Search Results for author: Yun-Nung Chen

Found 92 papers, 52 papers with code

Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling

1 code implementation6 Mar 2024 Chao-Wei Huang, Chen-An Li, Tsu-Yuan Hsu, Chen-Yu Hsu, Yun-Nung Chen

Dense retrieval methods have demonstrated promising performance in multilingual information retrieval, where queries and documents can be in different languages.

Information Retrieval Retrieval

Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model

2 code implementations29 Nov 2023 Yen-Ting Lin, Yun-Nung Chen

Leveraging a comprehensive pretraining corpus and instruction-finetuning datasets, we have developed a model that not only understands the complexities of Traditional Chinese but also embodies the cultural context of Taiwan.

Language Modelling Large Language Model

SalesBot 2.0: A Human-Like Intent-Guided Chit-Chat Dataset

no code implementations28 Aug 2023 Wen-Yu Chang, Yun-Nung Chen

In recent research on dialogue systems and corpora, there has been a significant focus on two distinct categories: task-oriented (TOD) and open-domain (chit-chat) dialogues.

Zero-Shot Dialogue Relation Extraction by Relating Explainable Triggers and Relation Names

1 code implementation9 Jun 2023 Ze-Song Xu, Yun-Nung Chen

Overall, our findings highlight the potential for this method to enhance the scalability and practicality of DRE systems.

Relation Relation Extraction

Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations

1 code implementation24 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.

In-Context Learning

LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models

no code implementations23 May 2023 Yen-Ting Lin, Yun-Nung Chen

We propose LLM-Eval, a unified multi-dimensional automatic evaluation method for open-domain conversations with large language models (LLMs).

Open-Domain Conversational Question Answering with Historical Answers

1 code implementation17 Nov 2022 Hung-Chieh Fang, Kuo-Han Hung, Chao-Wei Huang, Yun-Nung Chen

Open-domain conversational question answering can be viewed as two tasks: passage retrieval and conversational question answering, where the former relies on selecting candidate passages from a large corpus and the latter requires better understanding of a question with contexts to predict the answers.

Conversational Question Answering Passage Retrieval +1

Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning

1 code implementation12 Oct 2022 Hui-Chi Kuo, Yun-Nung Chen

Intelligent virtual assistants are currently designed to perform tasks or services explicitly mentioned by users, so multiple related domains or tasks need to be performed one by one through a long conversation with many explicit intents.

Language Modelling

PLM-ICD: Automatic ICD Coding with Pretrained Language Models

2 code implementations NAACL (ClinicalNLP) 2022 Chao-Wei Huang, Shang-Chi Tsai, Yun-Nung Chen

Prior work has shown that pretrained language models underperformed on this task with the regular finetuning scheme.

Natural Language Understanding

Miutsu: NTU's TaskBot for the Alexa Prize

no code implementations16 May 2022 Yen-Ting Lin, Hui-Chi Kuo, Ze-Song Xu, Ssu Chiu, Chieh-Chi Hung, Yi-Cheng Chen, Chao-Wei Huang, Yun-Nung Chen

This paper introduces Miutsu, National Taiwan University's Alexa Prize TaskBot, which is designed to assist users in completing tasks requiring multiple steps and decisions in two different domains -- home improvement and cooking.

Question Answering Retrieval

Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding

1 code implementation2 May 2022 Ya-Hsin Chang, Yun-Nung Chen

Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions.

Contrastive Learning Spoken Language Understanding

Islander: A Real-Time News Monitoring and Analysis System

no code implementations25 Apr 2022 Chao-Wei Huang, Kai-Chou Yang, Zi-Yuan Chen, Hao-Chien Cheng, Po-Yu Wu, Yu-Yang Huang, Chung-Kai Hsieh, Geng-Zhi Wildsky Fann, Ting-Yin Cheng, Ethan Tu, Yun-Nung Chen

With thousands of news articles from hundreds of sources distributed and shared every day, news consumption and information acquisition have been increasingly difficult for readers.

SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues

1 code implementation ACL 2022 Ssu Chiu, Maolin Li, Yen-Ting Lin, Yun-Nung Chen

The first one focuses on chatting with users and making them engage in the conversations, where selecting a proper topic to fit the dialogue context is essential for a successful dialogue.

Dialogue Generation

Towards Generating Citation Sentences for Multiple References with Intent Control

no code implementations2 Dec 2021 Jia-Yan Wu, Alexander Te-Wei Shieh, Shih-Ju Hsu, Yun-Nung Chen

Machine-generated citation sentences can aid automated scientific literature review and assist article writing.

Sentence

Relating Neural Text Degeneration to Exposure Bias

no code implementations EMNLP (BlackboxNLP) 2021 Ting-Rui Chiang, Yun-Nung Chen

This work focuses on relating two mysteries in neural-based text generation: exposure bias, and text degeneration.

Language Modelling Text Generation

TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues

1 code implementation SIGDIAL (ACL) 2022 Po-Wei Lin, Shang-Yu Su, Yun-Nung Chen

The goal of dialogue relation extraction (DRE) is to identify the relation between two entities in a given dialogue.

Relation Relation Extraction

Modeling Diagnostic Label Correlation for Automatic ICD Coding

1 code implementation NAACL 2021 Shang-Chi Tsai, Chao-Wei Huang, Yun-Nung Chen

To address this problem, we propose a two-stage framework to improve automatic ICD coding by capturing the label correlation.

Medical Code Prediction

Why Can You Lay Off Heads? Investigating How BERT Heads Transfer

no code implementations14 Jun 2021 Ting-Rui Chiang, Yun-Nung Chen

Hence, the acceptable deduction of performance on the pre-trained task when distilling a model can be derived from the results, and we further compare the behavior of the pruned model before and after fine-tuning.

Transfer Learning

An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker

1 code implementation27 Jan 2021 Yen-Ting Lin, Yun-Nung Chen

There has been a rapid development in data-driven task-oriented dialogue systems with the benefit of large-scale datasets.

dialog state tracking Dialogue State Tracking +1

TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation

1 code implementation NeurIPS 2020 Chun-Hsing Lin, Siang-Ruei Wu, Hung-Yi Lee, Yun-Nung Chen

Score function-based natural language generation (NLG) approaches such as REINFORCE, in general, suffer from low sample efficiency and training instability problems.

Text Generation

TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation

1 code implementation27 Nov 2020 Chun-Hsing Lin, Siang-Ruei Wu, Hung-Yi Lee, Yun-Nung Chen

Score function-based natural language generation (NLG) approaches such as REINFORCE, in general, suffer from low sample efficiency and training instability problems.

Text Generation

Adapting Pretrained Transformer to Lattices for Spoken Language Understanding

1 code implementation2 Nov 2020 Chao-Wei Huang, Yun-Nung Chen

It is shown that encoding lattices as opposed to 1-best results generated by automatic speech recognizer (ASR) boosts the performance of spoken language understanding (SLU).

Natural Language Understanding speech-recognition +2

Real-time Tropical Cyclone Intensity Estimation by Handling Temporally Heterogeneous Satellite Data

no code implementations28 Oct 2020 Boyo Chen, Buo-Fu Chen, Yun-Nung Chen

Analyzing big geophysical observational data collected by multiple advanced sensors on various satellite platforms promotes our understanding of the geophysical system.

Generative Adversarial Network

What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding

1 code implementation EMNLP 2020 Yu-An Wang, Yun-Nung Chen

This paper focuses on providing a new insight of pre-trained position embeddings through feature-level analysis and empirical experiments on most of iconic NLP tasks.

