2000 character limit reached
Reframing Tax Law Entailment as Analogical Reasoning
Published 12 Jan 2024 in cs.CL and cs.AI | (2401.06715v1)
Abstract: Statutory reasoning refers to the application of legislative provisions to a series of case facts described in natural language. We re-frame statutory reasoning as an analogy task, where each instance of the analogy task involves a combination of two instances of statutory reasoning. This increases the dataset size by two orders of magnitude, and introduces an element of interpretability. We show that this task is roughly as difficult to Natural Language Processing models as the original task. Finally, we come back to statutory reasoning, solving it with a combination of a retrieval mechanism and analogy models, and showing some progress on prior comparable work.
- A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering. In: Proceedings of the Natural Legal Language Processing Workshop 2020 co-located with KDD 2020, August 24, 2020. vol. 2645 of CEUR Workshop Proceedings. CEUR-WS.org; 2020. p. 31-8.
- Solving Word Analogies: A Machine Learning Perspective. In: ECSQARU 2019, Belgrade, Serbia, September 18-20, 2019, Proceedings. vol. 11726 of Lecture Notes in Computer Science. Springer; 2019. p. 238-50.
- McCarty LT. Reflections on ”Taxman”: An Experiment in Artificial Intelligence and Legal Reasoning. Harvard Law Review. 1977;90:837.
- Sherman DM. A Prolog Model of The Income Tax Act Of Canada. ICAIL. 1987.
- The British Nationality Act as a Logic Program. Commun ACM. 1986;29(5):370-86.
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1. Association for Computational Linguistics; 2019. p. 4171-86.
- Language Models are Few-Shot Learners. vol. 33; 2020. p. 1877-901.
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In: NeurIPS; 2022. .
- Large Language Models are Zero-Shot Reasoners. In: NeurIPS; 2022. .
- Can GPT-3 Perform Statutory Reasoning? CoRR. 2023;abs/2302.06100.
- LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models. arXiv preprint arXiv:230811462. 2023.
- Holzenberger N, Van Durme B. Factoring Statutory Reasoning as Language Understanding Challenges. In: ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021. Association for Computational Linguistics; 2021. p. 2742-58.
- Automatic semantics extraction in law documents. In: ICAIL, June 6-11, 2005, Bologna, Italy. ACM; 2005. p. 133-40.
- Combining NLP approaches for rule extraction from legal documents. In: MIREL; 2016. .
- Prade H, Richard G. Analogical Proportions: Why They Are Useful in AI. In: IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021; 2021. p. 4568-76.
- Lepage Y, Denoual E. Purest ever example-based machine translation: Detailed presentation and assessment. Mach Transl. 2005;19(3-4):251-82.
- Learning a Distance Metric from Relative Comparisons between Quadruplets of Images. Int J Comput Vis. 2017;121(1):65-94.
- Visual analogy: Deep learning versus compositional models. CoRR. 2021.
- Fahandar MA, Hüllermeier E. Analogical Embedding for Analogy-Based Learning to Rank. In: IDA 2021, Porto, Portugal, April 26-28, 2021, Proceedings. vol. 12695 of Lecture Notes in Computer Science. Springer; 2021. p. 76-88.
- Efficient Estimation of Word Representations in Vector Space. In: ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings; 2013. .
- Glove: Global Vectors for Word Representation. In: EMNLP 2014, October 25-29, 2014, Doha, Qatar. ACL; 2014. p. 1532-43.
- Linguistic Regularities in Continuous Space Word Representations. In: Proceedings of the 2013 conference of the north american chapter of the association for computational linguistics: Human language technologies; 2013. p. 746-51.
- Learning Analogy-Preserving Sentence Embeddings for Answer Selection. In: CoNLL 2019, Hong Kong, China, November 3-4, 2019. Association for Computational Linguistics; 2019. p. 910-9.
- Mao W, Lepage Y. Embedding-To-Embedding Method Based on Autoencoder for Solving Sentence Analogies. In: ICCBR-WS 2023 co-located. vol. 3438 of CEUR Workshop Proceedings; 2023. .
- Brüninghaus S, Ashley KD. Predicting Outcomes of Case-Based Legal Arguments. In: ICAIL 2003, Edinburgh, Scotland, UK, June 24-28, 2003. ACM; 2003. p. 233-42.
- Combining a Legal Knowledge Model with Machine Learning for Reasoning with Legal Cases. In: ICAIL 2023, June 19–23, 2023, Braga, Portugal. ACM; 2023. .
- Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems. vol. 35; 2022. p. 27730-44. Available from: https://openreview.net/forum?id=TG8KACxEON.
- OpenAI. GPT-4 Technical Report. ArXiv. 2023;abs/2303.08774. Available from: https://api.semanticscholar.org/CorpusID:257532815.
- Reimers N, Gurevych I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Association for Computational Linguistics; 2019. p. 3980-90.
- Dense Passage Retrieval for Open-Domain Question Answering. In: EMNLP 2020, Online, November 16-20, 2020. Association for Computational Linguistics; 2020. p. 6769-81.
- On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning. In: ACL 2023, Toronto, Canada, July 9-14, 2023. Association for Computational Linguistics; 2023. p. 4454-70.
- Optuna: A Next-generation Hyperparameter Optimization Framework. In: KDD 2019. ACM; 2019. p. 2623-31.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.