Thi Hong Hanh Tran


2023

pdf bib
Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages
Nikola Ivačič | Thi Hong Hanh Tran | Boshko Koloski | Senja Pollak | Matthew Purver
Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)

This paper analyzes a Named Entity Recognition task for South-Slavic languages using the pre-trained multilingual neural network models. We investigate whether the performance of the models for a target language can be improved by using data from closely related languages. We have shown that the model performance is not influenced substantially when trained with other than a target language. While for Slovene, the monolingual setting generally performs better, for Croatian and Serbian the results are slightly better in selected cross-lingual settings, but the improvements are not large. The most significant performance improvement is shown for the Serbian language, which has the smallest corpora. Therefore, fine-tuning with other closely related languages may benefit only the “low resource” languages.

pdf bib
L3I++ at SemEval-2023 Task 2: Prompting for Multilingual Complex Named Entity Recognition
Carlos-Emiliano Gonzalez-Gallardo | Thi Hong Hanh Tran | Nancy Girdhar | Emanuela Boros | Jose G. Moreno | Antoine Doucet
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

This paper summarizes the participation of the L3i laboratory of the University of La Rochelle in the SemEval-2023 Task 2, Multilingual Complex Named Entity Recognition (MultiCoNER II). Similar to MultiCoNER I, the task seeks to develop methods to detect semantic ambiguous and complex entities in short and low-context settings. However, MultiCoNER II adds a fine-grained entity taxonomy with over 30 entity types and corrupted data on the test partitions. We approach these complications following prompt-based learning as (1) a ranking problem using a seq2seq framework, and (2) an extractive question-answering task. Our findings show that even if prompting techniques have a similar recall to fine-tuned hierarchical language model-based encoder methods, precision tends to be more affected.

pdf bib
IJS@LT-EDI : Ensemble Approaches to Detect Signs of Depression from Social Media Text
Jaya Caporusso | Thi Hong Hanh Tran | Senja Pollak
Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion

This paper presents our ensembling solutions for detecting signs of depression in social media text, as part of the Shared Task at LT-EDI@RANLP 2023. By leveraging social media posts in English, the task involves the development of a system to accurately classify them as presenting signs of depression of one of three levels: “severe”, “moderate”, and “not depressed”. We verify the hypothesis that combining contextual information from a language model with local domain-specific features can improve the classifier’s performance. We do so by evaluating: (1) two global classifiers (support vector machine and logistic regression); (2) contextual information from language models; and (3) the ensembling results.

2022

pdf bib
IJS at TextGraphs-16 Natural Language Premise Selection Task: Will Contextual Information Improve Natural Language Premise Selection?
Thi Hong Hanh Tran | Matej Martinc | Antoine Doucet | Senja Pollak
Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing

Natural Language Premise Selection (NLPS) is a mathematical Natural Language Processing (NLP) task that retrieves a set of applicable relevant premises to support the end-user finding the proof for a particular statement. In this research, we evaluate the impact of Transformer-based contextual information and different fundamental similarity scores toward NLPS. The results demonstrate that the contextual representation is better at capturing meaningful information despite not being pretrained in the mathematical background compared to the statistical approach (e.g., the TF-IDF) with a boost of around 3.00% MAP@500.

pdf bib
JSI at SemEval-2022 Task 1: CODWOE - Reverse Dictionary: Monolingual and cross-lingual approaches
Thi Hong Hanh Tran | Matej Martinc | Matthew Purver | Senja Pollak
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

The reverse dictionary task is a sequence-to-vector task in which a gloss is provided as input, and the output must be a semantically matching word vector. The reverse dictionary is useful in practical applications such as solving the tip-of-the-tongue problem, helping new language learners, etc. In this paper, we evaluate the effect of a Transformer-based model with cross-lingual zero-shot learning to improve the reverse dictionary performance. Our experiments are conducted in five languages in the CODWOE dataset, including English, French, Italian, Spanish, and Russian. Even if we did not achieve a good ranking in the CODWOE competition, we show that our work partially improves the current baseline from the organizers with a hypothesis on the impact of LSTM in monolingual, multilingual, and zero-shot learning. All the codes are available at https://github.com/honghanhh/codwoe2021.