A Surprisingly Robust Trick for the Winograd Schema Challenge
Open accessAbstract
The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning.In this paper, we show that the performance of three language models on WSC273 consistently and robustly improves when finetuned on a similar pronoun disambiguation problem dataset (denoted WSCR).We additionally generate a large unsupervised WSClike dataset.By fine-tuning the BERT language model both on the introduced and on the WSCR dataset, we achieve overall accuracies of 72.5% and 74.7% on WSC273 and WNLI, improving the previous state-of-theart solutions by 8.8% and 9.6%, respectively.Furthermore, our fine-tuned models are also consistently more accurate on the "complex" subsets of WSC273, introduced by Trichelair et al. (2018).
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
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.
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?
Including DPR data in the multi-task mixture is known to boost WSC task performance.
“including DPR data in the multi-task mixture, which is known to boost WSC task performance(Kocijan et al., 2019).”
From The Power of Scale for Parameter-Efficient Prompt Tuning (2021) · cites this paper as Kocijan et al., 2019
The Definite Pronoun Resolution section identifies DPR as the dataset called WSCR in the paper. The Evaluation section reports that fine-tuning on WSCR consistently improves WSC273 performance, but it does not establish that adding DPR to a multi-task mixture has the same effect. (LLM, conf=0.87)
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.
The citation lists haven’t been fetched yet
References 22 · Cited by 81
Research works printed but not linked: 15
- Ernest Davis, Leora Morgenstern, and Charles L. Or- tiz. 2017. The first Winograd Schema Challenge at IJCAI-16. AI Magazine, 38(3):97-98.
- Ali Emami, Noelia De La Cruz, Adam Trischler, Kaheer Suleman, and Jackie Chi Kit Cheung. 2018. A knowledge hunting framework for common sense reasoning. Computing Research Repository, arXiv:1810.01375. · arXiv
- Hany Hassan, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Feder- mann, Xuedong Huang, Marcin Junczys-Dowmunt, William Lewis, Mu Li, Shujie Liu, Tie-Yan Liu, Renqian Luo, Arul Menezes, Tao Qin, Frank Seide, Xu Tan, Fei Tian, Lijun Wu, Shuangzhi Wu, Yingce Xia, Dongdong Zhang, Zhirui Zhang, and Ming Zhou. 2018. Achieving human parity on automatic Chinese to English news translation. Computing Re- search Repository, arXiv:1803.05567. · arXiv
- Jeremy Howard and Sebastian Ruder. 2018. Fine-tuned language models for text classification. Computing Research Repository, arXiv:1801.06146. · arXiv
- Rie Johnson and Tong Zhang. 2017. Deep pyramid convolutional neural networks for text categoriza- tion. In Proceedings of ACL, pages 562-570. ACL. · DOI
- Hector J. Levesque, Ernest Davis, and Leora Mor- genstern. 2011. The Winograd Schema Challenge. AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning, 46.
- Hector J. Levesque, Ernest Davis, and Leora Morgen- stern. 2012. The Winograd Schema Challenge. In Proceedings of KR. AAAI Press.
- Xiaodong Liu, Pengcheng He, Weizhu Chen, and Jian- feng Gao. 2019. Multi-task deep neural networks for natural language understanding. Computing Re- search Repository, arXiv:1901.11504. · arXiv
- Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David Mc- Closky. 2014. The Stanford CoreNLP natural lan- guage processing toolkit. In Association for Compu- tational Linguistics (ACL) System Demonstrations, pages 55-60.
- Juri Opitz and Anette Frank. 2018. Addressing the Winograd Schema Challenge as a sequence rank- ing task. In Proceedings of the First International Workshop on Language Cognition and Computa- tional Models, pages 41-52. ACL.
- Altaf Rahman and Vincent Ng. 2012. Resolving com- plex cases of definite pronouns: The Winograd Schema Challenge. In Proceedings of EMNLP.
- Paul Trichelair, Ali Emami, Jackie Chi Kit Cheung, Adam Trischler, Kaheer Suleman, and Fernando Diaz. 2018. On the evaluation of common-sense reasoning in natural language understanding. Com- puting Research Repository, arXiv:1811.01778. · arXiv
- T. H. Trinh and Q. V. Le. 2018. A Simple Method for Commonsense Reasoning. Computing Research repository, arXiv:1806.02847. · arXiv
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Computing Research Repository, arXiv:1706.03762. · arXiv
- Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. GLUE: A multi-task benchmark and analysis plat- form for natural language understanding. In Pro- ceedings of ICLR.
- Authors
- Kocijan, V., Cretu, A.-M., Camburu, O.-M., Yordanov, Y., & Lukasiewicz, T.
- Affiliations
- University of Oxford (GB)
- Venue
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Published
- 2019
- Pages
- 4837-4842
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2945290257
- Cited by
- 81
- References
- 22
- Citations by year
- 2026: 1 · 2024: 2 · 2023: 5 · 2022: 6 · 2021: 33 · 2020: 24 · 2019: 10
- FWCI
- 6.98
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- UCL Discovery (University College London) (submittedVersion)
- Spiral (Imperial College London) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- Alan Turing Institute (EP/N510129/1., N510129)
- Engineering and Physical Sciences Research Council (N510129, EP/N510129/, EP/N510129/1, EP/R013667/1, EPSRC grant EP/N510129/1, EP/P020275/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- Winograd Schema Challenge, commonsense reasoning, BERT fine-tuning, natural language understanding
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
