no code implementations • CONLL 2017 • Van-Khanh Tran, Le-Minh Nguyen
Natural language generation (NLG) is a critical component in a spoken dialogue system.
no code implementations • 1 Jun 2017 • Van-Khanh Tran, Le-Minh Nguyen
Natural language generation (NLG) plays a critical role in spoken dialogue systems.
no code implementations • WS 2017 • Van-Khanh Tran, Le-Minh Nguyen
Natural language generation (NLG) is an important component in spoken dialogue systems.
1 code implementation • 18 May 2018 • Thi-Vinh Ngo, Thanh-Le Ha, Phuong-Thai Nguyen, Le-Minh Nguyen
Neural machine translation (NMT) systems have recently obtained state-of-the art in many machine translation systems between popular language pairs because of the availability of data.
no code implementations • COLING 2018 • Van-Khanh Tran, Le-Minh Nguyen
In this procedure, a model is first trained on a source domain data and then fine-tuned on a small set of target domain utterances under the guidance of two proposed critics.
no code implementations • CONLL 2018 • Van-Khanh Tran, Le-Minh Nguyen
Recent deep learning models have shown improving results to natural language generation (NLG) irrespective of providing sufficient annotated data.
1 code implementation • EMNLP (IWSLT) 2019 • Thi-Vinh Ngo, Thanh-Le Ha, Phuong-Thai Nguyen, Le-Minh Nguyen
While translating between East Asian languages, many works have discovered clear advantages of using characters as the translation unit.
no code implementations • WS 2019 • Thi-Vinh Ngo, Thanh-Le Ha, Phuong-Thai Nguyen, Le-Minh Nguyen
Among the six challenges of neural machine translation (NMT) coined by (Koehn and Knowles, 2017), rare-word problem is considered the most severe one, especially in translation of low-resource languages.
no code implementations • 16 Dec 2020 • Thi-Vinh Ngo, Phuong-Thai Nguyen, Thanh-Le Ha, Khac-Quy Dinh, Le-Minh Nguyen
Prior works have demonstrated that a low-resource language pair can benefit from multilingual machine translation (MT) systems, which rely on many language pairs' joint training.
no code implementations • 8 Mar 2021 • Ha-Thanh Nguyen, Le-Minh Nguyen
Deep learning is a powerful approach with good performance on many different tasks.
no code implementations • 15 Apr 2021 • Ha-Thanh Nguyen, Le-Minh Nguyen
Legal English is a sublanguage that is important for everyone but not for everyone to understand.
no code implementations • 11 Sep 2021 • Ha-Thanh Nguyen, Vu Tran, Tran-Binh Dang, Minh-Quan Bui, Minh-Phuong Nguyen, Le-Minh Nguyen
Attention is all we need as long as we have enough data.
no code implementations • 13 Feb 2022 • Ha-Thanh Nguyen, Minh-Phuong Nguyen, Thi-Hai-Yen Vuong, Minh-Quan Bui, Minh-Chau Nguyen, Tran-Binh Dang, Vu Tran, Le-Minh Nguyen, Ken Satoh
In this paper, we introduce our approaches using Transformer-based models for different problems of the COLIEE 2021 automatic legal text processing competition.
no code implementations • 13 Dec 2022 • Ha-Thanh Nguyen, Manh-Kien Phi, Xuan-Bach Ngo, Vu Tran, Le-Minh Nguyen, Minh-Phuong Tu
The performance of legal text retrieval depends, to a large extent, on the representation of text, both query and legal documents.
no code implementations • 16 Dec 2022 • Ha-Thanh Nguyen, Vu Tran, Ngoc-Cam Le, Thi-Thuy Le, Quang-Huy Nguyen, Le-Minh Nguyen, Ken Satoh
First, legal reasoning can be performed on the basis of the binary tree representation of the regulations.
no code implementations • 8 Jun 2023 • Thi-Hai-Yen Vuong, Ha-Thanh Nguyen, Quang-Huy Nguyen, Le-Minh Nguyen, Xuan-Hieu Phan
Question answering (QA) in law is a challenging problem because legal documents are much more complicated than normal texts in terms of terminology, structure, and temporal and logical relationships.
1 code implementation • 19 Oct 2023 • Guanqun Sun, Yizhi Pan, Weikun Kong, Zichang Xu, Jianhua Ma, Teeradaj Racharak, Le-Minh Nguyen, Junyi Xin
Unlike earlier transformer-based U-net models, DA-TransUNet utilizes Transformers and DA-Block to integrate not only global and local features, but also image-specific positional and channel features, improving the performance of medical image segmentation.
1 code implementation • 7 Jan 2024 • Chau Nguyen, Phuong Nguyen, Thanh Tran, Dat Nguyen, An Trieu, Tin Pham, Anh Dang, Le-Minh Nguyen
The Competition on Legal Information Extraction/Entailment (COLIEE) is held annually to encourage advancements in the automatic processing of legal texts.
no code implementations • 31 Jan 2024 • Chau Nguyen, Le-Minh Nguyen
ChatGPT, a large language model, is robust in many natural language processing tasks, including legal text entailment: when we set the temperature = 0 (the ChatGPT answers are deterministic) and prompt the model, it achieves 70. 64% accuracy on COLIEE 2022 dataset, which outperforms the previous SOTA of 67. 89%.
no code implementations • 6 Mar 2024 • Vu Tran, Ha-Thanh Nguyen, Trung Vo, Son T. Luu, Hoang-Anh Dang, Ngoc-Cam Le, Thi-Thuy Le, Minh-Tien Nguyen, Truong-Son Nguyen, Le-Minh Nguyen
In this new era of rapid AI development, especially in language processing, the demand for AI in the legal domain is increasingly critical.
no code implementations • 12 Apr 2024 • Yizhi Pan, Junyi Xin, Tianhua Yang, Teeradaj Racharak, Le-Minh Nguyen, Guanqun Sun
Our approach, inspired by radiologists' working patterns, features two distinct modules: (i) \textbf{Mutual Inclusion of Position and Channel Attention (MIPC) module}: To enhance the precision of boundary segmentation in medical images, we introduce the MIPC module, which enhances the focus on channel information when extracting position features and vice versa; (ii) \textbf{GL-MIPC-Residue}: To improve the restoration of medical images, we propose the GL-MIPC-Residue, a global residual connection that enhances the integration of the encoder and decoder by filtering out invalid information and restoring the most effective information lost during the feature extraction process.
1 code implementation • COLING 2022 • Xuan-Dung Doan, Le-Minh Nguyen, Khac-Hoai Nam Bui
Heterogeneous Graph Neural Networks (HeterGNN) have been recently introduced as an emergent approach for extracting document summarization (EDS) by exploiting the cross-relations between words and sentences.
no code implementations • loresmt (AACL) 2020 • Thi-Vinh Ngo, Phuong-Thai Nguyen, Thanh-Le Ha, Khac-Quy Dinh, Le-Minh Nguyen
Prior works have demonstrated that a low-resource language pair can benefit from multilingual machine translation (MT) systems, which rely on many language pairs’ joint training.