Hai-Long Trieu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hai-Long Trieu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
Le-Minh Nguyen
Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan
4 shared publicationsMakoto Miwa
Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology (AIST) , Tokyo 135-0064, Japan
2 shared publications- Makoto Miwa
Toyota Technological Institute
2 shared publications Sophia Ananiadou
National Centre for Text Mining, Computer Science, University of Manchester 131 Princess Street, M7 1DN , UK
2 shared publications- Sophia Ananiadou
University of Manchester, UK
2 shared publications Anh Nguyen
Artificial Intelligence Research Center (AIRC), National Institute of Advanced Industrial Science and Technology (AIST) , Tokyo 135-0064, Japan
1 shared publication
Latest Publications
- Open Access
- 9 January 2024
- Published by Russian Research Anti-Plague Institute Microbe in Problems of Particularly Dangerous Infections
- No. 4,p. 84-90
Antibiotic Resistance Patterns in Shiga Toxin-Producing Escherichia coli (STEC), Salmonella, Shigella and Staphylococcus aureus Isolated at Two Communal Kitchens Located in Hanoi City, Vietnam
The aim of our study was to investigate the antibiotic resistance profiles of Shiga toxin-producing Escherichia coli (STEC), Salmonella spp., Shigella spp., and Staphylococcus aureus strains.Materials and methods. 660 samples were collected at two communal kitchens in Hanoi, Vietnam between 2021 and 2022. They included foodstuffs, environmental (food processing tools) and biological ones (swabs from the hands of personnel). The VITEK® 2 Compact system in combination with DNA sequencing was used to identify bacterial species. The antibiotic susceptibility test (AST) was performed according to Kirby-Bauer Disk Diffusion Susceptibility protocol following Clinical & Laboratory Standards Institute (CLSI) method (M100-Ed32).Results and discussion. In total, 53 pathogenic bacterial strains have been detected, including 11 STEC, 24 Salmonella enterica, 9 Shigella sonnei, Shigella flexneri, and 8 S. aureus. AST of STEC has showed the highest resistance rates to tetracycline and chloramphenicol (90.9 %); trimethoprim+sulfamethoxazole (81.8 %); ampicillin, gentamycin and piperacillin (63.6 %). The STEC isolates were susceptible to carbapenem group. Among the Salmonella strains, 50 % demonstrated resistance to ampicillin, followed by tetracycline and piperacillin (45.8 %). Additionally, 25 % were resistant to ticarcillin+clavulanic acid, 20.8 % – to trimethoprim+sulfamethoxazole, and 16.7 % – to chloramphenicol. All Salmonella strains exhibited susceptibility to gentamicin, cefoxitin, imipenem, meropenem, and ceftazidime. AST of Shigella strains revealed the highest resistance rate for tetracycline (30 %), followed by cefazolin and ceftazidime (20 %). However, all Shigella strains were susceptible to cefoxitin, carbapenem groups, and chloramphenicol. Among the S. aureus strains, 50 % exhibited resistance to erythromycin, azithromycin, clindamycin, penicillin, telithromycin, and gentamicin, followed by ciprofloxacin, moxifloxacin, levofloxacin, and chloramphenicol (25 %). All S. aureus strains were still susceptible to trimethoprim+sulfamethoxazole, daptomycin, linezolid, doxycycline, minocycline, and vancomycin. Our findings reflect the current situation on antibiotic resistance among pathogenic bacteria strains circulating at the study sites during food processing. They are an evidence of potential risk of food poisoning. There is a need to undertake the proper containment measures on the part of authorities or policy makers.
