LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval

William Bruno, Dan Roth


Abstract
Natural language inference has trended toward studying contexts beyond the sentence level. An important application area is law: past cases often do not foretell how they apply to new situations and implications must be inferred. This paper introduces LawngNLI, constructed from U.S. legal opinions with automatic labels with high human-validated accuracy. Premises are long and multigranular. Experiments show two use cases. First, LawngNLI can benchmark for in-domain generalization from short to long contexts. It has remained unclear if large-scale long-premise NLI datasets actually need to be constructed: near-top performance on long premises could be achievable by fine-tuning using short premises. Without multigranularity, benchmarks cannot distinguish lack of fine-tuning on long premises versus domain shift between short and long datasets. In contrast, our long and short premises share the same examples and domain. Models fine-tuned using several past NLI datasets and/or our short premises fall short of top performance on our long premises. So for at least certain domains (such as ours), large-scale long-premise datasets are needed. Second, LawngNLI can benchmark for implication-based retrieval. Queries are entailed or contradicted by target documents, allowing users to move between arguments and evidence. Leading retrieval models perform reasonably zero shot on a LawngNLI-derived retrieval task. We compare different systems for re-ranking, including lexical overlap and cross-encoders fine-tuned using a modified LawngNLI or past NLI datasets. LawngNLI can train and test systems for implication-based case retrieval and argumentation.
Anthology ID:
2022.findings-emnlp.369
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5019–5043
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.369
DOI:
10.18653/v1/2022.findings-emnlp.369
Bibkey:
Cite (ACL):
William Bruno and Dan Roth. 2022. LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5019–5043, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval (Bruno & Roth, Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.369.pdf