Fine-Grained Domain Adaptation for Chinese Syntactic Processing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AUF6DNFKL" target="_blank" >RIV/00216208:11320/23:UF6DNFKL - isvavai.cz</a>

Výsledek na webu

<a href="https://dl.acm.org/doi/10.1145/3629519" target="_blank" >https://dl.acm.org/doi/10.1145/3629519</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3629519" target="_blank" >10.1145/3629519</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Fine-Grained Domain Adaptation for Chinese Syntactic Processing

Popis výsledku v původním jazyce

"Syntactic processing is fundamental to natural language processing. It provides rich and comprehensive syntax information in sentences that could be potentially beneficial for downstream tasks. Recently, pretrained language models have shown great success in Chinese syntactic processing, which typically involves word segmentation, POS tagging, and dependency parsing. However, the on-going research never ends since performance would be degraded drastically when tested on a highly-discrepant domain. This problem is widely accepted as domain adaptation, where the test domain differs from the training domain in supervised learning. Self-training is one promising solution for it, and straightforward source-to-target adaptation has already shown remarkable effectiveness in previous work. While this strategy ignores the fact that sentences of the target domain sentences may have very different gaps from the source training domain. More specifically, sentences with large gaps might fail by direct self-training adaptation. To this end, we propose fine-grained domain adaptation for Chinese syntactic processing in this work, aiming to model the gaps between the source and the target domains accurately and progressively. The key idea is to divide the target domain into fine-grained subdomains by using a specified domain distance metric, and then perform gradual self-training on the subdomains. We further offer an intuitive theoretical illustration based on the theory of Kumar et al. (2020) approximately. In addition, a novel representation learning framework is proposed to encode fine-grained subdomains effectively, aiming to utilize the above idea fully. Experimental results on benchmark datasets show that our method can achieve significant improvements over a variety of baselines."

Název v anglickém jazyce

Fine-Grained Domain Adaptation for Chinese Syntactic Processing

Popis výsledku anglicky

"Syntactic processing is fundamental to natural language processing. It provides rich and comprehensive syntax information in sentences that could be potentially beneficial for downstream tasks. Recently, pretrained language models have shown great success in Chinese syntactic processing, which typically involves word segmentation, POS tagging, and dependency parsing. However, the on-going research never ends since performance would be degraded drastically when tested on a highly-discrepant domain. This problem is widely accepted as domain adaptation, where the test domain differs from the training domain in supervised learning. Self-training is one promising solution for it, and straightforward source-to-target adaptation has already shown remarkable effectiveness in previous work. While this strategy ignores the fact that sentences of the target domain sentences may have very different gaps from the source training domain. More specifically, sentences with large gaps might fail by direct self-training adaptation. To this end, we propose fine-grained domain adaptation for Chinese syntactic processing in this work, aiming to model the gaps between the source and the target domains accurately and progressively. The key idea is to divide the target domain into fine-grained subdomains by using a specified domain distance metric, and then perform gradual self-training on the subdomains. We further offer an intuitive theoretical illustration based on the theory of Kumar et al. (2020) approximately. In addition, a novel representation learning framework is proposed to encode fine-grained subdomains effectively, aiming to utilize the above idea fully. Experimental results on benchmark datasets show that our method can achieve significant improvements over a variety of baselines."

Druh

J_ost - Ostatní články v recenzovaných periodicích

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

2023

Kód důvěrnosti údajů

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

Název periodika

"ACM Transactions on Asian and Low-Resource Language Information Processing"

ISSN

2375-4699

e-ISSN

—

Svazek periodika

22

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

24

Strana od-do

1-24

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—