- 9 January 2024
- Published by Russian Research Anti-Plague Institute Microbe in Problems of Particularly Dangerous Infections
- No. 4,p. 84-90
Open AccessAntibiotic Resistance Patterns in Shiga Toxin-Producing Escherichia coli (STEC), Salmonella, Shigella and Staphylococcus aureus Isolated at Two Communal Kitchens Located in Hanoi City, Vietnam
The aim of our study was to investigate the antibiotic resistance profiles of Shiga toxin-producing Escherichia coli (STEC), Salmonella spp., Shigella spp., and Staphylococcus aureus strains.Materials and methods. 660 samples were collected at two communal kitchens in Hanoi, Vietnam between 2021 and 2022. They included foodstuffs, environmental (food processing tools) and biological ones (swabs from the hands of personnel). The VITEK® 2 Compact system in combination with DNA sequencing was used to identify bacterial species. The antibiotic susceptibility test (AST) was performed according to Kirby-Bauer Disk Diffusion Susceptibility protocol following Clinical & Laboratory Standards Institute (CLSI) method (M100-Ed32).Results and discussion. In total, 53 pathogenic bacterial strains have been detected, including 11 STEC, 24 Salmonella enterica, 9 Shigella sonnei, Shigella flexneri, and 8 S. aureus. AST of STEC has showed the highest resistance rates to tetracycline and chloramphenicol (90.9 %); trimethoprim+sulfamethoxazole (81.8 %); ampicillin, gentamycin and piperacillin (63.6 %). The STEC isolates were susceptible to carbapenem group. Among the Salmonella strains, 50 % demonstrated resistance to ampicillin, followed by tetracycline and piperacillin (45.8 %). Additionally, 25 % were resistant to ticarcillin+clavulanic acid, 20.8 % – to trimethoprim+sulfamethoxazole, and 16.7 % – to chloramphenicol. All Salmonella strains exhibited susceptibility to gentamicin, cefoxitin, imipenem, meropenem, and ceftazidime. AST of Shigella strains revealed the highest resistance rate for tetracycline (30 %), followed by cefazolin and ceftazidime (20 %). However, all Shigella strains were susceptible to cefoxitin, carbapenem groups, and chloramphenicol. Among the S. aureus strains, 50 % exhibited resistance to erythromycin, azithromycin, clindamycin, penicillin, telithromycin, and gentamicin, followed by ciprofloxacin, moxifloxacin, levofloxacin, and chloramphenicol (25 %). All S. aureus strains were still susceptible to trimethoprim+sulfamethoxazole, daptomycin, linezolid, doxycycline, minocycline, and vancomycin. Our findings reflect the current situation on antibiotic resistance among pathogenic bacteria strains circulating at the study sites during food processing. They are an evidence of potential risk of food poisoning. There is a need to undertake the proper containment measures on the part of authorities or policy makers.
- Open Access
- 12 October 2021
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 38 (3) , 872-874
BioVAE: a pre-trained latent variable language model for biomedical text mining
Large-scale pre-trained language models (PLMs) have advanced state-of-the-art (SOTA) performance on various biomedical text mining tasks. The power of such PLMs can be combined with the advantages of deep generative models. These are examples of these combinations. However, they are trained only on general domain text, and biomedical models are still missing. In this work, we describe BioVAE, the first large-scale pre-trained latent variable language model for the biomedical domain, which uses the OPTIMUS framework to train on large volumes of biomedical text. The model shows SOTA performance on several biomedical text mining tasks when compared to existing publicly available biomedical PLMs. In addition, our model can generate more accurate biomedical sentences than the original OPTIMUS output. Our source code and pre-trained models are freely available: https://github.com/aistairc/BioVAE. Supplementary data are available at Bioinformatics online.
- 12 October 2021
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 38 (3) , 872-874
Open AccessBioVAE: a pre-trained latent variable language model for biomedical text mining
Large-scale pre-trained language models (PLMs) have advanced state-of-the-art (SOTA) performance on various biomedical text mining tasks. The power of such PLMs can be combined with the advantages of deep generative models. These are examples of these combinations. However, they are trained only on general domain text, and biomedical models are still missing. In this work, we describe BioVAE, the first large-scale pre-trained latent variable language model for the biomedical domain, which uses the OPTIMUS framework to train on large volumes of biomedical text. The model shows SOTA performance on several biomedical text mining tasks when compared to existing publicly available biomedical PLMs. In addition, our model can generate more accurate biomedical sentences than the original OPTIMUS output. Our source code and pre-trained models are freely available: https://github.com/aistairc/BioVAE. Supplementary data are available at Bioinformatics online.
