Hanh Thi Hong Tran

Hanh Thi Hong Tran

Auto-generated profile, based on publicly available information

Hanh Thi Hong Tran

University of La Rochelle, L3i

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 December 2022
Verified
Book Chapter
Closed access
PDF file
HTHanh Thi Hong Tran
Hanh Thi Hong Tran
MMMatej Martinc
Matej Martinc
APAndraž Pelicon
Andraž Pelicon
ADAntoine Doucet
Antoine Doucet
Senja PollakSenja Pollak
Senja Pollak

26 September 2024
Verified
Book Chapter
Closed access
PDF file
CGCarlos-Emiliano González-Gallardo
Carlos-Emiliano González-Gallardo
HTHanh Thi Hong Tran
Hanh Thi Hong Tran
AHAhmed Hamdi
Ahmed Hamdi
ADAntoine Doucet
Antoine Doucet

30 November 2021
Verified
Book Chapter
Closed access
PDF file
THTran Thi Hong Hanh
Tran Thi Hong Hanh
ADAntoine Doucet
Antoine Doucet
NSNicolas Sidere
Nicolas Sidere
JMJose G. Moreno
Jose G. Moreno
Senja PollakSenja Pollak
Senja Pollak

27 March 2024 in Machine Learning
Verified
Journal Article
Open access
PDF file
HTHanh Thi Hong Tran
Hanh Thi Hong Tran
MMMatej Martinc
Matej Martinc
ARAndraz Repar
Andraz Repar
NLNikola Ljubešić
Nikola Ljubešić
ADAntoine Doucet
Antoine Doucet
Senja PollakSenja Pollak
Senja Pollak
Automatic term extraction (ATE) is a natural language processing task that eases the effort of manually identifying terms from domain-specific corpora by providing a list of candidate terms. In this paper, we treat ATE as a sequence-labeling task and explore the efficacy of XLMR in evaluating cross-lingual and multilingual learning against monolingual learning in the cross-domain ATE context. Additionally, we introduce NOBI, a novel annotation mechanism enabling the labeling of single-word nested terms. Our experiments are conducted on the ACTER corpus, encompassing four domains and three languages (English, French, and Dutch), as well as the RSDO5 Slovenian corpus, encompassing four additional domains. Results indicate that cross-lingual and multilingual models outperform monolingual settings, showcasing improved F1-scores for all languages within the ACTER dataset. When incorporating an additional Slovenian corpus into the training set, the multilingual model exhibits superior performance compared to state-of-the-art approaches in specific scenarios. Moreover, the newly introduced NOBI labeling mechanism enhances the classifier’s capacity to extract short nested terms significantly, leading to substantial improvements in Recall for the ACTER dataset and consequentially boosting the overall F1-score performance.

6 November 2022
Verified
Book Chapter
Closed access
PDF file
HTHanh Thi Hong Tran
Hanh Thi Hong Tran
MMMatej Martinc
Matej Martinc
ADAntoine Doucet
Antoine Doucet
Senja PollakSenja Pollak
Senja Pollak

1 September 2024
Verified
Book Chapter
Closed access
PDF file
HTHanh Thi Hong Tran
Hanh Thi Hong Tran
CGCarlos-Emiliano González-Gallardo
Carlos-Emiliano González-Gallardo
JDJulien Delaunay
Julien Delaunay
ADAntoine Doucet
Antoine Doucet
Senja PollakSenja Pollak
Senja Pollak