no code implementations • EMNLP 2021 • Ting-Wei Hsu, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Both the issues of data deficiencies and semantic consistency are important for data augmentation.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +1
no code implementations • EMNLP (ACL) 2021 • Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
In this tutorial, we will show where we are and where we will be to those researchers interested in this topic.
1 code implementation • COLING 2022 • Wei-Lin Chen, An-Zi Yen, Hen-Hsen Huang, Hsin-Hsi Chen
Explaining the reasoning of neural models has attracted attention in recent years.
1 code implementation • FNP (COLING) 2020 • Pei-Wei Kao, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
In order to provide an explanation of machine learning models, causality detection attracts lots of attention in the artificial intelligence research community.
1 code implementation • 23 Oct 2023 • Wei-Lin Chen, Cheng-Kuang Wu, Hsin-Hsi Chen, Chung-Chi Chen
In this paper, we address the hallucination problem commonly found in natural language generation tasks.
no code implementations • 4 Sep 2023 • Jian-Tao Huang, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Headline generation, a key task in abstractive summarization, strives to condense a full-length article into a succinct, single line of text.
1 code implementation • 18 Jul 2023 • Cheng-Kuang Wu, Wei-Lin Chen, Hsin-Hsi Chen
We explore the extension of chain-of-thought (CoT) prompting to medical reasoning for the task of automatic diagnosis.
1 code implementation • 24 May 2023 • Wei-Lin Chen, Cheng-Kuang Wu, Yun-Nung Chen, Hsin-Hsi Chen
Finally, we perform ICL for the test input with the pseudo-input-label pairs as demonstrations.
1 code implementation • 12 May 2023 • Wei-Lin Chen, An-Zi Yen, Cheng-Kuang Wu, Hen-Hsen Huang, Hsin-Hsi Chen
Inspired by the implicit mental process of how human beings assess explanations, we present a novel approach, Zero-shot Augmentation of Rationale-Answer pairs (ZARA), to automatically construct pseudo-parallel data for self-training by reducing the problem of plausibility judgement to natural language inference.
1 code implementation • 17 Apr 2023 • Yi-Pei Chen, An-Zi Yen, Hen-Hsen Huang, Hideki Nakayama, Hsin-Hsi Chen
Our proposed life event dialog dataset and in-depth analysis of IE frameworks will facilitate future research on life event extraction from conversations.
1 code implementation • 7 Feb 2023 • Sin-Han Yang, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Fake news and misinformation spread rapidly on the Internet.
no code implementations • 13 Nov 2022 • Chung-Chi Chen, Hiroya Takamura, Hsin-Hsi Chen
Making our research results positively impact on society and environment is one of the goals our community has been pursuing recently.
no code implementations • EACL 2021 • Yi-Ting Liou, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Textual information extraction is a typical research topic in the NLP community.
no code implementations • SEMEVAL 2020 • Po-Chun Chen, Hen-Hsen Huang, Hsin-Hsi Chen
This paper presents our hierarchical multi-task learning (HMTL) and multi-task learning (MTL) approaches for improving the text encoder in Sub-tasks A, B, and C of Multilingual Offensive Language Identification in Social Media (SemEval-2020 Task 12).
no code implementations • COLING 2020 • Charles Hinson, Hen-Hsen Huang, Hsin-Hsi Chen
Most recent works in the field of grammatical error correction (GEC) rely on neural machine translation-based models.
no code implementations • ACL 2020 • Shyh-Shiun Hung, Hen-Hsen Huang, Hsin-Hsi Chen
This work proposes a standalone, complete Chinese discourse parser for practical applications.
no code implementations • 5 May 2020 • Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Opinion mining is a prevalent research issue in many domains.
no code implementations • 4 May 2020 • Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Financial Technology (FinTech) is one of the worldwide rapidly-rising topics in the past five years according to the statistics of FinTech from Google Trends.
no code implementations • 4 May 2020 • An-Zi Yen, Hen-Hsen Huang, Hsin-Hsi Chen
With the advance of science and technology, people are used to record their daily life events via writing blogs, uploading social media posts, taking photos, or filming videos.
no code implementations • LREC 2020 • Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
In this paper, we investigate the annotation of financial social media data from several angles.
no code implementations • LREC 2020 • Ting-Yu Yen, Yang-Yin Lee, Yow-Ting Shiue, Hen-Hsen Huang, Hsin-Hsi Chen
However, most of these datasets are not designed for evaluating sense embeddings.
no code implementations • LREC 2020 • Yi-Ting Chen, Hen-Hsen Huang, Hsin-Hsi Chen
In this paper, we collect the conversions from TV series scripts, and annotate emotion and interpersonal relationship labels on each utterance.
no code implementations • LREC 2020 • Lin Chuan-An, Shyh-Shiun Hung, Hen-Hsen Huang, Hsin-Hsi Chen
Chinese discourse parsing, which aims to identify the hierarchical relationships of Chinese elementary discourse units, has not yet a consistent evaluation metric.
no code implementations • WS 2019 • Jian-Fu Lin, Kuo Yu Huang, Hen-Hsen Huang, Hsin-Hsi Chen
Identification of argumentative components is an important stage of argument mining.
