Unified Neural Lexical Analysis Via Two-Stage Span Tagging

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3ANI54NRVE" target="_blank" >RIV/00216208:11320/26:NI54NRVE - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1049/cit2.70015" target="_blank" >http://dx.doi.org/10.1049/cit2.70015</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1049/cit2.70015" target="_blank" >10.1049/cit2.70015</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Unified Neural Lexical Analysis Via Two-Stage Span Tagging

Popis výsledku v původním jazyce

Lexical analysis is a fundamental task in natural language processing, which involves several subtasks, such as word segmentation (WS), part-of-speech (POS) tagging, and named entity recognition (NER). Recent works have shown that taking advantage of relatedness between these subtasks can be beneficial. This paper proposes a unified neural framework to address these subtasks simultaneously. Apart from the sequence tagging paradigm, the proposed method tackles the multitask lexical analysis via two-stage sequence span classification. Firstly, the model detects the word and named entity boundaries by multi-label classification over character spans in a sentence. Then, the authors assign POS labels and entity labels for words and named entities by multi-class classification, respectively. Furthermore, a Gated Task Transformation (GTT) is proposed to encourage the model to share valuable features between tasks. The performance of the proposed model was evaluated on Chinese and Thai public datasets, demonstrating state-of-the-art results. © 2025 The Author(s). CAAI Transactions on Intelligence Technology published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology and Chongqing University of Technology.

Název v anglickém jazyce

Unified Neural Lexical Analysis Via Two-Stage Span Tagging

Popis výsledku anglicky

Lexical analysis is a fundamental task in natural language processing, which involves several subtasks, such as word segmentation (WS), part-of-speech (POS) tagging, and named entity recognition (NER). Recent works have shown that taking advantage of relatedness between these subtasks can be beneficial. This paper proposes a unified neural framework to address these subtasks simultaneously. Apart from the sequence tagging paradigm, the proposed method tackles the multitask lexical analysis via two-stage sequence span classification. Firstly, the model detects the word and named entity boundaries by multi-label classification over character spans in a sentence. Then, the authors assign POS labels and entity labels for words and named entities by multi-class classification, respectively. Furthermore, a Gated Task Transformation (GTT) is proposed to encourage the model to share valuable features between tasks. The performance of the proposed model was evaluated on Chinese and Thai public datasets, demonstrating state-of-the-art results. © 2025 The Author(s). CAAI Transactions on Intelligence Technology published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology and Chongqing University of Technology.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

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

2025

Kód důvěrnosti údajů

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

Název periodika

CAAI Transactions on Intelligence Technology

ISSN

2468-6557

e-ISSN

—

Svazek periodika

10

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

1254-1267

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-105004463858