The DOI matches its Crossref record; 27 of the 29 references it cites were found in a registry or an index.
Generating Sentences by Editing Prototypes
Open accessAbstract
We propose a new generative language model for sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional language models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perplexity on language modeling and generates higher quality outputs according to human evaluation. Furthermore, the model gives rise to a latent edit vector that captures interpretable semantics such as sentence similarity and sentence-level analogies.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore, which allows them to learn through explicitly memorizing the training datapoints.”
From Efficient Nearest Neighbor Language Models (2021) · cites this paper as Guu et al., 2018
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Prompt augmentation is closely related to retrieval-based methods that provide more textual context to the model to improve performance [37], a method that has also been shown to be effective in prompt-based learning [99].”
From Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2023) · cites this paper as [37]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 3×
“Interestingly, the top-10 performance of our model in Table 5 is nearly as good as the performance of GloVe vectors on the simpler lexical analogy task, despite the fact that the sentence prediction task is harder.”
MethodInfluentialEfficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 2×
“Our use of lexical similarity neighborhoods is comparable to context windows used in word vector training (Mikolov et al., 2013a).”
BackgroundMethodAuto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · cited 6×
“aining p(xjx0) as a conditional variational autoencoder (C-VAE) (it is conditioned on x0). We maximize the objective via SGD, approximating the gradient using the usual Monte Carlo estimate for VAEs (Kingma and Welling, 2014). Neural editor p edit(xjx0;z): We implement our neural editor as a left-to-right sequence-to-…”
MethodInfluentialSequence 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 · cited 2×
“Neural language models (Bengio et al., 2003) based upon recurrent neural networks and sequence-to-sequence architectures (Sutskever et al., 2014) have been widely used due to their flexibility and performance across a wide-range of NLP tasks (Ju-rafsky and Martin, 2000; Kalchbrenner and Blun-som,…”
BackgroundMethodA Global Geometric Framework for Nonlinear Dimensionality Reduction
Tenenbaum, J. B., Silva, V. D., & Langford, J. C. (2000) · Science · doi:10.1126/science.290.5500.2319 · Cited by 13,585 · cited 1×
“More generally, results in manifold learning demonstrate that a weak metric such as lexical similarity can be used to extract semantic similarity through distributional statistics (Tenenbaum et al., 2000; Hashimoto et al., 2016).”
BackgroundOn Estimation of a Probability Density Function and Mode
Parzen, E. (1962) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177704472 · Cited by 10,585 · cited 1×
“From a generative modeling perspective, editing randomly sampled training sentences closely resembles nonparametric kernel density estimation (Parzen, 1962) where one samples points from a training set, and adds noise to smooth the density.”
BackgroundGoogle's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319 · cited 2×
“Our work is motivated by an emerging consensus that attention-based mechanisms (Bahdanau et al., 2015) can substantially improve performance on various sequence to sequence tasks by capturing more information from the input sequence (Wu et al., 2016; Vaswani et al., 2017).”
BackgroundMethodAn Introduction to Variational Methods for Graphical Models
Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., & Saul, L. K. (1999) · Machine Learning · doi:10.1023/a:1007665907178 · Cited by 3,791
Linguistic Regularities in Continuous Space Word Representations
Mikolov, T., Yih, W.-T., & Zweig, G. (2013) · North American Chapter of the Association for Computational Linguistics · Cited by 2,912
Generating Sentences from a Continuous Space
Bowman, S. R., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R., & Bengio, S. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1002 · Cited by 2,061 · cited 10×
“Second, our parameterization avoids collapsing the latent code, which is a serious problem with variational autoencoders in practice (Bowman et al., 2016).”
BackgroundMethodInfluentialA Diversity-Promoting Objective Function for Neural Conversation Models
Li, J., Galley, M., Brockett, C., Gao, J., & Dolan, B. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1014 · Cited by 1,926 · cited 3×
“Many NLM systems have noted an undesirable tradeoff between grammaticality and diversity, where a temperature low enough to enforce grammaticality results in short and generic utterances (Li et al., 2016).”
