LLMs Are Few-Shot In-Context Low-Resource Language Learners

Confucius, cyberpunk and Mr. Science: comparing AI ethics principles between China and the EU

Survey of Hallucination in Natural Language Generation

Context Generation Improves Open Domain Question Answering

Contrastive Learning for Inference in Dialogue

Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition

Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference

Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values

Generating Hashtags for Short-form Videos with Guided Signals

Improving Fairness and Robustness in End-to-End Speech Recognition Through Unsupervised Clustering

Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge

InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning

InstructTODS: Large language models for end-to-end task-oriented dialogue systems

Mitigating Framing Bias with Polarity Minimization Loss

NusaCrowd: Open Source Initiative for Indonesian NLP Resources

Nusawrites: Constructing high-quality corpora for underrepresented and extremely low-resource languages

NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages

Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training

RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding

RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training

Towards Answering Ethical Quandary Questions

Towards Mitigating Hallucination in Large Language Models via Self-Reflection

Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue

ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation

Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset

CI-AVSR: A Cantonese Audio-Visual Speech Datasetfor In-car Command Recognition

Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension

Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation

Every picture tells a story: Image-grounded controllable stylistic story generation

Factuality Enhanced Language Models for Open-Ended Text Generation

How Long is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling

IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages

Integrating Question Rewriting in Conversational Question Answering: A Reinforcement Learning Approach

Korean Language Modeling via Syntactic Guide

NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias

QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation

QAConv: Question Answering on Informative Conversations

Read before Generate! Faithful Long Form Question Answering with Machine Reading

Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters

SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study

VScript: Controllable Script Generation with Visual Presentation

VScript: Controllable Script Generation with Visual Presentation

Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data

AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization

Are Multilingual Models Effective in Code-Switching?

Are Multilingual Models Effective in Code-Switching?

Assessing Political Prudence of Open-Domain Chatbots

CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System

Continual Learning in Task-Oriented Dialogue Systems

Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation

CrossNER: Evaluating Cross-Domain Named Entity Recognition

ERICA: An Empathetic Android Companion for Covid-19 Quarantine

Fight for 4230 at CheckThat! 2021: Domain-Specific Preprocessing and Pretrained Model for Ranking Claims by Check-Worthiness

Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance

IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation

Language Models are Few-shot Multilingual Learners

Mitigating Media Bias through Neutral Article Generation

Model Generalization on COVID-19 Fake News Detection

Multimodal End-to-End Sparse Model for Emotion Recognition

On the Importance of Word Order Information in Cross-lingual Sequence Labeling

On Unifying Misinformation Detection

Preserving Cross-Linguality of Pre-trained Models via Continual Learning

The Adapter-Bot: All-In-One Controllable Conversational Model

Towards Few-Shot Fact-Checking via Perplexity

Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization

X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing

XPersona: Evaluating Multilingual Personalized Chatbot

Zero-Shot Dialogue State Tracking via Cross-Task Transfer

Multilingual and Interlingual Semantic Representations for Natural Language Processing: A Brief Introduction

Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems

Caire: An end-to-end empathetic chatbot

CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling

Cross-lingual Spoken Language Understanding with Regularized Representation Alignment

Dimsum @LaySumm 20: BART-based Approach for Scientific Document Summarization

Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning

Generating Empathetic Responses by Looking Ahead the User’s Sentiment

Getting To Know You: User Attribute Extraction from Dialogues

Improving Spoken Question Answering Using Contextualized Word Representation

IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding

Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection

Learning Fast Adaptation on Cross-Accented Speech Recognition

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

Learning to Classify the Wrong Answers for Multiple Choice Question Answering (Student Abstract)

Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer

MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models

Meta-Transfer Learning for Code-Switched Speech Recognition

MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems

Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition

Multi-hop Question Generation with Graph Convolutional Network

Plug-and-Play Conversational Models

Zero-Resource Cross-Domain Named Entity Recognition

A Novel Repetition Normalized Adversarial Reward for Headline Generation

A Submodular Feature-Aware Framework for Label Subset Selection in Extreme Classification Problems.

