Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference

10/29/2020
by   Lasha Abzianidze, et al.
0

Tackling Natural Language Inference with a logic-based method is becoming less and less common. While this might have been counterintuitive several decades ago, nowadays it seems pretty obvious. The main reasons for such a conception are that (a) logic-based methods are usually brittle when it comes to processing wide-coverage texts, and (b) instead of automatically learning from data, they require much of manual effort for development. We make a step towards to overcome such shortcomings by modeling learning from data as abduction: reversing a theorem-proving procedure to abduce semantic relations that serve as the best explanation for the gold label of an inference problem. In other words, instead of proving sentence-level inference relations with the help of lexical relations, the lexical relations are proved taking into account the sentence-level inference relations. We implement the learning method in a tableau theorem prover for natural language and show that it improves the performance of the theorem prover on the SICK dataset by 1.4 maintaining high precision (>94 the state of the art among logic-based systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/07/2021

A Logic-Based Framework for Natural Language Inference in Dutch

We present a framework for deriving inference relations between Dutch se...
research
07/06/2020

Logic, Language, and Calculus

The difference between object-language and metalanguage is crucial for l...
research
10/19/2019

MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity

We present a new logic-based inference engine for natural language infer...
research
10/13/2022

RWN: A Novel Neighborhood-Based Method for Statistical Disclosure Control

A novel variation of the data swapping approach to statistical disclosur...
research
08/30/2017

LangPro: Natural Language Theorem Prover

LangPro is an automated theorem prover for natural language (https://git...
research
11/02/2020

Combining Event Semantics and Degree Semantics for Natural Language Inference

In formal semantics, there are two well-developed semantic frameworks: e...
research
06/04/2019

SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference

We present SherLIiC, a testbed for lexical inference in context (LIiC), ...

Please sign up or login with your details

Forgot password? Click here to reset