The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
oLMpics-On What Language Model Pre-training Captures
Open accessAbstract
Recent success of pre-trained language models (LMs) has spurred widespread interest in the language capabilities that they possess. However, efforts to understand whether LM representations are useful for symbolic reasoning tasks have been limited and scattered. In this work, we propose eight reasoning tasks, which conceptually require operations such as comparison, conjunction, and composition. A fundamental challenge is to understand whether the performance of a LM on a task should be attributed to the pre-trained representations or to the process of fine-tuning on the task data. To address this, we propose an evaluation protocol that includes both zero-shot evaluation (no fine-tuning), as well as comparing the learning curve of a fine-tuned LM to the learning curve of multiple controls, which paints a rich picture of the LM capabilities. Our main findings are that: (a) different LMs exhibit qualitatively different reasoning abilities, e.g., RoBERTa succeeds in reasoning tasks where BERT fails completely; (b) LMs do not reason in an abstract manner and are context-dependent, e.g., while RoBERTa can compare ages, it can do so only when the ages are in the typical range of human ages; (c) On half of our reasoning tasks all models fail completely. Our findings and infrastructure can help future work on designing new datasets, models, and objective functions for pre-training.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
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
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, 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/n18-1202 · Cited by 11,983
WordNet: An Electronic Lexical Database
Kilgarriff, A., & Fellbaum, C. (2000) · Language · doi:10.2307/417141 · Cited by 11,464
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
WordNet: An Electronic Lexical Database
(1998) · The MIT Press eBooks · doi:10.7551/mitpress/7287.001.0001 · Cited by 4,857
Wikidata: a free collaborative knowledgebase
Vrandečić, D., & Krötzsch, M. (2014) · Communications of the ACM · doi:10.1145/2629489 · Cited by 3,342
Language Models as Knowledge Bases?
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1250 · Cited by 1,834
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W., Salakhutdinov, R., & Manning, C. D. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1259 · Cited by 1,804
Generalized Quantifiers and Natural Language
Barwise, J., & Cooper, R. (1981) · Studies in Cognitive Systems · doi:10.1007/978-94-009-2727-8_10 · Cited by 1,622
BERT Rediscovers the Classical NLP Pipeline
Tenney, I., Das, D., & Pavlick, E. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1452 · Cited by 1,307
Enhanced LSTM for Natural Language Inference
Chen, Q., Zhu, X., Ling, Z.-H., Wei, S., Jiang, H., & Inkpen, D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1152 · Cited by 1,113
Lewis, D. (1975) · Formal Semantics of Natural Language · doi:10.1017/cbo9780511897696.003 · Cited by 1,042
How Can We Know What Language Models Know?
Jiang, Z., Xu, F. F., Araki, J., & Neubig, G. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00324 · Cited by 1,002
Neural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
Talmor, A., Herzig, J., Lourie, N., & Berant, J. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1421 · Cited by 941
Self-citationConceptNet 5.5: An Open Multilingual Graph of General Knowledge
Speer, R., Chin, J., & Havasi, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.03975 · Cited by 758
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
Linzen, T., Dupoux, E., & Goldberg, Y. (2016) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00115 · Cited by 737
Self-citationSWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
Zellers, R., Bisk, Y., Schwartz, R., & Choi, Y. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1009 · Cited by 690
Adversarial NLI: A New Benchmark for Natural Language Understanding
Nie, Y., Williams, A., Dinan, E., Bansal, M., Weston, J., & Kiela, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.441 · Cited by 656
Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
Mihaylov, T., Clark, P., Khot, T., & Sabharwal, A. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1260 · Cited by 649
(2019) · doi:10.18653/v1/n19-1419 · Cited by 601
What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models
Ettinger, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00298 · Cited by 511
Analysis Methods in Neural Language Processing: A Survey
Belinkov, Y., & Glass, J. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00254 · Cited by 477
Constructing Datasets for Multi-hop Reading Comprehension Across Documents
Welbl, J., Stenetorp, P., & Riedel, S. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00021 · Cited by 456
Dissecting Contextual Word Embeddings: Architecture and Representation
Peters, M., Neumann, M., Zettlemoyer, L., & Yih, W.-T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1179 · Cited by 434
Designing and Interpreting Probes with Control Tasks