Attention over Parameters for Dialogue Systems

CAiRE HKUST at SemEval-2019 task 3: Hierarchical attention for dialogue emotion classification

Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning

Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences

End-to-End Question Answering Models for Goal-Oriented Dialog Learning

Exploring Perceived Emotional Intelligence of Personality-driven Virtual Agents in Handling User Challenges

Exploring Social Bias in Chatbots using Stereotype Knowledge

Generalizing Question Answering System with Pre-trained Language Model Fine-tuning

Getting To Know You: User Attribute Extraction from Dialogues

GlobalTrait: Personality Alignment of Multilingual Word Embeddings

Hierarchical Attention for Dialogue Emotion Classification

Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition

Human-agent Communication: Connecting Research and Development in HCI and AI

Incorporate User Representation for Personal Question Answer Selection Using Siamese Network

Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring

Learning Comment Generation by Leveraging User-generated Data

Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition

Modality-based Factorization for Multimodal Fusion

Modality-based Factorization for Multimodal Fusion

MoEL: Mixture of Empathetic Listeners

On the effectiveness of low-rank matrix factorization for LSTM model compression

Personalizing Dialogue Agents via Meta-Learning

Team yeon-zi at SemEval-2019 Task 4: Hyperpartisan News Detection by De-noising Weakly-labeled Data

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

Understanding the Shades of Sexism in Popular TV Series

Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables

Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervision

Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition

Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning

Emo2vec: Learning generalized emotion representation by multi-task training

Empathetic Dialog Systems

End-to-End Dynamic Query Memory Network for Entity-Value Independent Task-oriented Dialog

Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging

Interpreting Word Embeddings with Eigenvector Analysis

Investigating Audio, Video, and Text Fusion Methods for End-to-End Automatic Personality Prediction

MEM2Seq: Effectively Incorporating Knowledge Bases into End-to-end task-Oriented Dialog Systems

PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags

Reducing Gender Bias in Abusive Language Detection

A First Look into a Convolutional Neural Network for speech emotion detection

A Note Based Query by Humming System Using Convolutional Neural Network

Adapting a Virtual Agent to User Personality

Bilingual Word Embeddings for Cross-Lingual Personality Recognition Using Convolutional Neural Nets

Emojive! Collecting Emotion Data from Speech and Facial Expression using Mobile Game App

End-to-End Recurrent Entity Network for Entity-Value Independent Goal-Oriented Dialog Learning

Multimodal Deep Neural Nets for Detecting Humor in TV Sitcoms

Nora the empathetic psychologist

One-step and Two-step Classification for Abusive Language Detection on Twitter

Perceived Emotional Intelligence in Virtual Agents

Towards a Corpus of Speech Emotion for Interactive Dialog Systems

Zara Returns: Improved Personality Induction and Adaptation by an Empathetic Virtual Agent

A Long Short-Term Memory Framework for Predicting Humor in Dialogues

A Machine Learning based Music Retrieval and Recommendation System

Deep Learning of Audio and Language Features for Humor Prediction

Predicting Humor Response in Dialogues from TV Sitcoms

Real-Time Speech Emotion and Sentiment Recognition for Interactive Dialogue Systems

Towards Empathetic Human-Robot Interactions

Towards Empathetic Human-Robot Interactions

Zara The Supergirl: An Empathetic Personality Recognition System

Zara: A Virtual Interactive Dialogue System Incorporating Emotion, Sentiment and Personality Recognition

Zara: An Empathetic Interactive Virtual Agent

Robots with heart

A Comparison between a DNN and a CRF Disfluency Detection and Reconstruction System

HLTC-HKUST: A Neural Network Paraphrase Classifier using Translation Metrics, Semantic Roles and Lexical Similarity Features

Discriminatively Trained Sparse Inverse Covariance Matrices for Speech Recognition

Efficient Sparse Banded Acoustic Models for Speech Recognition

A Hindi-English Code-Switching Corpus

Acoustic modeling for hindi speech recognition in low-resource settings

Code switch language modeling with Functional Head Constraint

Co-Training for Classification of Live or Studio Music Recordings

Language Modeling with Functional Head Constraint for Code Switching Speech Recognition

Cross-Lingual Language Modeling for Low-Resource Speech Recognition

Sparse Inverse Covariance Matrices for Low Resource Speech Recognition

Discriminatively Trained Sparse Inverse Covariance Matrices for Low Resource Acoustic Modeling

