Assessing Word Importance Using Models Trained for Semantic Tasks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475877" target="_blank" >RIV/00216208:11320/23:10475877 - isvavai.cz</a>

Alternative codes found

RIV/00216208:11320/23:HAZ4W4VN

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Assessing Word Importance Using Models Trained for Semantic Tasks

Original language description

Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve semantic task: Natural Language Inference and Paraphrase Identification. Using an attribution method aimed to explain the predictions of these models, we derive importance scores for each input token. We evaluate their relevance using a so-called cross-task evaluation: Analyzing the performance of one model on an input masked according to the other model&apos;s weight, we show that our method is robust with respect to the choice of the initial task. Additionally, we investigate the scores from the syntax point of view and observe interesting patterns, e.g. words closer to the root of a syntactic tree receive higher importance scores. Altogether, these observations suggest that our method can be used to identify important words in sentences without any explicit word importance labeling in training.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Findings of the Association for Computational Linguistics: ACL 2023

ISBN

978-1-959429-62-3

ISSN

—

e-ISSN

—

Number of pages

11

Pages from-to

8846-8856

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg, PA, USA

Event location

Toronto, Canada

Event date

Jul 9, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—