The Typology of Ellipsis: A Corpus for Linguistic Analysis and Machine Learning Applications

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AU9Q5SRF4" target="_blank" >RIV/00216208:11320/25:U9Q5SRF4 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189615255&partnerID=40&md5=8bb9d16d82460d0224284a8f3e5e7417" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189615255&partnerID=40&md5=8bb9d16d82460d0224284a8f3e5e7417</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

The Typology of Ellipsis: A Corpus for Linguistic Analysis and Machine Learning Applications

Popis výsledku v původním jazyce

Ellipsis constructions are challenging for State-of-the-art (SotA) Natural Language Processing (NLP) technologies. Although theoretically well-documented and understood, there needs to be more sufficient cross-linguistic language resources to document, study, and ultimately engineer NLP solutions that can adequately provide analyses for ellipsis constructions. This article describes the typological data set on ellipsis that we created for currently seventeen languages. We demonstrate how SotA parsers based on a variety of syntactic frameworks fail to parse sentences with ellipsis, and in fact, probabilistic, neural, and Large Language Models (LLM) do so, too. We discuss experiments that focus on detecting sentences with ellipsis, predicting the position of elided elements, and predicting elided surface forms in the appropriate positions. We show that cross-linguistic variation of ellipsis-related phenomena has different consequences for the architecture of NLP systems. © 2024 Association for Computational Linguistics.

Název v anglickém jazyce

The Typology of Ellipsis: A Corpus for Linguistic Analysis and Machine Learning Applications

Popis výsledku anglicky

Ellipsis constructions are challenging for State-of-the-art (SotA) Natural Language Processing (NLP) technologies. Although theoretically well-documented and understood, there needs to be more sufficient cross-linguistic language resources to document, study, and ultimately engineer NLP solutions that can adequately provide analyses for ellipsis constructions. This article describes the typological data set on ellipsis that we created for currently seventeen languages. We demonstrate how SotA parsers based on a variety of syntactic frameworks fail to parse sentences with ellipsis, and in fact, probabilistic, neural, and Large Language Models (LLM) do so, too. We discuss experiments that focus on detecting sentences with ellipsis, predicting the position of elided elements, and predicting elided surface forms in the appropriate positions. We show that cross-linguistic variation of ellipsis-related phenomena has different consequences for the architecture of NLP systems. © 2024 Association for Computational Linguistics.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

SIGTYP - Workshop Res. Comput. Linguist. Typology Multiling. NLP, Proc. Workshop

ISBN

979-889176071-4

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

46-54

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

St. Julian's

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—