Identification of Live or Studio Versions of a Song Via Supervised Learning

Improved Mixed Language Speech Recognition Using Asymmetric Acoustic Model and Language Model with Code-switch Inversion Constraints

Language Modeling for Mixed Language Speech Recognition Using Weighted Phrase Extraction

Multimodal Music Emotion Classification Using AdaBoost with Decision Stumps

These Words Are Music to My Ears: Recognizing Music Emotion from Lyrics using AdaBoost

Active learning with semi-automatic annotation for extractive speech summarization

Automatic Parliamentary Meeting Minute Generation Using Rhetorical Structure Modeling

A Mandarin-English Code-switching Corpus

A Multilingual Database of Natural Stress Emotion

Code Switching Language Model with Translation Constraint for Mixed Language Speech Recognition

Cross-Lingual language modeling with syntactic reordering for low-resource speech recognition

Low Resource Speech Recognition with Automatically Learned Sparse Inverse Covariance Matrices

Personalized music emotion classification via active learning

Phrase-level Transduction Model with Reordering for Spoken to Written Language Transformation

Sparse banded precision matrices for low resource speech recognition

Using English Acoustic Models for Hindi Automatic Speech Recognition

Using English Acoustic Models for Hindi Automatic Speech Recognition

A cross gender and cross lingual study on acoustic features for stress recognition in speech

Asymmetric acoustic modeling of mixed language speech

Automatic minute generation for parliamentary speech using conditional random fields

Mining Parallel Documents Using Low Bandwidth and High Precision CLIR from the Heterogeneous Web

Rare Word Translation Extraction from Aligned Comparable Documents

Extractive speech summarization using shallow rhetorical structure modeling

Building and Mining Parallel Corpora

Chinese Machine Translation

A Very Large Scale Mandarin Chinese Broadcast Collection for the GALE Program

A Very Large Scale Mandarin Chinese Broadcast Corpus for GALE Project

Learning deep rhetorical structure for extractive speech summarization

Rhetorical syntax-driven model for speech summarization

Trillions of comparable documents

Unsupervised synthesis of multilingual wikipedia articles

BUCC 2009: 2nd Workshop on Building and Using Comparable Corpora: from Parallel to Non-parallel Corpora: Proceedings of the Workshop, 6 August 2009, Suntec, Singapore

Active Learning of Extractive Reference Summaries for Lecture Speech Summarization

Can semantic role labeling improve SMT?

Extractive speech summarization by active learning

Rhetorical structure modeling for lecture speech summarization

Semantic Roles for SMT: A Hybrid Two-Pass Model

Multilingual spoken language processing

Rhetorical-state hidden markov models for extractive speech summarization

RSHMM++ for extractive lecture speech summarization

Using output probability distribution for oov word rejection

A comparative study on speech summarization of broadcast news and lecture speech

A mandarin lecture speech transcription system for speech summarization

Improving lecture speech summarization using rhetorical information

Learning Bilingual Semantic Frames: Shallow Semantic Parsing vs. Semantic Role Projection

Aligning word senses using bilingual corpora

One Story One Flow: Hidden Markov Story Models for Multilingual and Multi-document Summarization

Automatic learning of Chinese English semantic structure mapping

HKUST/MTS: A very large scale Mandarin telephone speech corpus

Multi-accent Chinese speech recognition

Robust Word Sense Translation by EM Learning of Frame Semantics

Effects and modeling of phonetic and acoustic confusions in accented speech

Translation disambiguation in mixed language queries

Acoustic and phonetic confusions in accented speech recognition

EARSCTS: A Chinese Telephony Conversational Corpus for Speech Processing

Inversion transduction grammar constraints for mining parallel sentences from quasi-comparable corpora

A maximum-entropy Chinese parser augmented by transformation-based learning

Pronunciation Modeling for Spontaneous Mandarin Speech Recognition

State-dependent phonetic tied mixtures with pronunciation modeling for spontaneous speech recognition

Unsupervised Learning of a Chinese Spontaneous and Colloquial Speech Lexicon with Content and Filler Phrase Classification

A Grammar-Based Chinese to English Speech Translation System for Portable Devices

