Results 21 to 30 of about 52,458 (341)
Uncertain Natural Language Inference [PDF]
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020 We introduce Uncertain Natural Language Inference (UNLI), a refinement of Natural Language Inference (NLI) that shifts away from categorical labels, targeting instead the direct prediction of subjective probability assessments. We demonstrate the feasibility of collecting annotations for UNLI by relabeling a portion of the SNLI dataset under a ...
Tongfei Chen +4 more
openaire +3 more sources
Inferring symmetry in natural language [PDF]
Findings of the Association for Computational Linguistics: EMNLP 2020, 2020 10 pages, 4 figures, Findings of ...
Chelsea Tanchip +3 more
openaire +2 more sources
On the Language-specificity of Multilingual BERT and the Impact of Fine-tuning [PDF]
, 2021 Recent work has shown evidence that the knowledge acquired by multilingual BERT (mBERT) has two components: a language-specific and a language-neutral one.
Dupoux, Emmanuel +12 more
core +1 more source
Natural Language Syntax and First Order Inference
Artificial Intelligence, 1992 : We have argued elsewhere that first order inference can be made more efficient by using non-standard syntax for first order logic. In this paper we define a syntax for first order logic based on the structure of natural language under Montague ...
David Mcallester, Robert Givan
core +3 more sources
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
Transactions of the Association for Computational Linguistics, 2022 A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same importance in Natural Language Processing (NLP), which has traditionally ...
Amir Feder +12 more
doaj +1 more source
Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference
Transactions of the Association for Computational Linguistics, 2022 We introduce a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision. The model samples and rewards specific reasoning paths through policy gradient, in which the introspective revision algorithm modifies ...
Yufei Feng +3 more
doaj +1 more source
NILE : Natural Language Inference with Faithful Natural Language Explanations [PDF]
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020 13 pages, 3 figures, Accepted to ACL ...
Sawan Kumar, Partha P. Talukdar
openaire +2 more sources
Alignment Rationale for Natural Language Inference [PDF]
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), 2021 Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors. Existing explanation methods usually pick prominent features such as words or phrases from the input text. However, for NLI, alignments among words or phrases are more enlightening clues to explain
Zhongtao Jiang +4 more
openaire +1 more source
Natural Language Inference with Monotonicity [PDF]
Proceedings of the 13th International Conference on Computational Semantics - Short Papers, 2019 This paper describes a working system which performs natural language inference using polarity-marked parse trees. The system handles all of the instances of monotonicity inference in the FraCaS data set. Except for the initial parse, it is entirely deterministic.
Hai Hu 0001, Qi Chen, Larry Moss
openaire +1 more source
Dialogue Natural Language Inference [PDF]
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019 Consistency is a long standing issue faced by dialogue models. In this paper, we frame the consistency of dialogue agents as natural language inference (NLI) and create a new natural language inference dataset called Dialogue NLI. We propose a method which demonstrates that a model trained on Dialogue NLI can be used to improve the consistency of a ...
Sean Welleck +3 more
openaire +2 more sources