1 code implementation • ACL 2019 • Chung-Chi Chen, Hen-Hsen Huang, Hiroya Takamura, Hsin-Hsi Chen
In this paper, we attempt to answer the question of whether neural network models can learn numeracy, which is the ability to predict the magnitude of a numeral at some specific position in a text description.
no code implementations • 14 Sep 2018 • Chung-Chi Chen, Hen-Hsen Huang, Yow-Ting Shiue, Hsin-Hsi Chen
Numerals that contain much information in financial documents are crucial for financial decision making.
no code implementations • COLING 2018 • Yow-Ting Shiue, Hen-Hsen Huang, Hsin-Hsi Chen
For more than 91{\%} of the cases, our system can propose at least one acceptable correction within a list of five candidates.
no code implementations • COLING 2018 • Lin Chuan-An, Hen-Hsen Huang, Zi-Yuan Chen, Hsin-Hsi Chen
This paper demonstrates an end-to-end Chinese discourse parser.
no code implementations • COLING 2018 • Yow-Ting Shiue, Hen-Hsen Huang, Hsin-Hsi Chen
We present a Chinese writing correction system for learning Chinese as a foreign language.
1 code implementation • COLING 2018 • Yang-Yin Lee, Ting-Yu Yen, Hen-Hsen Huang, Yow-Ting Shiue, Hsin-Hsi Chen
In the experiment, we show that the generalized model can outperform previous approaches in three types of experiment: semantic relatedness, contextual word similarity and semantic difference.
no code implementations • ACL 2018 • Hen-Hsen Huang, Chiao-Chen Chen, Hsin-Hsi Chen
The reliability of self-labeled data is an important issue when the data are regarded as ground-truth for training and testing learning-based models.
no code implementations • SEMEVAL 2018 • Yow-Ting Shiue, Hen-Hsen Huang, Hsin-Hsi Chen
This paper presents the NTU NLP Lab system for the SemEval-2018 Capturing Discriminative Attributes task.
no code implementations • IJCNLP 2017 • Wei-Chuan Hsiao, Hen-Hsen Huang, Hsin-Hsi Chen
Besides, we split a relation in KB into type and property.
no code implementations • SEMEVAL 2017 • Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen
Short length, multi-targets, target relation-ship, monetary expressions, and outside reference are characteristics of financial tweets.
no code implementations • SEMEVAL 2017 • Po-Yu Huang, Hen-Hsen Huang, Yu-Wun Wang, Ching Huang, Hsin-Hsi Chen
This study proposes a system to participate in the Clinical TempEval 2017 shared task, a part of the SemEval 2017 Tasks.
no code implementations • ACL 2017 • Yow-Ting Shiue, Hen-Hsen Huang, Hsin-Hsi Chen
Selecting appropriate words to compose a sentence is one common problem faced by non-native Chinese learners.
no code implementations • COLING 2016 • Hen-Hsen Huang, Yen-Chi Shao, Hsin-Hsi Chen
Misuse of Chinese prepositions is one of common word usage errors in grammatical error diagnosis.
no code implementations • COLING 2016 • Yong-Siang Shih, Hsin-Hsi Chen
In this paper, we investigate four important issues together for explicit discourse relation labelling in Chinese texts: (1) discourse connective extraction, (2) linking ambiguity resolution, (3) relation type disambiguation, and (4) argument boundary identification.
no code implementations • COLING 2016 • Sheng-Lun Wei, Yen-Pin Chiu, Hen-Hsen Huang, Hsin-Hsi Chen
With the demo system called NL2KB in this paper, users can browse which properties in KB side may be mapped to for a given relational pattern in NL side.
no code implementations • COLING 2016 • Hen-Hsen Huang, Chang-Rui Yang, Hsin-Hsi Chen
This paper explores the role of tense information in Chinese causal analysis.
no code implementations • 22 Jul 2016 • Kuan-Yu Chen, Shih-Hung Liu, Berlin Chen, Hsin-Min Wang, Hsin-Hsi Chen
Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words, sentences and documents in context.
no code implementations • LREC 2016 • Yow-Ting Shiue, Hsin-Hsi Chen
By utilizing certain combination of the sets of features, we can construct a system that favors precision or recall.
no code implementations • LREC 2016 • Huan-Yuan Chen, Wan-Shan Liao, Hen-Hsen Huang, Hsin-Hsi Chen
Marker-Sum feature considers total contribution of markers and Marker-Preference feature captures the probability distribution of discourse functions of a representative marker by using preference rule.
no code implementations • LREC 2016 • Chung-Lun Kuo, Hsin-Hsi Chen
How-knowledge is indispensable in daily life, but has relatively less quantity and poorer quality than what-knowledge in publicly available knowledge bases.
no code implementations • 14 Jun 2015 • Kuan-Yu Chen, Shih-Hung Liu, Hsin-Min Wang, Berlin Chen, Hsin-Hsi Chen
Owing to the rapidly growing multimedia content available on the Internet, extractive spoken document summarization, with the purpose of automatically selecting a set of representative sentences from a spoken document to concisely express the most important theme of the document, has been an active area of research and experimentation.
no code implementations • LREC 2014 • Hen-Hsen Huang, Huan-Yuan Chen, Chang-Sheng Yu, Hsin-Hsi Chen, Po-Ching Lee, Chun-Hsun Chen
To deal with this problem, we propose a sentence rephrasing approach to replace each OOV word in a sentence with a popular word of the same named entity type in the training set, so that the knowledge of the word forms can be used for parsing.
no code implementations • LREC 2012 • Chi-Hsin Yu, Yi-jie Tang, Hsin-Hsi Chen
Web provides a large-scale corpus for researchers to study the language usages in real world.
no code implementations • LREC 2012 • Chieh-Jen Wang, Shuk-Man Cheng, Lung-Hao Lee, Hsin-Hsi Chen, Wen-shen Liu, Pei-Wen Huang, Shih-Peng Lin
This paper proposes a method to construct an evaluation dataset from microblogs for the development of recommendation systems.
no code implementations • LREC 2012 • Yi-jie Tang, Hsin-Hsi Chen
The conversations between posters and repliers in microblogs form a valuable writer-reader emotion corpus.