A system for mandarin short phrase recognition on portable devices

A system for Mandarin short phrase recognition on portable devices

Automatic Construction of an English-Chinese Bilingual FrameNet

BiFrameNet: bilingual Frame Semantics Resource Construction by Cross-lingual Induction

Development of a Chinese telephony conversational corpus for speech processing

From Parallel Corpora to Non-Parallel Corpora, Methods for Bilingual Sentence Extraction

Mining Very-Non-Parallel Corpora: Parallel Sentence and Lexicon Extraction via Bootstrapping and EM

Multi-level Bootstrapping for Extracting Parallel Sentences from a Quasi-comparable Corpora

Sentence Alignment in Paralllel, Comparable and Quasi-comparable Corpora

Using N-best Lists for Named Entity Recognition from Chinese Speech

Modeling partial pronunciation variations for spontaneous Mandarin speech recognition

Automatic phone set extension with confidence measure for spontaneous speech

Flooring the observation probability for robust ASR in impulsive noise

Partial change accent models for accented mandarin speech recognition

Triphone Model Reconstruction for Mandarin Variations

Mandarin pronunciation modeling based on CASS corpus

A Maximum-Entropy Approach to HowNet-based Chinese Word-Sense Disambiguation

Creating a Bilingual Ontology: A Corpus-Based Approach for Aligning WordNet and HowNet

Identifying Concepts Across Languages: A First Step towards a Corpus-based Approach to Automatic Ontology Alignment

Model Partial Pronunciation Variations for Spontaneous Mandarin Speech Recognition

Modeling Partial Pronunciation Variations for Spontaneous Mandarin Speech Recognition

Nouns in WordNet and HowNet: an Analysis and Comparison of Semantic Relations

Partial Change Phone Models for Pronunciation Variations in Spontaneous Mandarin Speech

Reducing pronunciation lexicon confusion and using more data without phonetic transcription for pronunciation modeling

Automatic Generation of Pronunciation Lexicons for Mandarin Spontaneous Speech

CLEF 2001 bilingual task simple dictionary-based query translation

Estimating Pronunciation Variations from Acoustic Likelihood Score for HMM Reconstruction

Modeling Pronunciation Variation Using Context-Dependent Weighting and B/S Refined Acoustic Modeling

Log-add approximation on-line noise compensation method adopting robust decision rules for robust digits recognition

A multi-path syllable to word decoder with language model optimization and automatic lexicon augmentation

A Novel Technique for Frame Selection for GMM-based text-independent Speaker Recognition

A Phonetically Transcribed Corpus of Mandarin Spontaneous Speech

An LLR-based technique of frame selection for GMM-based text-independent speaker identification

MLLR-based accent model adaptation without accented data

Principal mixture speaker adaptation for improved continuous speech recognition

Residual noise compensation for robust speech recognition in nonstationary noise

Rule-Based Word Pronunciation Networks Generation for Mandarin Speech Recognition

SALSA Version 3.0: A Single Recognizer-based Multilingual Speech-based Web Browser

Fast accent identification and accented speech recognition

More efficient and optimal LLR for decoding and verification

Statistical Augmentation of a Chinese Machine-Readable Dictionary

A Monolingual Semantic Decoder Based on Word Sense Disambiguation for Mixed Language

A Monolingual Semantic Decoder based on Word Sense Disambiguation for Mixed Language Query Processing

Decision Tree-Based Triphones are Robust and Practical for Mandarin Speech Recognition

keyword / Fillerword Modeling for Spontaneous Spoken Mixed Language Query Processing

Liftered forward masking procedure for robust digits recognition

MAP-based Cross-Language Adaptation Augmented by Linguistic Knowledge: from English to Chinese

Mixed-language Query Disambiguation

A Statistical View on Bilingual Lexicon Extraction: From Parallel Corpora to Non-Parallel Corpora

Extracting Key Terms from Chinese and Japanese texts

An IR Approach for Translating New Words from Nonparallel, Comparable Texts

Are Initial/Final Units Acoustically Accurate?

SALSA version 1.0, A Speech-Based Web Browser

SALSA, A Multilingual Speech-Based Web Browser

Translating Unknown Words Using Nonparallel, Comparable Texts

Understanding Chinese Spontaneous Speech? Are Mandarin and Cantonese Very Different?

