paper-with-me

홈 › Papers

Natural Language Deduction with Incomplete Information

2022-11-01 · Zayne Sprague, Kaj Bostrom, Swarat Chaudhuri, Greg Durrett

A growing body of work studies how to answer a question or verify a claim by generating a natural language "proof": a chain of deductive inferences yielding the answer based on a set of premises. However, these methods can only make sound deductions when they follow from evidence that is given. We propose a new system that can handle the underspecified setting where not all premises are stated at the outset; that is, additional assumptions need to be materialized to prove a claim. By using a natural language generation model to abductively infer a premise given another premise and a conclusion, we can impute missing pieces of evidence needed for the conclusion to be true. Our system searches over two fringes in a bidirectional fashion, interleaving deductive (forward-chaining) and abductive (backward-chaining) generation steps. We sample multiple possible outputs for each step to achieve coverage of the search space, at the same time ensuring correctness by filtering low-quality generations with a round-trip validation procedure. Results on a modified version of the EntailmentBank dataset and a new dataset called Everyday Norms: Why Not? show that abductive generation with validation can recover premises across in- and out-of-domain settings.

📄 PDF Abstract BibTeX arXiv:2211.00614

Code (2)

zayne-sprague/natural_language_deduction_with_incomplete_information 공식 구현
zayne-sprague/deductive_additivity_for_planning_of_natural_language_proofs pytorch

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Determining Semantic Textual Similarity using Natural Deduction Proofs

2017-07-27 · EMNLP 2017 9 · Hitomi Yanaka, Koji Mineshima, Pascual Martinez-Gomez, Daisuke Bekki

Determining semantic textual similarity is a core research subject in natural language processing. Since vector-based models for sentence representation often use shallow information, capturing accurate semantics is diff…

Semantic Textual SimilaritySentence

Chart Parsing Multimodal Grammars

2018-04-06 · Richard Moot

The short note describes the chart parser for multimodal type-logical grammars which has been developed in conjunction with the type-logical treebank for French. The chart parser presents an incomplete but fast implement…

Vocal Bursts Type Prediction

Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction

2023-06-16 · Shuai Xiao, Chen Pan, Min Wang, Xinxin Zhu 외

Automatic bill payment is an important part of business operations in fintech companies. The practice of deduction was mainly based on the total amount or heuristic search by dividing the bill into smaller parts to deduc…

Heuristic SearchHierarchical Reinforcement Learningreinforcement-learningReinforcement Learning

Revac: A Social Deduction Reasoning Agent

2026-04-21 · Mihir Shriniwas Arya, Avinash Anish, Aditya Ranjan arxiv

Social deduction games such as Mafia present a unique AI challenge: players must reason under uncertainty, interpret incomplete and intentionally misleading information, evaluate human-like communication, and make strate…

Active Reasoning in an Open-World Environment

2023-11-03 · NeurIPS 2023 11

Recent advances in vision-language learning have achieved notable success on complete-information question-answering datasets through the integration of extensive world knowledge. Yet, most models operate passively, resp…

Instruction FollowingMinecraftQuestion AnsweringWorld Knowledge