Search Results for author: He-Yan Huang

Found 40 papers, 11 papers with code

Which Kind Is Better in Open-domain Multi-turn Dialog,Hierarchical or Non-hierarchical Models? An Empirical Study

no code implementations7 Aug 2020 Tian Lan, Xian-Ling Mao, Wei Wei, He-Yan Huang

Thus, in this paper, we will measure systematically nearly all representative hierarchical and non-hierarchical models over the same experimental settings to check which kind is better.

InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training

4 code implementations NAACL 2021 Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian-Ling Mao, He-Yan Huang, Ming Zhou

In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts.

Contrastive Learning Cross-Lingual Transfer +2

Generating Informative Dialogue Responses with Keywords-Guided Networks

no code implementations3 Jul 2020 Heng-Da Xu, Xian-Ling Mao, Zewen Chi, Jing-Jing Zhu, Fanshu Sun, He-Yan Huang

Specifically, KW-Seq2Seq first uses a keywords decoder to predict some topic keywords, and then generates the final response under the guidance of them.

Weibo-COV: A Large-Scale COVID-19 Social Media Dataset from Weibo

1 code implementation EMNLP (NLP-COVID19) 2020 Yong Hu, He-Yan Huang, Anfan Chen, Xian-Ling Mao

Therefore, in this paper, we release Weibo-COV, a first large-scale COVID-19 social media dataset from Weibo, covering more than 30 million tweets from 1 November 2019 to 30 April 2020.

Social and Information Networks

PONE: A Novel Automatic Evaluation Metric for Open-Domain Generative Dialogue Systems

1 code implementation6 Apr 2020 Tian Lan, Xian-Ling Mao, Wei Wei, Xiaoyan Gao, He-Yan Huang

Through extensive experiments, the learning-based metrics are demonstrated that they are the most effective evaluation metrics for open-domain generative dialogue systems.

Dialogue Evaluation

Evaluating Low-Resource Machine Translation between Chinese and Vietnamese with Back-Translation

no code implementations4 Mar 2020 Hongzheng Li, He-Yan Huang

Back translation (BT) has been widely used and become one of standard techniques for data augmentation in Neural Machine Translation (NMT), BT has proven to be helpful for improving the performance of translation effectively, especially for low-resource scenarios.

Data Augmentation Machine Translation +2

When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation

no code implementations20 Dec 2019 Tian Lan, Xian-Ling Mao, He-Yan Huang, Wei Wei

Intuitively, a dialogue model that can control the timing of talking autonomously based on the conversation context can chat with humans more naturally.

Dialogue Generation

Tag Recommendation by Word-Level Tag Sequence Modeling

no code implementations30 Nov 2019 Xuewen Shi, He-Yan Huang, Shuyang Zhao, Ping Jian, Yi-Kun Tang

In this paper, we transform tag recommendation into a word-based text generation problem and introduce a sequence-to-sequence model.

General Classification TAG +3

Neural Chinese Word Segmentation as Sequence to Sequence Translation

1 code implementation29 Nov 2019 Xuewen Shi, He-Yan Huang, Ping Jian, Yuhang Guo, Xiaochi Wei, Yi-Kun Tang

In this paper, we cast the CWS as a sequence translation problem and propose a novel sequence-to-sequence CWS model with an attention-based encoder-decoder framework.

Chinese Word Segmentation Spelling Correction +1

SEPT: Improving Scientific Named Entity Recognition with Span Representation

no code implementations8 Nov 2019 Tan Yan, He-Yan Huang, Xian-Ling Mao

We introduce a new scientific named entity recognizer called SEPT, which stands for Span Extractor with Pre-trained Transformers.

named-entity-recognition Named Entity Recognition +1

Improving Neural Machine Translation by Achieving Knowledge Transfer with Sentence Alignment Learning

no code implementations CONLL 2019 Xuewen Shi, He-Yan Huang, Wenguan Wang, Ping Jian, Yi-Kun Tang

To alleviate this problem, we propose an NMT approach that heightens the adequacy in machine translation by transferring the semantic knowledge learned from bilingual sentence alignment.

Machine Translation NMT +5

Cross-Lingual Natural Language Generation via Pre-Training

1 code implementation23 Sep 2019 Zewen Chi, Li Dong, Furu Wei, Wenhui Wang, Xian-Ling Mao, He-Yan Huang

In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages.

Abstractive Text Summarization Machine Translation +5

Generative Dialog Policy for Task-oriented Dialog Systems

no code implementations17 Sep 2019 Tian Lan, Xian-Ling Mao, He-Yan Huang

As far as we know, the existing task-oriented dialogue systems obtain the dialogue policy through classification, which can assign either a dialogue act and its corresponding parameters or multiple dialogue acts without their corresponding parameters for a dialogue action.