Language Modelling Position

Dual Inference for Improving Language Understanding and Generation

1 code implementation Findings of the Association for Computational Linguistics 2020 Shang-Yu Su, Yung-Sung Chuang, Yun-Nung Chen

Natural language understanding (NLU) and Natural language generation (NLG) tasks hold a strong dual relationship, where NLU aims at predicting semantic labels based on natural language utterances and NLG does the opposite.

Natural Language Understanding Text Generation

Lifelong Language Knowledge Distillation

1 code implementation EMNLP 2020 Yung-Sung Chuang, Shang-Yu Su, Yun-Nung Chen

It is challenging to perform lifelong language learning (LLL) on a stream of different tasks without any performance degradation comparing to the multi-task counterparts.

Knowledge Distillation Language Modelling +3

Towards Unsupervised Language Understanding and Generation by Joint Dual Learning

1 code implementation ACL 2020 Shang-Yu Su, Chao-Wei Huang, Yun-Nung Chen

The prior work is the first attempt that utilized the duality between NLU and NLG to improve the performance via a dual supervised learning framework.

Natural Language Understanding Text Generation

DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs

1 code implementation IJCNLP 2019 Yi-Lin Tuan, Yun-Nung Chen, Hung-Yi Lee

This paper proposes a new task about how to apply dynamic knowledge graphs in neural conversation model and presents a novel TV series conversation corpus (DyKgChat) for the task.

Benchmarking Dialogue Generation +1

An Empirical Study of Content Understanding in Conversational Question Answering

1 code implementation24 Sep 2019 Ting-Rui Chiang, Hao-Tong Ye, Yun-Nung Chen

However, to best of our knowledge, two important questions for conversational comprehension research have not been well studied: 1) How well can the benchmark dataset reflect models' content understanding?

Conversational Question Answering

Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding

1 code implementation24 Sep 2019 Chao-Wei Huang, Yun-Nung Chen

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks.

Spoken Language Understanding

Tree Transformer: Integrating Tree Structures into Self-Attention

3 code implementations IJCNLP 2019 Yau-Shian Wang, Hung-Yi Lee, Yun-Nung Chen

This paper proposes Tree Transformer, which adds an extra constraint to attention heads of the bidirectional Transformer encoder in order to encourage the attention heads to follow tree structures.

Language Modelling

QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization

1 code implementation IJCNLP 2019 Yi-Ting Yeh, Yun-Nung Chen

Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets.

Question Answering Reading Comprehension

Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation

no code implementations22 Aug 2019 Kuan-Yen Lin, Chao-Chun Hsu, Yun-Nung Chen, Lun-Wei Ku

After the entropy-enhanced DMN secures the video context, we apply an attention model that in-corporates summary and caption to generate an accurate answer given the question about the video.

Dialogue Generation Scene-Aware Dialogue

Reactive Multi-Stage Feature Fusion for Multimodal Dialogue Modeling

no code implementations14 Aug 2019 Yi-Ting Yeh, Tzu-Chuan Lin, Hsiao-Hua Cheng, Yu-Hsuan Deng, Shang-Yu Su, Yun-Nung Chen

Visual question answering and visual dialogue tasks have been increasingly studied in the multimodal field towards more practical real-world scenarios.

Question Answering Scene-Aware Dialogue +2

FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension

1 code implementation WS 2019 Yi-Ting Yeh, Yun-Nung Chen

Conversational machine comprehension requires deep understanding of the dialogue flow, and the prior work proposed FlowQA to implicitly model the context representations in reasoning for better understanding.

Reading Comprehension

HUMBO: Bridging Response Generation and Facial Expression Synthesis

no code implementations24 May 2019 Shang-Yu Su, Po-Wei Lin, Yun-Nung Chen

Spoken dialogue systems that assist users to solve complex tasks such as movie ticket booking have become an emerging research topic in artificial intelligence and natural language processing areas.

