Search Results for author:
Found 109 papers, 63 papers with code
Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature Similarity
Multi-task auxiliary learning utilizes a set of relevant auxiliary tasks to improve the performance of a primary task.
FactAlign: Long-form Factuality Alignment of Large Language Models
In this paper, we address this gap by proposing FactAlign, a novel alignment framework designed to enhance the factuality of LLMs' long-form responses while maintaining their helpfulness.
PairDistill: Pairwise Relevance Distillation for Dense Retrieval
Effective information retrieval (IR) from vast datasets relies on advanced techniques to extract relevant information in response to queries.
Rehearsing Answers to Probable Questions with Perspective-Taking
Question answering (QA) has been a long-standing focus in the NLP field, predominantly addressing reading comprehension and common sense QA.
Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition
Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models
Structured generation, the process of producing content in standardized formats like JSON and XML, is widely utilized in real-world applications to extract key output information from large language models (LLMs).
I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation
This study explores the proactive ability of LLMs to seek user support.
Visualizing Dialogues: Enhancing Image Selection through Dialogue Understanding with Large Language Models
Recent advancements in dialogue systems have highlighted the significance of integrating multimodal responses, which enable conveying ideas through diverse modalities rather than solely relying on text-based interactions.
A Survey of Data Synthesis Approaches
This paper provides a detailed survey of synthetic data techniques.
DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging
Reinforcement learning from human feedback (RLHF) is a popular strategy for aligning large language models (LLMs) with desired behaviors.
StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment.
A Survey of Generative Information Retrieval
By examining state-of-the-art GR techniques and their applications, this survey aims to provide a foundational understanding of GR and inspire further innovations in this transformative approach to information retrieval.
A Survey of Useful LLM Evaluation
We proposed the two-stage framework: from ``core ability'' to ``agent'', clearly explaining how LLMs can be applied based on their specific capabilities, along with the evaluation methods in each stage.
Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
To foster future research, we have released the complementary materials such as paper collection publicly at https://github. com/MiuLab/EditLLM-Survey
Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization
The concept of persona, originally adopted in dialogue literature, has re-surged as a promising framework for tailoring large language models (LLMs) to specific context (e. g., personalized search, LLM-as-a-judge).
Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning
This model excels in transitioning topics, understanding user intents, and selecting appropriate strategies.
Measuring Taiwanese Mandarin Language Understanding
We present TMLU, a holistic evaluation suit tailored for assessing the advanced knowledge and reasoning capability in LLMs, under the context of Taiwanese Mandarin.
InstUPR : Instruction-based Unsupervised Passage Reranking with Large Language Models
This paper introduces InstUPR, an unsupervised passage reranking method based on large language models (LLMs).
Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling
Dense retrieval methods have demonstrated promising performance in multilingual information retrieval, where queries and documents can be in different languages.
Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model
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.
CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation
Conversational search provides a natural interface for information retrieval (IR).
SalesBot 2.0: A Human-Like Intent-Guided Chit-Chat Dataset
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
Overall, our findings highlight the potential for this method to enhance the scalability and practicality of DRE systems.
Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations
Finally, we perform ICL for the test input with the pseudo-input-label pairs as demonstrations.
LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models
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
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.
Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning
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.
Controllable User Dialogue Act Augmentation for Dialogue State Tracking
Prior work has demonstrated that data augmentation is useful for improving dialogue state tracking.
PLM-ICD: Automatic ICD Coding with Pretrained Language Models
Prior work has shown that pretrained language models underperformed on this task with the regular finetuning scheme.
Miutsu: NTU's TaskBot for the Alexa Prize
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.
Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding
Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions.
Islander: A Real-Time News Monitoring and Analysis System
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
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.
BARCOR: Towards A Unified Framework for Conversational Recommendation Systems
CRS is a complex problem that consists of two main tasks: (1) recommendation and (2) response generation.
Towards Generating Citation Sentences for Multiple References with Intent Control
Machine-generated citation sentences can aid automated scientific literature review and assist article writing.
Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems
Task-oriented dialogue systems have been a promising area in the NLP field.
Relating Neural Text Degeneration to Exposure Bias
This work focuses on relating two mysteries in neural-based text generation: exposure bias, and text degeneration.
TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues
The goal of dialogue relation extraction (DRE) is to identify the relation between two entities in a given dialogue.
Modeling Diagnostic Label Correlation for Automatic ICD Coding
To address this problem, we propose a two-stage framework to improve automatic ICD coding by capturing the label correlation.
Why Can You Lay Off Heads? Investigating How BERT Heads Transfer
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.
Mitigating Biases in Toxic Language Detection through Invariant Rationalization
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse.
An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker
There has been a rapid development in data-driven task-oriented dialogue systems with the benefit of large-scale datasets.
TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation
Score function-based natural language generation (NLG) approaches such as REINFORCE, in general, suffer from low sample efficiency and training instability problems.
TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation
Score function-based natural language generation (NLG) approaches such as REINFORCE, in general, suffer from low sample efficiency and training instability problems.
Overview of the Ninth Dialog System Technology Challenge: DSTC9
Interactive evaluation of dialog, and 4.
Adapting Pretrained Transformer to Lattices for Spoken Language Understanding
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).
Zero-Shot Rationalization by Multi-Task Transfer Learning from Question Answering
Extracting rationales can help human understand which information the model utilizes and how it makes the prediction towards better interpretability.
Real-time Tropical Cyclone Intensity Estimation by Handling Temporally Heterogeneous Satellite Data
Analyzing big geophysical observational data collected by multiple advanced sensors on various satellite platforms promotes our understanding of the geophysical system.
What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding
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.
Dual Inference for Improving Language Understanding and Generation
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.
Lifelong Language Knowledge Distillation
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.
Learning Spoken Language Representations with Neural Lattice Language Modeling
Pre-trained language models have achieved huge improvement on many NLP tasks.
Towards Unsupervised Language Understanding and Generation by Joint Dual Learning
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.
Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification
Also, the performance is on par with a recently proposed weakly-supervised text classification method.
What Does This Word Mean? Explaining Contextualized Embeddings with Natural Language Definition
Contextualized word embeddings have boosted many NLP tasks compared with traditional static word embeddings.
Leveraging Hierarchical Category Knowledge for Data-Imbalanced Multi-Label Diagnostic Text Understanding
Clinical notes are essential medical documents to record each patient{'}s symptoms.
Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation
We first build a pointer-generator baseline model for conclusion generation.
DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs
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.
Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding
Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks.
An Empirical Study of Content Understanding in Conversational Question Answering
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?
Tree Transformer: Integrating Tree Structures into Self-Attention
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.
QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization
Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets.
Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
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.
Reactive Multi-Stage Feature Fusion for Multimodal Dialogue Modeling
Visual question answering and visual dialogue tasks have been increasingly studied in the multimodal field towards more practical real-world scenarios.
FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
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.
HUMBO: Bridging Response Generation and Facial Expression Synthesis
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.
Dual Supervised Learning for Natural Language Understanding and Generation
Natural language understanding (NLU) and natural language generation (NLG) are both critical research topics in the NLP field.
Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain Adaptation
Spoken question answering (SQA) is challenging due to complex reasoning on top of the spoken documents.
Ranked #3 on
Spoken Language Understanding
on Spoken-SQuAD
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus.
Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer
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.
RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection
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.
Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
Automatic melody generation has been a long-time aspiration for both AI researchers and musicians.
BCWS: Bilingual Contextual Word Similarity
This paper introduces the first dataset for evaluating English-Chinese Bilingual Contextual Word Similarity, namely BCWS (https://github. com/MiuLab/BCWS).
TopicGAN: Unsupervised Text Generation from Explainable Latent Topics
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.
Investigating Linguistic Pattern Ordering in Hierarchical Natural Language Generation
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.
Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts
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
The model is evaluated on the Stanford Contextual Word Similarity (SCWS) dataset to ensure the quality of monolingual sense embeddings.
xSense: Learning Sense-Separated Sparse Representations and Textual Definitions for Explainable Word Sense Networks
This paper focuses on interpreting the embeddings for various aspects, including sense separation in the vector dimensions and definition generation.
Dynamically Context-Sensitive Time-Decay Attention for Dialogue Modeling
Spoken language understanding (SLU) is an essential component in conversational systems.
Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning
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.
Slot-Gated Modeling for Joint Slot Filling and Intent Prediction
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.
Ranked #8 on
Slot Filling
on SNIPS
How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogues
Spoken language understanding (SLU) is an essential component in conversational systems.
Open-Domain Neural Dialogue Systems
In the past decade, spoken dialogue systems have been the most prominent component in today{'}s personal assistants.
Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning
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.
Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning
Language understanding (LU) and dialogue policy learning are two essential components in conversational systems.
Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding
However, the previous model only paid attention to the content in history utterances without considering their temporal information and speaker roles.
Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification
Connectionist temporal classification (CTC) is a powerful approach for sequence-to-sequence learning, and has been popularly used in speech recognition.
MUSE: Modularizing Unsupervised Sense Embeddings
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.
Real-time On-Demand Crowd-powered Entity Extraction
Output-agreement mechanisms such as ESP Game have been widely used in human computation to obtain reliable human-generated labels.
Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems
Language understanding is a key component in a spoken dialogue system.
End-to-End Task-Completion Neural Dialogue Systems
One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges.
A User Simulator for Task-Completion Dialogues
Then, one can train reinforcement learning agents in an online fashion as they interact with the simulator.
End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager
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.
Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
Natural language understanding (NLU) is a core component of a spoken dialogue system.
Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
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.
AppDialogue: Multi-App Dialogues for Intelligent Assistants
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
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.