Hewitt, J., & Liang, P. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1275 · Cited by 393
Assessing BERT's Syntactic Abilities
Goldberg, Y. (2019) · arXiv · doi:10.48550/arxiv.1901.05287 · Cited by 385
Self-citationLearning and Evaluating General Linguistic IntelligencePreprint
Yogatama, D., d’Autume, C. D. M., Connor, J. T., Kočiský, T., Chrzanowski, M., Kong, L., Lazaridou, A., Wang, L., Yu, L., Dyer, C., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.11373 · Cited by 242
Open Sesame: Getting inside BERT’s Linguistic Knowledge
Lin, Y., Tan, Y. C., & Frank, R. (2019) · Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w19-4825 · Cited by 237
Do NLP Models Know Numbers? Probing Numeracy in Embeddings
Wallace, E., Wang, Y., Li, S., Singh, S., & Gardner, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1534 · Cited by 227
Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly
Kassner, N., & Schütze, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.698 · Cited by 223
Reporting bias and knowledge acquisition
Gordon, J., & Van Durme, B. (2013) · Proceedings of the 2013 workshop on Automated knowledge base construction · doi:10.1145/2509558.2509563 · Cited by 169
Just Say No to Single Embeddings: Why Your AI Needs Multiple Perspectives
Coenen, A., Reif, E., Yuan, A., Kim, B., Pearce, A., Viégas, F., & WATTENBERG, M. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.02715 · Cited by 163
Probing for semantic evidence of composition by means of simple classification tasks
Ettinger, A., Elgohary, A., & Resnik, P. (2016) · Workshop on Evaluating Vector-Space Representations for NLP · doi:10.18653/v1/w16-2524 · Cited by 147
The Description Length of Deep Learning modelsPreprint
Blier, L., & Ollivier, Y. (2018) · Neural Information Processing Systems · doi:10.48550/arxiv.1802.07044 · Cited by 128
Investigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs
Warstadt, A., Cao, Y. H., Grosu, I., Peng, W., Blix, H., Nie, Y., Alsop, A., Bordia, S., Liu, H., Parrish, A., et al. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1286 · Cited by 105
Knowledge of animal appearance among sighted and blind adults
Kim, J. S., Elli, G. V., & Bedny, M. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1900952116 · Cited by 103
Premise Selection for Theorem Proving by Deep Graph EmbeddingPreprint
Wang, M., Tang, Y., Wang, J., & Deng, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.09994 · Cited by 92
Still a Pain in the Neck: Evaluating Text Representations on Lexical Composition
Shwartz, V., & Dagan, I. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00277 · Cited by 78
Verb Physics: Relative Physical Knowledge of Actions and Objects
Forbes, M., & Choi, Y. (2017) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p17-1025 · Cited by 77
How Large Are Lions? Inducing Distributions over Quantitative Attributes
Elazar, Y., Mahabal, A., Ramachandran, D., Bedrax-Weiss, T., & Roth, D. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1388 · Cited by 58
Self-citationDiversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets
Rozen, O., Shwartz, V., Aharoni, R., & Dagan, I. (2019) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k19-1019 · Cited by 35
On Making Reading Comprehension More Comprehensive
Gardner, M., Berant, J., Hajishirzi, H., Talmor, A., & Min, S. (2019) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/d19-5815 · Cited by 33
Self-citationIs the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts
Pezzelle, S., & Fernández, R. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1285 · Cited by 21
Extracting Commonsense Properties from Embeddings with Limited Human Guidance
Yang, Y., Birnbaum, L., Wang, J., & Downey, D. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-2102 · Cited by 20
Elazar, Y., & Goldberg, Y. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00280 · Cited by 20
Self-citationAre Elephants Bigger than Butterflies? Reasoning about Sizes of ObjectsPreprint
Bagherinezhad, H., Hajishirzi, H., Choi, Y., & Farhadi, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.00753 · Cited by 19
Cited by
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.139 · Cited by 2,824
A primer in BERTology: What we know about how BERT works
Rogers, A., Kovaleva, O., & Rumshisky, A. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00349 · Cited by 1,552
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey
Min, B., Ross, H., Sulem, E., Veyseh, A. P. B., Nguyen, T. H., Sainz, O., Agirre, E., Heintz, I., & Roth, D. (2024) · ACM Computing Surveys · doi:10.1145/3605943 · Cited by 1,387
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.295 · Cited by 1,380
Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference
Schick, T., & Schütze, H. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.20 · Cited by 1,305
Metadata
- Authors
- Talmor, A., Elazar, Y., Goldberg, Y., & Berant, J.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2020-12
- Volume
- 8
- Pages
- 743-758
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W2998696444
- Cited by
- 271
- References
- 51
- FWCI
- 23.01
- Type
- journal article
- Language
- en
- Open access
- diamond
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.