no code implementations • 3 Apr 2024 • Viet-Tung Do, Van-Khanh Hoang, Duy-Hung Nguyen, Shahab Sabahi, Jeff Yang, Hajime Hotta, Minh-Tien Nguyen, Hung Le
Our approach consists of three steps: (1) clustering the training data and generating candidate prompts for each cluster using an LLM-based prompt generator; (2) synthesizing a dataset of input-prompt-output tuples for training a prompt evaluator to rank the prompts based on their relevance to the input; (3) using the prompt evaluator to select the best prompt for a new input at test time.
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 • 18 Oct 2023 • Shumpei Inoue, Minh-Tien Nguyen, Hiroki Mizokuchi, Tuan-Anh D. Nguyen, Huu-Hiep Nguyen, Dung Tien Le
This paper introduces a new IncidentAI dataset for safety prevention.
no code implementations • 12 May 2023 • Minh-Tien Nguyen, Duy-Hung Nguyen, Shahab Sabahi, Hung Le, Jeff Yang, Hajime Hotta
Based on the task we design a new model relied on LLMs which are empowered by additional knowledge extracted from insurance policy rulebooks and DBpedia.
no code implementations • 5 Jan 2023 • Huu-Hiep Nguyen, Minh-Tien Nguyen
The task of Emotion-Cause Pair Extraction (ECPE) aims to extract all potential emotion-cause pairs of a document without any annotation of emotion or cause clauses.
no code implementations • 23 Dec 2022 • Minh-Tien Nguyen, Nhung Bui, Manh Tran-Tien, Linh Le, Huy-The Vu
We release the two new datasets with the code of the baselines.
Multi Label Text Classification Multi-Label Text Classification +5
no code implementations • 20 Oct 2022 • Shumpei Inoue, Hy Nguyen, Pham Viet Hoang, Tsungwei Liu, Minh-Tien Nguyen
Meetings are a universal process to make decisions in business and project collaboration.
no code implementations • 26 Sep 2022 • Bao-Sinh Nguyen, Dung Tien Le, Hieu M. Vu, Tuan Anh D. Nguyen, Minh-Tien Nguyen, Hung Le
In this paper, we investigate the problem of improving the performance of Artificial Intelligence systems in understanding document images, especially in cases where training data is limited.
no code implementations • 26 May 2022 • Nguyen Hong Son, Hieu M. Vu, Tuan-Anh D. Nguyen, Minh-Tien Nguyen
This paper introduces a new information extraction model for business documents.
no code implementations • Findings (NAACL) 2022 • Duy-Hung Nguyen, Nguyen Viet Dung Nghiem, Bao-Sinh Nguyen, Dung Tien Le, Shahab Sabahi, Minh-Tien Nguyen, Hung Le
For summarization, human preference is critical to tame outputs of the summarizer in favor of human interests, as ground-truth summaries are scarce and ambiguous.
1 code implementation • NAACL 2022 • Shumpei Inoue, Tsungwei Liu, Nguyen Hong Son, Minh-Tien Nguyen
To support the picker, we design two label creation methods (soft and hard labels), which can work in cases of no annotation data for the omitted tokens.
no code implementations • 13 Nov 2021 • Duy-Hung Nguyen, Bao-Sinh Nguyen, Nguyen Viet Dung Nghiem, Dung Tien Le, Mim Amina Khatun, Minh-Tien Nguyen, Hung Le
Automatic summarization of legal texts is an important and still a challenging task since legal documents are often long and complicated with unusual structures and styles.
no code implementations • 2 Jun 2021 • Tuan-Anh D. Nguyen, Hieu M. Vu, Nguyen Hong Son, Minh-Tien Nguyen
Firstly, we introduce a new query-based IE model that employs span extraction instead of using the common sequence labeling approach.
no code implementations • 5 Jun 2020 • Minh-Tien Nguyen, Bui Cong Minh, Dung Tien Le, Le Thai Linh
Sentence compression is the task of creating a shorter version of an input sentence while keeping important information.
no code implementations • 6 Mar 2020 • Minh-Tien Nguyen, Viet-Anh Phan, Le Thai Linh, Nguyen Hong Son, Le Tien Dung, Miku Hirano, Hajime Hotta
This paper presents a practical approach to fine-grained information extraction.
no code implementations • 16 Mar 2017 • Phong-Khac Do, Huy-Tien Nguyen, Chien-Xuan Tran, Minh-Tien Nguyen, Minh-Le Nguyen
This paper presents a study of employing Ranking SVM and Convolutional Neural Network for two missions: legal information retrieval and question answering in the Competition on Legal Information Extraction/Entailment.
no code implementations • WS 2016 • Minh-Tien Nguyen, Dac Viet Lai, Phong-Khac Do, Duc-Vu Tran, Minh-Le Nguyen
This paper presents VSoLSCSum, a Vietnamese linked sentence-comment dataset, which was manually created to treat the lack of standard corpora for social context summarization in Vietnamese.
no code implementations • 3 Sep 2016 • Danilo S. Carvalho, Minh-Tien Nguyen, Tran Xuan Chien, Minh Le Nguyen
In the context of the Competition on Legal Information Extraction/Entailment (COLIEE), we propose a method comprising the necessary steps for finding relevant documents to a legal question and deciding on textual entailment evidence to provide a correct answer.