Using English Phoneme Models for Chinese Speech Recognition

Dealing with Multilinguality in a Spoken Language Query Translator

Extracting Japanese Domain and Technical Terms is Relatively Easy

Finding Terminology Translations from Non-parallel Corpora

A Technical Word and Term Translation Aid using Noisy Parallel Corpora Across Language Groups

Domain Word Translation by Space-Frequency Analysis of Context Length Histograms

A Pattern Matching Method for Finding Noun and Proper Noun Translations from Noisy Parallel Corpora

Coerced Markov Models for Cross-lingual Lexical-Tag Relations

Compiling Bilingual Lexicon Entries from a Non-Parallel English-Chinese Corpus

Aligning Noisy Parallel Corpora across Language Groups: Word Pair Feature Matching by Dynamic Time Warping

Improving Chinese tokenization with linguistic Filters on statistical lexical acquisition

K-vec: A New Approach for Aligning Parallel Texts

Statistical Augmentation of a Chinese Machine-Readable Dictionary

Aligning Parallel Texts: Do Methods Developed for English-French generalize to Asian Languages?

The BBN/HARC Spoken Language system

The Estimation of Powerful Language Models from Small and Large Corpora

Design and Performance of HARC, the BBN Spoken Language Understanding System

Improved Speaker Markov Modeling for Unsupervised Speaker Normalization

Unsupervised Speaker Normalization by Speaker Markov Model Converter for Speaker-Independent Speech Recognition

Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervision

Conference paper

Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition

Conference paper

Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning

Conference paper

Emo2vec: Learning generalized emotion representation by multi-task training

Conference paper

Empathetic Dialog Systems

Conference paper

End-to-End Dynamic Query Memory Network for Entity-Value Independent Task-oriented Dialog

Conference paper

Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging

Conference paper

Interpreting Word Embeddings with Eigenvector Analysis

Conference paper

Investigating Audio, Video, and Text Fusion Methods for End-to-End Automatic Personality Prediction

Conference paper

MEM2Seq: Effectively Incorporating Knowledge Bases into End-to-end task-Oriented Dialog Systems

Conference paper

PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags

Conference paper

Reducing Gender Bias in Abusive Language Detection

Conference paper

A First Look into a Convolutional Neural Network for speech emotion detection

Conference paper

A Note Based Query by Humming System Using Convolutional Neural Network

Conference paper

Adapting a Virtual Agent to User Personality

Conference paper

Bilingual Word Embeddings for Cross-Lingual Personality Recognition Using Convolutional Neural Nets

Conference paper

Emojive! Collecting Emotion Data from Speech and Facial Expression using Mobile Game App

Conference paper

End-to-End Recurrent Entity Network for Entity-Value Independent Goal-Oriented Dialog Learning

Conference paper

Multimodal Deep Neural Nets for Detecting Humor in TV Sitcoms

Conference paper

Nora the empathetic psychologist

Conference paper

One-step and Two-step Classification for Abusive Language Detection on Twitter

Conference paper

Perceived Emotional Intelligence in Virtual Agents

Conference paper

Towards a Corpus of Speech Emotion for Interactive Dialog Systems

Conference paper

Zara Returns: Improved Personality Induction and Adaptation by an Empathetic Virtual Agent

Conference paper

A Long Short-Term Memory Framework for Predicting Humor in Dialogues

Conference paper

A Machine Learning based Music Retrieval and Recommendation System

Conference paper

Deep Learning of Audio and Language Features for Humor Prediction

Conference paper

Predicting Humor Response in Dialogues from TV Sitcoms

Conference paper

Real-Time Speech Emotion and Sentiment Recognition for Interactive Dialogue Systems

Conference paper

Towards Empathetic Human-Robot Interactions

Conference paper

Towards Empathetic Human-Robot Interactions

Conference paper

Zara The Supergirl: An Empathetic Personality Recognition System

Conference paper

Zara: A Virtual Interactive Dialogue System Incorporating Emotion, Sentiment and Personality Recognition

Conference paper

Zara: An Empathetic Interactive Virtual Agent

Conference paper

Robots with heart

Article

A Comparison between a DNN and a CRF Disfluency Detection and Reconstruction System

