Search Results for author:
Found 47 papers, 13 papers with code
Multi-Facet Blending for Faceted Query-by-Example Retrieval
In this paper, we propose a multi-facet blending (FaBle) augmentation method, which exploits modularity by decomposing and recomposing to explicitly synthesize facet-specific training sets.
Guide-to-Explain for Controllable Summarization
Recently, large language models (LLMs) have demonstrated remarkable performance in abstractive summarization tasks.
Multi-aspect Depression Severity Assessment via Inductive Dialogue System
With the advancement of chatbots and the growing demand for automatic depression detection, identifying depression in patient conversations has gained more attention.
Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages
Automatic question generation (QG) serves a wide range of purposes, such as augmenting question-answering (QA) corpora, enhancing chatbot systems, and developing educational materials.
Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing
In this study, we propose Cross-Lingual Back-Parsing (CBP), a novel data augmentation methodology designed to enhance cross-lingual transfer for SP.
Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering
We apply the grammar to knowledge base question answering, where the constraints by candidate expressions assist a semantic parser to generate valid KB elements.
Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards
Recent advances in automated essay scoring (AES) have shifted towards evaluating multiple traits to provide enriched feedback.
Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model
Our method proves to be a scalable and effective solution for generating high-quality G2T data, significantly advancing the field of G2T generation.
Ranked #1 on
Data-to-Text Generation
on WikiOFGraph
Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT
Traditional dialogue state tracking approaches heavily rely on extensive training data and handcrafted features, limiting their scalability and adaptability to new domains.
Keyword-Aware ASR Error Augmentation for Robust Dialogue State Tracking
Dialogue State Tracking (DST) is a key part of task-oriented dialogue systems, identifying important information in conversations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
An Investigation Into Explainable Audio Hate Speech Detection
The cascading approach initially converts audio to transcripts, identifies hate speech within these transcripts, and subsequently locates the corresponding audio time frames.
Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning
To maximize the advantage of context awareness, our approach includes decoder pre-training using text-based dialogue data and noise representation learning for a context encoder.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
DiagESC: Dialogue Synthesis for Integrating Depression Diagnosis into Emotional Support Conversation
Dialogue systems for mental health care aim to provide appropriate support to individuals experiencing mental distress.
Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment
In automated pronunciation assessment, recent emphasis progressively lies on evaluating multiple aspects to provide enriched feedback.
Key-Element-Informed sLLM Tuning for Document Summarization
Remarkable advances in large language models (LLMs) have enabled high-quality text summarization.
Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning
The evaluation of summary quality encompasses diverse dimensions such as consistency, coherence, relevance, and fluency.
Multi-Objective Reinforcement Learning
Multi-Task Learning
+3
Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents
Recent advancements in open-domain dialogue systems have been propelled by the emergence of high-quality large language models (LLMs) and various effective training methodologies.
Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation
Contemporary neural speech synthesis models have indeed demonstrated remarkable proficiency in synthetic speech generation as they have attained a level of quality comparable to that of human-produced speech.
Explainable Multi-hop Question Generation: An End-to-End Approach without Intermediate Question Labeling
We also prove that our model logically and incrementally increases the complexity of questions, and the generated multi-hop questions are also beneficial for training question answering models.
Denoising Table-Text Retrieval for Open-Domain Question Answering
Previous studies in table-text open-domain question answering have two common challenges: firstly, their retrievers can be affected by false-positive labels in training datasets; secondly, they may struggle to provide appropriate evidence for questions that require reasoning across the table.
Ranked #3 on
Question Answering
on OTT-QA
Autoregressive Score Generation for Multi-trait Essay Scoring
Recently, encoder-only pre-trained models such as BERT have been successfully applied in automated essay scoring (AES) to predict a single overall score.
Optimizing Two-Pass Cross-Lingual Transfer Learning: Phoneme Recognition and Phoneme to Grapheme Translation
This research contributes to the advancements of two-pass ASR systems in low-resource languages, offering the potential for improved cross-lingual transfer learning.
Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking
We address this by investigating synthetic audio data for audio-based DST.
Score-balanced Loss for Multi-aspect Pronunciation Assessment
With rapid technological growth, automatic pronunciation assessment has transitioned toward systems that evaluate pronunciation in various aspects, such as fluency and stress.
Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring
Thus, predicting various trait scores of unseen-prompt essays (called cross-prompt essay trait scoring) is a remaining challenge of AES.
DORIC : Domain Robust Fine-Tuning for Open Intent Clustering through Dependency Parsing
We present our work on Track 2 in the Dialog System Technology Challenges 11 (DSTC11).
Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Tracking
In dialogue state tracking (DST), labeling the dataset involves considerable human labor.
Hierarchical Pronunciation Assessment with Multi-Aspect Attention
In this paper, we propose a Hierarchical Pronunciation Assessment with Multi-aspect Attention (HiPAMA) model, which hierarchically represents the granularity levels to directly capture their linguistic structures and introduces multi-aspect attention that reflects associations across aspects at the same level to create more connotative representations.
Multi-Type Conversational Question-Answer Generation with Closed-ended and Unanswerable Questions
Conversational question answering (CQA) facilitates an incremental and interactive understanding of a given context, but building a CQA system is difficult for many domains due to the problem of data scarcity.
Schema Encoding for Transferable Dialogue State Tracking
In this paper, we propose Schema Encoding for Transferable Dialogue State Tracking (SETDST), which is a neural DST method for effective transfer to new domains.
Conversational QA Dataset Generation with Answer Revision
Conversational question--answer generation is a task that automatically generates a large-scale conversational question answering dataset based on input passages.
SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task
Few-shot dialogue state tracking (DST) model tracks user requests in dialogue with reliable accuracy even with a small amount of data.
High Recall Data-to-text Generation with Progressive Edit
We observed that when the same target sentence was repeated twice, Transformer (T5) based model generates an output made up of asymmetric sentences from structured inputs.
DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context
In this paper, we propose a multi-domain task-oriented dialogue system, called Dialogue System with Optimizing a Recurrent Action Policy using Efficient Context (DORA), that uses SL, with subsequently applied RL to optimize dialogue systems using a recurrent dialogue policy.
Domain State Tracking for a Simplified Dialogue System
In this paper, we present DoTS (Domain State Tracking for a Simplified Dialogue System), a task-oriented dialogue system that uses a simplified input context instead of the entire dialogue history.
Out-of-domain Detection based on Generative Adversarial Network
The main goal of this paper is to develop out-of-domain (OOD) detection for dialog systems.
Generative Adversarial Network
Out of Distribution (OOD) Detection
+1
Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systems
Then we used domain-category analysis as an auxiliary task to train neural sentence embedding for OOD sentence detection.
Automatic Open Knowledge Acquisition via Long Short-Term Memory Networks with Feedback Negative Sampling
To the best of our knowledge, this is the first work to apply deep learning to Open IE.
Grammatical Error Annotation for Korean Learners of Spoken English
The goal of our research is to build a grammatical error-tagged corpus for Korean learners of Spoken English dubbed Postech Learner Corpus.
