Filters








4 Hits in 2.7 sec

ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts [article]

Yuta Koreeda, Christopher D. Manning
2021 arXiv   pre-print
In this work, we propose "document-level natural language inference (NLI) for contracts", a novel, real-world application of NLI that addresses such problems.  ...  start and end tokens, and (2) employs more sophisticated context segmentation for dealing with long documents.  ...  Acknowledgements We used computational resource of AI Bridging Cloud Infrastructure (ABCI) provided by the National Institute of Advanced Industrial Science and Technology (AIST) for the experiments.  ... 
arXiv:2110.01799v1 fatcat:puxkmvettrc3rbkfspecrmctji

ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts

Yuta Koreeda, Christopher Manning
2021 Findings of the Association for Computational Linguistics: EMNLP 2021   unpublished
ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts Yuta Koreeda12 and Christopher D.  ...  // denotes a span border level natural language inference (NLI) for con- Examples of hypotheses: Receiving Party  ... 
doi:10.18653/v1/2021.findings-emnlp.164 fatcat:zy3qu72wurgbzkmojr4kcuuqku

SCROLLS: Standardized CompaRison Over Long Language Sequences [article]

Uri Shaham, Elad Segal, Maor Ivgi, Avia Efrat, Ori Yoran, Adi Haviv, Ankit Gupta, Wenhan Xiong, Mor Geva, Jonathan Berant, Omer Levy
2022 arXiv   pre-print
SCROLLS contains summarization, question answering, and natural language inference tasks, covering multiple domains, including literature, science, business, and entertainment.  ...  NLP benchmarks have largely focused on short texts, such as sentences and paragraphs, even though long texts comprise a considerable amount of natural language in the wild.  ...  Acknowledgements This research was supported in part by the Yandex Initiative for Machine Learning, the Tel Aviv University Data Science Center, the Shashua Fellowship, the Alon Scholarship, the 2021 Scholarship  ... 
arXiv:2201.03533v1 fatcat:uh25n7gtsvbd3ddmtojrbqnraa

Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters [article]

Tal Schuster, Sihao Chen, Senaka Buthpitiya, Alex Fabrikant, Donald Metzler
2022 arXiv   pre-print
Natural Language Inference (NLI) has been extensively studied by the NLP community as a framework for estimating the semantic relation between sentence pairs.  ...  Then, we develop new aggregation methods to allow operating over full documents, reaching state-of-the-art performance on the ContractNLI dataset.  ...  EN Dracula is a novel by Bram Stoker, published in 1897.  ... 
arXiv:2204.07447v1 fatcat:6pa3b6a55bedzednwrnq5s7nwu