Multivalent Entailment Graphs for Question Answering

04/16/2021
by   Nick McKenna, et al.
17

Drawing inferences between open-domain natural language predicates is a necessity for true language understanding. There has been much progress in unsupervised learning of entailment graphs for this purpose. We make three contributions: (1) we reinterpret the Distributional Inclusion Hypothesis to model entailment between predicates of different valencies, like DEFEAT(Biden, Trump) entails WIN(Biden); (2) we actualize this theory by learning unsupervised Multivalent Entailment Graphs of open-domain predicates; and (3) we demonstrate the capabilities of these graphs on a novel question answering task. We show that directional entailment is more helpful for inference than bidirectional similarity on questions of fine-grained semantics. We also show that drawing on evidence across valencies answers more questions than by using only the same valency evidence.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

11/26/2018

Visual Entailment Task for Visually-Grounded Language Learning

We introduce a new inference task - Visual Entailment (VE) - which diffe...
05/16/2016

Joint Learning of Sentence Embeddings for Relevance and Entailment

We consider the problem of Recognizing Textual Entailment within an Info...
05/17/2019

Functorial Question Answering

We study the relational variant of the categorical compositional distrib...
09/04/2002

The partition semantics of questions, syntactically

Groenendijk and Stokhof (1984, 1996; Groenendijk 1999) provide a logical...
04/17/2021

Explaining Answers with Entailment Trees

Our goal, in the context of open-domain textual question-answering (QA),...
04/24/2018

End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions

This work deals with SciTail, a natural entailment challenge derived fro...
12/18/2009

A Survey of Paraphrasing and Textual Entailment Methods

Paraphrasing methods recognize, generate, or extract phrases, sentences,...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.