BackgroundInfluentialTutorial on Variational Autoencoders
Doersch, C. (2016) · arXiv · doi:10.48550/arxiv.1606.05908 · Cited by 1,470 · cited 2×
“in Equation 1) by only summing over x0that are lexically similar to x. 2.We lower bound the expectation over the edit prior (in Equation 2) using the evidence lower bound (ELBO) (Jordan et al., 1999; Doersch, 2016) which can be effectively approximated. We describe and motivate these approximations in Sections 3.1 and…”
BackgroundMethodInfluentialFraming Image Description as a Ranking Task: Data, Models and Evaluation Metrics
Hodosh, M., Young, P., & Hockenmaier, J. (2013) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3994 · Cited by 1,314 · cited 1×
“For example, in the image captioning literature (Hodosh et al., 2013), Kuznetsova (2013) and Mason (2014) proposed to generate image captions by first retrieving a prototype caption based on an image context, and then applying sentence compression to tailor the prototype to a particular image.”
BackgroundRecurrent Continuous Translation Models
Kalchbrenner, N., & Blunsom, P. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1176 · Cited by 1,232 · cited 2×
“, 2003) have been widely used due to their flexibility and performance across a wide range of NLP tasks (Kalchbrenner and Blunsom, 2013; Hahn and Mani, 2000; Ritter et al., 2011).”
BackgroundOne Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., & Robinson, T. (2013) · arXiv · doi:10.48550/arxiv.1312.3005 · Cited by 1,051
Writing research and the writer.
Hayes, J. R., & Flower, L. S. (1986) · American Psychologist · doi:10.1037//0003-066x.41.10.1106 · Cited by 603 · cited 2×
“Indeed, it is difficult even for humans to write complex text from scratch in a single pass; we often create an initial draft and incrementally revise it (Hayes and Flower, 1986).”
BackgroundData-Driven Response Generation in Social Media
Ritter, A., Cherry, C., & Dolan, W. B. (2011) · NPARC · Cited by 565
SemEval-2014 Task 10: Multilingual Semantic Textual Similarity
Agirre, E., Banea, C., Cardie, C., Cer, D., Diab, M., Gonzalez-Agirre, A., Guo, W., Mihalcea, R., Rigau, G., & Wiebe, J. (2014) · Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) · doi:10.3115/v1/s14-2010 · Cited by 490 · cited 1×
“10 545 similarity assessments pairs were collected through Amazon Mechanical Turk following Agirre (2014), with the same scale and prompt.”
MethodScalable Modified Kneser-Ney Language Model Estimation
Heafield, K., Pouzyrevsky, I., Clark, J. H., & Koehn, P. (2013) · Cited by 442
The challenges of automatic summarization
Hahn, U., & Mani, I. (2000) · Computer · doi:10.1109/2.881692 · Cited by 348 · cited 4×
“…to generate sentences is a core component of many NLP systems, including machine translation (Kalchbrenner and Blunsom, 2013; Koehn et al., 2007), summarization (Hahn and Mani, 2000; Nallapati et al., 2016), speech recognition (Ju-rafsky and Martin, 2000), and dialogue (Ritter et al., 2011).”
BackgroundInfluentialSimulation of the von mises fisher distribution
Wood, A. T. A. (1994) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610919408813161 · Cited by 180 · cited 1×
“This distribution is straightforward to use as part of a variational autoen-coder, as sampling can be easily performed using the reparameterization trick and the rejection sampler of Wood (1994).”
MethodGenerating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
Shao, Y., Gouws, S., Britz, D., Goldie, A., Strope, B., & Kurzweil, R. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1235 · Cited by 179 · cited 1×
“At the same time, naive strategies to increase diversity have been shown to compromise grammaticality (Shao et al., 2017), suggesting that current NLMs may lack the inductive bias to faithfully represent the full diversity of complex utterances.”
