Exploring Knowledge Graphs in an Interpretable Composite Approach for Text Entailment

Vivian S Silva, Andre Freitas, Siegfried Handschuh

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

58 Downloads (Pure)

Abstract

Recognizing textual entailment is a key task for many semantic applications, such as Question Answering, Text Summarization, and Information Extraction, among others. Entailment scenarios can range from a simple syntactic variation to more complex semantic relationships between pieces of text, but most approaches try a one-size-fits-all solution that usually favors some scenario to the detriment of another. We propose a composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. We also make the answer interpretable: whenever an entailment is solved semantically, we explore a knowledge base composed of structured lexical definitions to generate natural language humanlike justifications, explaining the semantic relationship holding between the pieces of text. Besides outperforming wellestablished entailment algorithms, our composite approach gives an important step towards Explainable AI, using world knowledge to make the semantic reasoning process explicit and understandable.
Original languageEnglish
Title of host publicationThirty-Second AAAI Conference on Artificial Intelligence
DOIs
Publication statusPublished - 17 Jul 2019
EventThirty-Second AAAI Conference on Artificial Intelligence - New Orleans, United States
Duration: 2 Feb 20187 Feb 2018

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
PublisherAAAI Press
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

ConferenceThirty-Second AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI-18
Country/TerritoryUnited States
CityNew Orleans
Period2/02/187/02/18

Fingerprint

Dive into the research topics of 'Exploring Knowledge Graphs in an Interpretable Composite Approach for Text Entailment'. Together they form a unique fingerprint.

Cite this