Dialogue Generation Response Generation +1

Dual Supervised Learning for Natural Language Understanding and Generation

2 code implementations ACL 2019 Shang-Yu Su, Chao-Wei Huang, Yun-Nung Chen

Natural language understanding (NLU) and natural language generation (NLG) are both critical research topics in the NLP field.

Natural Language Understanding Text Generation

Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model

no code implementations23 Mar 2019 Hao-Tong Ye, Kai-Ling Lo, Shang-Yu Su, Yun-Nung Chen

End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus.

Dialogue Generation Response Generation

Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer

no code implementations21 Mar 2019 Ting-Rui Chiang, Chao-Wei Huang, Shang-Yu Su, Yun-Nung Chen

With the increasing research interest in dialogue response generation, there is an emerging branch formulating this task as selecting next sentences, where given the partial dialogue contexts, the goal is to determine the most probable next sentence.

Response Generation Sentence

RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection

no code implementations21 Mar 2019 Chao-Wei Huang, Ting-Rui Chiang, Shang-Yu Su, Yun-Nung Chen

The response selection has been an emerging research topic due to the growing interest in dialogue modeling, where the goal of the task is to select an appropriate response for continuing dialogues.

Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems

1 code implementation NAACL 2019 Ting-Rui Chiang, Yun-Nung Chen

Solving math word problems is a challenging task that requires accurate natural language understanding to bridge natural language texts and math expressions.

Math Math Word Problem Solving +2

Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder

no code implementations31 Oct 2018 Yu-An Wang, Yu-Kai Huang, Tzu-Chuan Lin, Shang-Yu Su, Yun-Nung Chen

Automatic melody generation has been a long-time aspiration for both AI researchers and musicians.

BCWS: Bilingual Contextual Word Similarity

2 code implementations21 Oct 2018 Ta-Chung Chi, Ching-Yen Shih, Yun-Nung Chen

This paper introduces the first dataset for evaluating English-Chinese Bilingual Contextual Word Similarity, namely BCWS (https://github. com/MiuLab/BCWS).

Word Similarity

TopicGAN: Unsupervised Text Generation from Explainable Latent Topics

no code implementations27 Sep 2018 Yau-Shian Wang, Yun-Nung Chen, Hung-Yi Lee

Learning discrete representations of data and then generating data from the discovered representations have been increasingly studied because the obtained discrete representations can benefit unsupervised learning.

Image Generation Text Generation

Investigating Linguistic Pattern Ordering in Hierarchical Natural Language Generation

1 code implementation19 Sep 2018 Shang-Yu Su, Yun-Nung Chen

Natural language generation (NLG) is a critical component in spoken dialogue system, which can be divided into two phases: (1) sentence planning: deciding the overall sentence structure, (2) surface realization: determining specific word forms and flattening the sentence structure into a string.

Sentence Text Generation

Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts

1 code implementation15 Sep 2018 Chih-Wen Goo, Yun-Nung Chen

Neural abstractive summarization has been increasingly studied, where the prior work mainly focused on summarizing single-speaker documents (news, scientific publications, etc).

Abstractive Dialogue Summarization Abstractive Text Summarization +1

CLUSE: Cross-Lingual Unsupervised Sense Embeddings

1 code implementation EMNLP 2018 Ta-Chung Chi, Yun-Nung Chen

The model is evaluated on the Stanford Contextual Word Similarity (SCWS) dataset to ensure the quality of monolingual sense embeddings.

Representation Learning Word Similarity

xSense: Learning Sense-Separated Sparse Representations and Textual Definitions for Explainable Word Sense Networks

1 code implementation10 Sep 2018 Ting-Yun Chang, Ta-Chung Chi, Shang-Chi Tsai, Yun-Nung Chen

This paper focuses on interpreting the embeddings for various aspects, including sense separation in the vector dimensions and definition generation.

Word Embeddings Word Sense Disambiguation

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

3 code implementations EMNLP 2018 Shang-Yu Su, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning.