Conference paper

HLTC-HKUST: A Neural Network Paraphrase Classifier using Translation Metrics, Semantic Roles and Lexical Similarity Features

Conference paper

Discriminatively Trained Sparse Inverse Covariance Matrices for Speech Recognition

Article

Efficient Sparse Banded Acoustic Models for Speech Recognition

Article

A Hindi-English Code-Switching Corpus

Conference paper

Acoustic modeling for hindi speech recognition in low-resource settings

Conference paper

Code switch language modeling with Functional Head Constraint

Conference paper

Co-Training for Classification of Live or Studio Music Recordings

Conference paper

Language Modeling with Functional Head Constraint for Code Switching Speech Recognition

Conference paper

Cross-Lingual Language Modeling for Low-Resource Speech Recognition

Article

Sparse Inverse Covariance Matrices for Low Resource Speech Recognition

Article

Discriminatively Trained Sparse Inverse Covariance Matrices for Low Resource Acoustic Modeling

Conference paper

Identification of Live or Studio Versions of a Song Via Supervised Learning

Conference paper

Improved Mixed Language Speech Recognition Using Asymmetric Acoustic Model and Language Model with Code-switch Inversion Constraints

Conference paper

Language Modeling for Mixed Language Speech Recognition Using Weighted Phrase Extraction

Conference paper

Multimodal Music Emotion Classification Using AdaBoost with Decision Stumps

Conference paper

These Words Are Music to My Ears: Recognizing Music Emotion from Lyrics using AdaBoost

Conference paper

Active learning with semi-automatic annotation for extractive speech summarization

Article

Automatic Parliamentary Meeting Minute Generation Using Rhetorical Structure Modeling

Article

A Mandarin-English Code-switching Corpus

Conference paper

A Multilingual Database of Natural Stress Emotion

Conference paper

Code Switching Language Model with Translation Constraint for Mixed Language Speech Recognition

Conference paper

Cross-Lingual language modeling with syntactic reordering for low-resource speech recognition

Conference paper

Low Resource Speech Recognition with Automatically Learned Sparse Inverse Covariance Matrices

Conference paper

Personalized music emotion classification via active learning

Conference paper

Phrase-level Transduction Model with Reordering for Spoken to Written Language Transformation

Conference paper

Sparse banded precision matrices for low resource speech recognition

Conference paper

Using English Acoustic Models for Hindi Automatic Speech Recognition

Conference paper

Using English Acoustic Models for Hindi Automatic Speech Recognition

Conference paper

A cross gender and cross lingual study on acoustic features for stress recognition in speech

Conference paper

Asymmetric acoustic modeling of mixed language speech

Conference paper

Automatic minute generation for parliamentary speech using conditional random fields

Conference paper

Mining Parallel Documents Using Low Bandwidth and High Precision CLIR from the Heterogeneous Web

Conference paper

Rare Word Translation Extraction from Aligned Comparable Documents

Conference paper

Extractive speech summarization using shallow rhetorical structure modeling

Article

Building and Mining Parallel Corpora

Book chapter

Chinese Machine Translation

Book chapter

A Very Large Scale Mandarin Chinese Broadcast Collection for the GALE Program

Conference paper

A Very Large Scale Mandarin Chinese Broadcast Corpus for GALE Project

Conference paper

Learning deep rhetorical structure for extractive speech summarization

Conference paper

Rhetorical syntax-driven model for speech summarization

Conference paper

Trillions of comparable documents

Conference paper

Unsupervised synthesis of multilingual wikipedia articles

Conference paper

BUCC 2009: 2nd Workshop on Building and Using Comparable Corpora: from Parallel to Non-parallel Corpora: Proceedings of the Workshop, 6 August 2009, Suntec, Singapore

Book

Active Learning of Extractive Reference Summaries for Lecture Speech Summarization

Conference paper

Can semantic role labeling improve SMT?

