Natural Language Deduction with Incomplete Information

by   Zayne Sprague, et al.

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.


page 15

page 20

page 21

page 22

page 24

page 25

page 26

page 28


Stochastic Answer Networks for Natural Language Inference

We propose a stochastic answer network (SAN) to explore multi-step infer...

Natural Language Specifications in Proof Assistants

Interactive proof assistants are computer programs carefully constructed...

ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language

Transformers have been shown to emulate logical deduction over natural l...

A Puzzle-Based Dataset for Natural Language Inference

We provide here a dataset for tasks related to natural language understa...

LAMBADA: Backward Chaining for Automated Reasoning in Natural Language

Remarkable progress has been made on automated reasoning with knowledge ...

ExClaim: Explainable Neural Claim Verification Using Rationalization

With the advent of deep learning, text generation language models have i...

PerspectroScope: A Window to the World of Diverse Perspectives

This work presents PerspectroScope, a web-based system which lets users ...

Please sign up or login with your details

Forgot password? Click here to reset