BackgroundWord Embeddings as Metric Recovery in Semantic Spaces
Hashimoto, T., Alvarez-Melis, D., & Jaakkola, T. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00098 · Cited by 103 · cited 1×
“More generally, results in manifold learning demonstrate that a weak metric such as lexical similarity can be used to extract semantic similarity through distributional statistics (Tenenbaum et al., 2000; Hashimoto et al., 2016).”
BackgroundSelf-citationGeneralizing Image Captions for Image-Text Parallel Corpus
Кузнецова, П., Ordóñez, V., Berg, A., Berg, T. L., & Choi, Y. (2013) · Cited by 73
Search Engine Guided Non-Parametric Neural Machine TranslationPreprint
Gu, J., Wang, Y., Cho, K., & Li, V. O. K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07267 · Cited by 32 · cited 1×
“For example, Song (2016) en-sembled a retrieval system and an NLM for dialogue, using the NLM to transform the retrieved ut-terance, and Gu (2017) used an off-the-shelf search engine system to retrieve and condition on training set examples.”
MethodSyntax-based Rewriting for Simultaneous Machine Translation
He, H., Grissom, A., Morgan, J., Boyd-Graber, J. L., & Daumé, H. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1006 · Cited by 24
Domain-Specific Image Captioning
Mason, R., & Eugene Charniak, D. (2014) · Conference on Computational Natural Language Learning · doi:10.3115/v1/w14-1602 · Cited by 12
Research works printed but not linked: 1
- Bengio Y., 2003, Journal of machine learning research, 3, 1137
Cited by
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361
“Prompt augmentation is closely related to retrieval-based methods that provide more textual context to the model to improve performance [37], a method that has also been shown to be effective in prompt-based learning [99].”
MethodRetrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101
“Such tasks include open-domain question answering [5, 25], fact checking [50], fact completion [42], long-form question answering [12], Wikipedia article generation [32], dialogue [36, 59, 9, 13], translation [16], and language modeling [17, 23].”
BackgroundAdversarial Example Generation with Syntactically Controlled Paraphrase Networks
Iyyer, M., Wieting, J., Gimpel, K., & Zettlemoyer, L. (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/n18-1170 · Cited by 615
“Shen et al. (2017) perform style transfer on non-parallel texts, while Guu et al. (2017) generate novel sentences from prototypes; again, these methods are not necessarily seeking to generate meaning-preserving paraphrases, merely transformed sentences that have an altered style.”
BackgroundWhat Makes Good In-Context Examples for GPT-3?
Liu, J., Shen, D., Zhang, Y., Dolan, B., Carin, L., & Chen, W. (2022) · Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures · doi:10.18653/v1/2022.deelio-1.10 · Cited by 563
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352
“Prompt augmentation is closely related to retrieval-based methods that provide more textual context to the model to improve performance [37], a method that has also been shown to be effective in prompt-based learning [99].”
Method
Metadata
- Authors
- Guu, K., Hashimoto, T. B., Oren, Y., & Liang, P.
- Affiliations
- Stanford University (US)
- Corresponding author
- Guu, Kelvin
- Hashimoto, Tatsunori B.
- Oren, Yonatan
- Liang, Percy
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2018-12
- Volume
- 6
- Pages
- 437-450
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W2963018920
- Cited by
- 300
- References
- 29
- Citations by year
- 2026: 4 · 2025: 7 · 2024: 7 · 2023: 30 · 2022: 30 · 2021: 48 · 2020: 56 · 2019: 72 · 2018: 44
- FWCI
- 30.55
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Defense Advanced Research Projects Agency
- Army Research Office (W911NF-15-1-, W911NF, W911NF-15)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- sentence generation, generative language models, sentence similarity, perplexity, interpretability
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.