Conference paper

Extractive speech summarization by active learning

Conference paper

Rhetorical structure modeling for lecture speech summarization

Conference paper

Semantic Roles for SMT: A Hybrid Two-Pass Model

Conference paper

Multilingual spoken language processing

Article

Rhetorical-state hidden markov models for extractive speech summarization

Conference paper

RSHMM++ for extractive lecture speech summarization

Conference paper

Using output probability distribution for oov word rejection

Conference paper

A comparative study on speech summarization of broadcast news and lecture speech

Conference paper

A mandarin lecture speech transcription system for speech summarization

Conference paper

Improving lecture speech summarization using rhetorical information

Conference paper

Learning Bilingual Semantic Frames: Shallow Semantic Parsing vs. Semantic Role Projection

Conference paper

Aligning word senses using bilingual corpora

Article

One Story One Flow: Hidden Markov Story Models for Multilingual and Multi-document Summarization

Article

Automatic learning of Chinese English semantic structure mapping

Conference paper

HKUST/MTS: A very large scale Mandarin telephone speech corpus

Conference paper

Multi-accent Chinese speech recognition

Conference paper

Robust Word Sense Translation by EM Learning of Frame Semantics

Conference paper

Effects and modeling of phonetic and acoustic confusions in accented speech

Article

Translation disambiguation in mixed language queries

Article

Acoustic and phonetic confusions in accented speech recognition

Conference paper

EARSCTS: A Chinese Telephony Conversational Corpus for Speech Processing

Conference paper

Inversion transduction grammar constraints for mining parallel sentences from quasi-comparable corpora

Conference paper

A maximum-entropy Chinese parser augmented by transformation-based learning

Article

Pronunciation Modeling for Spontaneous Mandarin Speech Recognition

Article

State-dependent phonetic tied mixtures with pronunciation modeling for spontaneous speech recognition

Article

Unsupervised Learning of a Chinese Spontaneous and Colloquial Speech Lexicon with Content and Filler Phrase Classification

Article

A Grammar-Based Chinese to English Speech Translation System for Portable Devices

Conference paper

A system for mandarin short phrase recognition on portable devices

Conference paper

A system for Mandarin short phrase recognition on portable devices

Conference paper

Automatic Construction of an English-Chinese Bilingual FrameNet

Conference paper

BiFrameNet: bilingual Frame Semantics Resource Construction by Cross-lingual Induction

Conference paper

Development of a Chinese telephony conversational corpus for speech processing

Conference paper

From Parallel Corpora to Non-Parallel Corpora, Methods for Bilingual Sentence Extraction

Conference paper

Mining Very-Non-Parallel Corpora: Parallel Sentence and Lexicon Extraction via Bootstrapping and EM

Conference paper

Multi-level Bootstrapping for Extracting Parallel Sentences from a Quasi-comparable Corpora

Conference paper

Sentence Alignment in Paralllel, Comparable and Quasi-comparable Corpora

Conference paper

Using N-best Lists for Named Entity Recognition from Chinese Speech

Conference paper

Modeling partial pronunciation variations for spontaneous Mandarin speech recognition

Article

Automatic phone set extension with confidence measure for spontaneous speech

Conference paper

Flooring the observation probability for robust ASR in impulsive noise

Conference paper

Partial change accent models for accented mandarin speech recognition

Conference paper

Triphone Model Reconstruction for Mandarin Variations

Conference paper

Mandarin pronunciation modeling based on CASS corpus

Article

A Maximum-Entropy Approach to HowNet-based Chinese Word-Sense Disambiguation

Conference paper

Creating a Bilingual Ontology: A Corpus-Based Approach for Aligning WordNet and HowNet

Conference paper

Identifying Concepts Across Languages: A First Step towards a Corpus-based Approach to Automatic Ontology Alignment

Conference paper

Model Partial Pronunciation Variations for Spontaneous Mandarin Speech Recognition

Conference paper

Modeling Partial Pronunciation Variations for Spontaneous Mandarin Speech Recognition

Conference paper

Nouns in WordNet and HowNet: an Analysis and Comparison of Semantic Relations

Conference paper

Partial Change Phone Models for Pronunciation Variations in Spontaneous Mandarin Speech

Conference paper

Reducing pronunciation lexicon confusion and using more data without phonetic transcription for pronunciation modeling

Conference paper

Automatic Generation of Pronunciation Lexicons for Mandarin Spontaneous Speech

Conference paper

CLEF 2001 bilingual task simple dictionary-based query translation

Conference paper

Estimating Pronunciation Variations from Acoustic Likelihood Score for HMM Reconstruction