Task-Completion Dialogue Policy Learning

Slot-Gated Modeling for Joint Slot Filling and Intent Prediction

2 code implementations NAACL 2018 Chih-Wen Goo, Guang Gao, Yun-Kai Hsu, Chih-Li Huo, Tsung-Chieh Chen, Keng-Wei Hsu, Yun-Nung Chen

Attention-based recurrent neural network models for joint intent detection and slot filling have achieved the state-of-the-art performance, while they have independent attention weights.

Intent Detection Sentence +4

Open-Domain Neural Dialogue Systems

no code implementations IJCNLP 2017 Yun-Nung Chen, Jianfeng Gao

In the past decade, spoken dialogue systems have been the most prominent component in today{'}s personal assistants.

Dialogue Management Dialogue State Tracking +4

Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning

no code implementations31 Oct 2017 Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen, Kam-Fai Wong

This paper presents a new method --- adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems.

Task-Completion Dialogue Policy Learning

Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding

1 code implementation30 Sep 2017 Po-Chun Chen, Ta-Chung Chi, Shang-Yu Su, Yun-Nung Chen

However, the previous model only paid attention to the content in history utterances without considering their temporal information and speaker roles.

Dialogue State Tracking Spoken Language Understanding

Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning

1 code implementation IJCNLP 2017 Ta-Chung Chi, Po-Chun Chen, Shang-Yu Su, Yun-Nung Chen

Language understanding (LU) and dialogue policy learning are two essential components in conversational systems.

Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification

no code implementations16 Sep 2017 Bo-Ru Lu, Frank Shyu, Yun-Nung Chen, Hung-Yi Lee, Lin-shan Lee

Connectionist temporal classification (CTC) is a powerful approach for sequence-to-sequence learning, and has been popularly used in speech recognition.

Abstractive Text Summarization General Classification +2

MUSE: Modularizing Unsupervised Sense Embeddings

1 code implementation EMNLP 2017 Guang-He Lee, Yun-Nung Chen

This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts.

Reinforcement Learning (RL) Representation Learning

Real-time On-Demand Crowd-powered Entity Extraction

1 code implementation12 Apr 2017 Ting-Hao 'Kenneth' Huang, Yun-Nung Chen, Jeffrey P. Bigham

Output-agreement mechanisms such as ESP Game have been widely used in human computation to obtain reliable human-generated labels.

Entity Extraction using GAN

End-to-End Task-Completion Neural Dialogue Systems

13 code implementations IJCNLP 2017 Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, Asli Celikyilmaz

One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges.

Chatbot

End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager

1 code implementation3 Dec 2016 Xuesong Yang, Yun-Nung Chen, Dilek Hakkani-Tur, Paul Crook, Xiujun Li, Jianfeng Gao, Li Deng

Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance.

Natural Language Understanding

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

1 code implementation ACL 2017 Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng

In this paper, we address this limitation by replacing symbolic queries with an induced "soft" posterior distribution over the KB that indicates which entities the user is interested in.

reinforcement-learning Reinforcement Learning (RL) +2

AppDialogue: Multi-App Dialogues for Intelligent Assistants

no code implementations LREC 2016 Ming Sun, Yun-Nung Chen, Zhenhao Hua, Yulian Tamres-Rudnicky, Arnab Dash, Alex Rudnicky, er

Users will interact with an individual app on smart devices (e. g., phone, TV, car) to fulfill a specific goal (e. g. find a photographer), but users may also pursue more complex tasks that will span multiple domains and apps (e. g. plan a wedding ceremony).

AIMU: Actionable Items for Meeting Understanding

no code implementations LREC 2016 Yun-Nung Chen, Dilek Hakkani-T{\"u}r

This paper presents an extended set of annotations for the ICSI meeting corpus with a goal of deeply understanding meeting conversations, where participant turns are annotated by actionable items that could be performed by an automated meeting assistant.

Cannot find the paper you are looking for? You can Submit a new open access paper.