Neural String Edit Distance

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10457039" target="_blank" >RIV/00216208:11320/22:10457039 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2022.spnlp-1.6" target="_blank" >https://aclanthology.org/2022.spnlp-1.6</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Neural String Edit Distance

Original language description

We propose the neural string edit distance model for string-pair matching and string transduction based on learnable string edit distance. We modify the original expectation-maximization learned edit distance algorithm into a differentiable loss function, allowing us to integrate it into a neural network providing a contextual representation of the input. We evaluate on cognate detection, transliteration, and grapheme-to-phoneme conversion, and show that we can trade off between performance and interpretability in a single framework. Using contextual representations, which are difficult to interpret, we match the performance of state-of-the-art string-pair matching models. Using static embeddings and a slightly different loss function, we force interpretability, at the expense of an accuracy drop.

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

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2022

Confidentiality

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

Article name in the collection

Proceedings of the Sixth Workshop on Structured Prediction for NLP

ISBN

978-1-955917-51-3

ISSN

—

e-ISSN

—

Number of pages

15

Pages from-to

52-66

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg, USA

Event location

Dublin, Ireland

Event date

May 27, 2022

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000847352600006