Conference paper

Modeling Pronunciation Variation Using Context-Dependent Weighting and B/S Refined Acoustic Modeling

Conference paper

Log-add approximation on-line noise compensation method adopting robust decision rules for robust digits recognition

Article

A multi-path syllable to word decoder with language model optimization and automatic lexicon augmentation

Conference paper

A Novel Technique for Frame Selection for GMM-based text-independent Speaker Recognition

Conference paper

A Phonetically Transcribed Corpus of Mandarin Spontaneous Speech

Conference paper

An LLR-based technique of frame selection for GMM-based text-independent speaker identification

Conference paper

MLLR-based accent model adaptation without accented data

Conference paper

Principal mixture speaker adaptation for improved continuous speech recognition

Conference paper

Residual noise compensation for robust speech recognition in nonstationary noise

Conference paper

Rule-Based Word Pronunciation Networks Generation for Mandarin Speech Recognition

Conference paper

SALSA Version 3.0: A Single Recognizer-based Multilingual Speech-based Web Browser

Conference paper

Fast accent identification and accented speech recognition

Article

More efficient and optimal LLR for decoding and verification

Article

Statistical Augmentation of a Chinese Machine-Readable Dictionary

Book chapter

A Monolingual Semantic Decoder Based on Word Sense Disambiguation for Mixed Language

Conference paper

A Monolingual Semantic Decoder based on Word Sense Disambiguation for Mixed Language Query Processing

Conference paper

Decision Tree-Based Triphones are Robust and Practical for Mandarin Speech Recognition

Conference paper

keyword / Fillerword Modeling for Spontaneous Spoken Mixed Language Query Processing

Conference paper

Liftered forward masking procedure for robust digits recognition

Conference paper

MAP-based Cross-Language Adaptation Augmented by Linguistic Knowledge: from English to Chinese

Conference paper

Mixed-language Query Disambiguation

Conference paper

A Statistical View on Bilingual Lexicon Extraction: From Parallel Corpora to Non-Parallel Corpora

Article

Extracting Key Terms from Chinese and Japanese texts

Article

An IR Approach for Translating New Words from Nonparallel, Comparable Texts

Conference paper

Are Initial/Final Units Acoustically Accurate?

Conference paper

SALSA version 1.0, A Speech-Based Web Browser

Conference paper

SALSA, A Multilingual Speech-Based Web Browser

Conference paper

Translating Unknown Words Using Nonparallel, Comparable Texts

Conference paper

Understanding Chinese Spontaneous Speech? Are Mandarin and Cantonese Very Different?

Conference paper

Using English Phoneme Models for Chinese Speech Recognition

Conference paper

Dealing with Multilinguality in a Spoken Language Query Translator

Conference paper

Extracting Japanese Domain and Technical Terms is Relatively Easy

Conference paper

Finding Terminology Translations from Non-parallel Corpora

Conference paper

A Technical Word and Term Translation Aid using Noisy Parallel Corpora Across Language Groups

Article

Domain Word Translation by Space-Frequency Analysis of Context Length Histograms

Conference paper

A Pattern Matching Method for Finding Noun and Proper Noun Translations from Noisy Parallel Corpora

Conference paper

Coerced Markov Models for Cross-lingual Lexical-Tag Relations

Conference paper

Compiling Bilingual Lexicon Entries from a Non-Parallel English-Chinese Corpus

Conference paper

Aligning Noisy Parallel Corpora across Language Groups: Word Pair Feature Matching by Dynamic Time Warping

Conference paper

Improving Chinese tokenization with linguistic Filters on statistical lexical acquisition

Conference paper

K-vec: A New Approach for Aligning Parallel Texts

Conference paper

Statistical Augmentation of a Chinese Machine-Readable Dictionary

Conference paper

Aligning Parallel Texts: Do Methods Developed for English-French generalize to Asian Languages?

Conference paper

The BBN/HARC Spoken Language system

Conference paper

The Estimation of Powerful Language Models from Small and Large Corpora

Conference paper

Design and Performance of HARC, the BBN Spoken Language Understanding System

Conference paper

Improved Speaker Markov Modeling for Unsupervised Speaker Normalization

Article

Unsupervised Speaker Normalization by Speaker Markov Model Converter for Speaker-Independent Speech Recognition

Conference paper