et al. (2021) · China Automation Congress (CAC) · doi:10.1109/cac53003.2021.9727767 · Cited by 6
Lei, L. (2022) · Mobile Information Systems · doi:10.1155/2022/5632131 · Cited by 7
Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation
Deng, J., Chen, Z., Sun, H., Zhang, Z., Wu, J., Nakagawa, S., Ren, F., & Huang, M. (2023) · Research · doi:10.34133/research.0189 · Cited by 6
Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation
Liu, M., Bao, Y., Zhao, C., & Huang, S. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26555 · Cited by 7
Explicit Syntactic Guidance for Neural Text Generation
Li, Y., Cui, L., Yan, J., Yin, Y., Bi, W., Shi, S., & Zhang, Y. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.788 · Cited by 10
XLM-D: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation
Wang, Y., He, S., Chen, G., Chen, Y., & Jiang, D. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.466 · Cited by 7
Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation
Li, S., Zhang, P., Gan, G., Lv, X., Wang, B., Wei, V. J., & Jiang, X. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.475 · Cited by 7
Reconstruction of Word Embeddings from Sub-Word Parameters
Stratos, K. (2017) · Workshop on Subword and Character Level Models in NLP (SCLeM) · doi:10.18653/v1/w17-4119 · Cited by 7
Sound Natural: Content Rephrasing in Dialog Systems
Einolghozati, A., Gupta, A., Diedrick, K., & Gupta, S. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.414 · Cited by 7
Interpretable Foreground Object Search as Knowledge Distillation
Li, B., Zhuang, P.-Y., Gu, J. H., Li, M., & Tan, P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58604-1_12 · Cited by 6
Revisiting Knowledge Distillation for Image Captioning
Dong, J., Hu, Z., & Zhou, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-93046-2_52 · Cited by 6
A Survey on Mobile Edge Computing for Deep Learning
Choi, P., & Kwak, J. (2023) · International Conference on Information Networking · doi:10.1109/icoin56518.2023.10048953 · Cited by 6
CTC-based Non-autoregressive Speech Translation
Xu, C., Liu, X., Liu, X., Sun, Q., Zhang, Y., Yang, M., Dong, Q., Ko, T., Wang, M., Xiao, T., et al. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.744 · Cited by 9
YANMTT: Yet Another Neural Machine Translation Toolkit
Dabre, R., Kanojia, D., Sawant, C., & Sumita, E. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-demo.24 · Cited by 8
Compression of Acoustic Model via Knowledge Distillation and Pruning
Li, C., Zhu, L., Xu, S., Gao, P., & Xu, B. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545028 · Cited by 6
Putting Machine Translation in Context with the Noisy Channel ModelPreprint
Yu, L., Sartran, L., Stokowiec, W., Wang, L., Kong, L., Blunsom, P., & Dyer, C. (2019) · arXiv (Cornell University) · Cited by 6
Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary DataPreprint
Ye, M., Choudhary, D., Yu, J., Wen, E., Chen, Z., Yang, J., Park, J., Liu, Q., & Kejariwal, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.08655 · Cited by 10
Solvable Model for Inheriting the Regularization through Knowledge DistillationPreprint
Saglietti, L., & Zdeborová, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.00194 · Cited by 6
Structural Knowledge Distillation: Tractably Distilling Information for Structured PredictorPreprint
Wang, X., Jiang, Y., Yan, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05010 · Cited by 6
MC$^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative RecommendationPreprint
Chen, Z., Yao, J., Wang, F., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.12314 · Cited by 6
Multi-view fusion for universal translation quality estimation
Huang, H., Wu, S., Chen, K., Liang, X., Di, H., Yang, M., & Zhao, T. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102022 · Cited by 6
Test time adaptation for cross-domain sleep stage classification
Guo, H., Li, C., Peng, H., et al. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106980 · Cited by 5
MDCNN: Multi-Teacher Distillation-Based CNN for News Text Classification
Guo, X., Liu, Q., Hu, Y., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3555224 · Cited by 5
Learning Evaluation Models From Large Language Models for Sequence Generation
Wang, C., Zhou, H., Chang, K., Liu, T., Zhang, C., Yang, M., Du, Q., Xiao, T., Zhang, Y., & Zhu, J. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3587460 · Cited by 11
Recent Advances in Dialogue Machine Translation
Liu, S., Sun, Y., & Wang, L. (2021) · Information · doi:10.3390/info12110484 · Cited by 5
Two-Pass End-to-End ASR Model Compression
Dawalatabad, N., Vatsal, T., Gupta, A., Kim, S.-S., Singh, S., Gowda, D., & Kim, C. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688121 · Cited by 7
Zeng, C., Chen, J., Zhuang, T., Xu, R., Yang, H., Qin, Y. H., Tao, S., & Xiao, Y. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.424 · Cited by 5
A novel multi-domain machine reading comprehension model with domain interference mitigation
Zhou, C., Wang, Z., He, S., Zhang, H., & Su, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.05.102 · Cited by 5
SuperFormer: Continual learning superposition method for text classification
Zeman, M., Pucer, J. F., Kononenko, I., & Bosnić, Z. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.040 · Cited by 5
Improving Simultaneous Machine Translation with Monolingual Data
Deng, H., Ding, L., Liu, X., Zhang, M., Tao, D., & Zhang, M. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26497 · Cited by 7
stopes - Modular Machine Translation Pipelines
Andrews, P., Wenzek, G., Heffernan, K. S., Çelebi, O., Sun, A., Kamran, A., Guo, Y., Mourachko, A., Schwenk, H., & Fan, A. (2022) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/2022.emnlp-demos.26 · Cited by 5
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