General Classification Task-Oriented Dialogue Systems

Multi-task Learning for Low-resource Second Language Acquisition Modeling

1 code implementation25 Aug 2019 Yong Hu, He-Yan Huang, Tian Lan, Xiaochi Wei, Yuxiang Nie, Jiarui Qi, Liner Yang, Xian-Ling Mao

Second language acquisition (SLA) modeling is to predict whether second language learners could correctly answer the questions according to what they have learned.

Language Acquisition Multi-Task Learning

Complicated Table Structure Recognition

1 code implementation13 Aug 2019 Zewen Chi, He-Yan Huang, Heng-Da Xu, Houjin Yu, Wanxuan Yin, Xian-Ling Mao

It also attracts lots of attention to recognize the table structures in PDF files.

Deep Hashing for Signed Social Network Embedding

no code implementations12 Aug 2019 Jia-Nan Guo, Xian-Ling Mao, Xiao-Jian Jiang, Ying-Xiang Sun, Wei Wei, He-Yan Huang

Network embedding is a promising way of network representation, facilitating many signed social network processing and analysis tasks such as link prediction and node classification.

Deep Hashing Link Prediction +2

Deep Cross-Modal Hashing with Hashing Functions and Unified Hash Codes Jointly Learning

no code implementations29 Jul 2019 Rong-Cheng Tu, Xian-Ling Mao, Bing Ma, Yong Hu, Tan Yan, Wei Wei, He-Yan Huang

Specifically, by an iterative optimization algorithm, DCHUC jointly learns unified hash codes for image-text pairs in a database and a pair of hash functions for unseen query image-text pairs.

Retrieval

Open Domain Event Extraction Using Neural Latent Variable Models

1 code implementation ACL 2019 Xiao Liu, He-Yan Huang, Yue Zhang

We consider open domain event extraction, the task of extracting unconstraint types of events from news clusters.

Event Extraction

Earlier Attention? Aspect-Aware LSTM for Aspect-Based Sentiment Analysis

no code implementations19 May 2019 Bowen Xing, Lejian Liao, Dandan song, Jingang Wang, Fuzheng Zhang, Zhongyuan Wang, He-Yan Huang

This paper proposes a novel variant of LSTM, termed as aspect-aware LSTM (AA-LSTM), which incorporates aspect information into LSTM cells in the context modeling stage before the attention mechanism.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)

Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding

no code implementations22 Dec 2018 Changsen Yuan, He-Yan Huang, Chong Feng, Xiao Liu, Xiaochi Wei

Distant supervision for relation extraction is an efficient method to reduce labor costs and has been widely used to seek novel relational facts in large corpora, which can be identified as a multi-instance multi-label problem.

Relation Relation Extraction +2

Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction

no code implementations EMNLP 2018 Ge Shi, Chong Feng, Lifu Huang, Boliang Zhang, Heng Ji, Lejian Liao, He-Yan Huang

Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions.

Feature Engineering Relation +2

Zewen at SemEval-2018 Task 1: An Ensemble Model for Affect Prediction in Tweets

no code implementations SEMEVAL 2018 Zewen Chi, He-Yan Huang, Jiangui Chen, Hao Wu, Ran Wei

This paper presents a method for Affect in Tweets, which is the task to automatically determine the intensity of emotions and intensity of sentiment of tweets.

Sentence Classification Sentiment Analysis

Supervised Deep Hashing for Hierarchical Labeled Data

no code implementations7 Apr 2017 Dan Wang, He-Yan Huang, Chi Lu, Bo-Si Feng, Liqiang Nie, Guihua Wen, Xian-Ling Mao

Specifically, we define a novel similarity formula for hierarchical labeled data by weighting each layer, and design a deep convolutional neural network to obtain a hash code for each data point.

Deep Hashing Image Retrieval

Conceptualization Topic Modeling

no code implementations7 Apr 2017 Yi-Kun Tang, Xian-Ling Mao, He-Yan Huang, Guihua Wen

Recently, topic modeling has been widely used to discover the abstract topics in text corpora.

Topic Models

Guided Filter based Edge-preserving Image Non-blind Deconvolution

no code implementations7 Sep 2016 Hang Yang, Ming Zhu, Zhongbo Zhang, He-Yan Huang

In the denoising step, the guided filter is used with the two obtained images for efficient edge-preserving filtering.

Deblurring Denoising +1

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