- Open Access
- 17 June 2020
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 36 (19) , 4910-4917
DeepEventMine: end-to-end neural nested event extraction from biomedical texts
Recent neural approaches on event extraction from text mainly focus on flat events in general domain, while there are less attempts to detect nested and overlapping events. These existing systems are built on given entities and they depend on external syntactic tools. We propose an end-to-end neural nested event extraction model named DeepEventMine that extracts multiple overlapping directed acyclic graph structures from a raw sentence. On the top of the bidirectional encoder representations from transformers model, our model detects nested entities and triggers, roles, nested events and their modifications in an end-to-end manner without any syntactic tools. Our DeepEventMine model achieves the new state-of-the-art performance on seven biomedical nested event extraction tasks. Even when gold entities are unavailable, our model can detect events from raw text with promising performance. Our codes and models to reproduce the results are available at: https://github.com/aistairc/DeepEventMine. Supplementary data are available at Bioinformatics online.
- 17 June 2020
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 36 (19) , 4910-4917
Open AccessDeepEventMine: end-to-end neural nested event extraction from biomedical texts
Recent neural approaches on event extraction from text mainly focus on flat events in general domain, while there are less attempts to detect nested and overlapping events. These existing systems are built on given entities and they depend on external syntactic tools. We propose an end-to-end neural nested event extraction model named DeepEventMine that extracts multiple overlapping directed acyclic graph structures from a raw sentence. On the top of the bidirectional encoder representations from transformers model, our model detects nested entities and triggers, roles, nested events and their modifications in an end-to-end manner without any syntactic tools. Our DeepEventMine model achieves the new state-of-the-art performance on seven biomedical nested event extraction tasks. Even when gold entities are unavailable, our model can detect events from raw text with promising performance. Our codes and models to reproduce the results are available at: https://github.com/aistairc/DeepEventMine. Supplementary data are available at Bioinformatics online.
- Open Access
- 17 June 2019
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 18 (3) , 1-22
Leveraging Additional Resources for Improving Statistical Machine Translation on Asian Low-Resource Languages
Phrase-based machine translation (MT) systems require large bilingual corpora for training. Nevertheless, such large bilingual corpora are unavailable for most language pairs in the world, causing a bottleneck for the development of MT. For the Asian language pairs—Japanese, Indonesian, Malay paired with Vietnamese—they are also not excluded from the case, in which there are no large bilingual corpora on these low-resource language pairs. Furthermore, although the languages are widely used in the world, there is no prior work on MT, which causes an issue for the development of MT on these languages. In this article, we conducted an empirical study of leveraging additional resources to improve MT for the Asian low-resource language pairs: translation from Japanese, Indonesian, and Malay to Vietnamese. We propose an innovative approach that lies in two strategies of building bilingual corpora from comparable data and phrase pivot translation on existing bilingual corpora of the languages paired with English. Bilingual corpora were built from Wikipedia bilingual titles to enhance bilingual data for the low-resource languages. Additionally, we introduced a combined model of the additional resources to create an effective solution to improve MT on the Asian low-resource languages. Experimental results show the effectiveness of our systems with the improvement of +2 to +7 BLEU points. This work contributes to the development of MT on low-resource languages, especially opening a promising direction for the progress of MT on the Asian language pairs.
- 17 June 2019
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 18 (3) , 1-22
Open AccessLeveraging Additional Resources for Improving Statistical Machine Translation on Asian Low-Resource Languages
Phrase-based machine translation (MT) systems require large bilingual corpora for training. Nevertheless, such large bilingual corpora are unavailable for most language pairs in the world, causing a bottleneck for the development of MT. For the Asian language pairs—Japanese, Indonesian, Malay paired with Vietnamese—they are also not excluded from the case, in which there are no large bilingual corpora on these low-resource language pairs. Furthermore, although the languages are widely used in the world, there is no prior work on MT, which causes an issue for the development of MT on these languages. In this article, we conducted an empirical study of leveraging additional resources to improve MT for the Asian low-resource language pairs: translation from Japanese, Indonesian, and Malay to Vietnamese. We propose an innovative approach that lies in two strategies of building bilingual corpora from comparable data and phrase pivot translation on existing bilingual corpora of the languages paired with English. Bilingual corpora were built from Wikipedia bilingual titles to enhance bilingual data for the low-resource languages. Additionally, we introduced a combined model of the additional resources to create an effective solution to improve MT on the Asian low-resource languages. Experimental results show the effectiveness of our systems with the improvement of +2 to +7 BLEU points. This work contributes to the development of MT on low-resource languages, especially opening a promising direction for the progress of MT on the Asian language pairs.
- Open Access
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 196-205
Coreference Resolution in Full Text Articles with BERT and Syntax-based Mention Filtering
Hai-Long Trieu, Anh-Khoa Duong Nguyen, Nhung Nguyen, Makoto Miwa, Hiroya Takamura, Sophia Ananiadou. Proceedings of The 5th Workshop on BioNLP Open Shared Tasks. 2019.
- 1 January 2019
- Published by Association for Computational Linguistics (ACL)
- p. 196-205
Open AccessCoreference Resolution in Full Text Articles with BERT and Syntax-based Mention Filtering
Hai-Long Trieu, Anh-Khoa Duong Nguyen, Nhung Nguyen, Makoto Miwa, Hiroya Takamura, Sophia Ananiadou. Proceedings of The 5th Workshop on BioNLP Open Shared Tasks. 2019.
- Open Access
- 1 January 2018
- Published by Association for Computational Linguistics (ACL)
- p. 183-188
Investigating Domain-Specific Information for Neural Coreference Resolution on Biomedical Texts
- 1 January 2018
- Published by Association for Computational Linguistics (ACL)
- p. 183-188
Open AccessInvestigating Domain-Specific Information for Neural Coreference Resolution on Biomedical Texts
- 1 January 2017
- Published by INSTICC
- p. 511-518
Towards Developing Dialogue Systems with Entertaining Conversations
- 1 January 2017
- Published by INSTICC
- p. 511-518
Towards Developing Dialogue Systems with Entertaining Conversations
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
The JAIST Machine Translation Systems for WMT 17
- 1 January 2017
- Published by Association for Computational Linguistics (ACL)
The JAIST Machine Translation Systems for WMT 17
- 1 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1043-1047
Applying Semantic Similarity to Phrase Pivot Translation
Pivot methods have shown to be an effective solution to overcome the problem of unavailable large bilingual corpora in statistical machine translation. The representative approach of pivot methods is the phrase pivot translation which is based on common pivot phrases to produce connections between source-pivot and pivot-target phrase tables. Nevertheless, this approach produces insufficient connections behind the phrase tables because pivot phrases still contain the same meaning even when they are not matched to each other. In this work, we propose applying semantic similarity between pivot phrases to phrase pivot translation. In order to extract similar pivot phrases, we used string similarity measures for phrase similarity, and WordNet and Word2Vec were used for word similarity. The experiments show that using semantic similarity is able to extract more informative phrases, which can support for phrase pivot translation.
- 1 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1043-1047
Applying Semantic Similarity to Phrase Pivot Translation
Pivot methods have shown to be an effective solution to overcome the problem of unavailable large bilingual corpora in statistical machine translation. The representative approach of pivot methods is the phrase pivot translation which is based on common pivot phrases to produce connections between source-pivot and pivot-target phrase tables. Nevertheless, this approach produces insufficient connections behind the phrase tables because pivot phrases still contain the same meaning even when they are not matched to each other. In this work, we propose applying semantic similarity between pivot phrases to phrase pivot translation. In order to extract similar pivot phrases, we used string similarity measures for phrase similarity, and WordNet and Word2Vec were used for word similarity. The experiments show that using semantic similarity is able to extract more informative phrases, which can support for phrase pivot translation.