Search Results for author: Tiejun Zhao

Found 88 papers, 20 papers with code

Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data

no code implementations17 Dec 2013 Yalong Bai, Kuiyuan Yang, Wei Yu, Wei-Ying Ma, Tiejun Zhao

Image retrieval refers to finding relevant images from an image database for a query, which is considered difficult for the gap between low-level representation of images and high-level representation of queries.

Image Retrieval Retrieval

Augmenting Phrase Table by Employing Lexicons for Pivot-based SMT

no code implementations1 Dec 2015 Yiming Cui, Conghui Zhu, Xiaoning Zhu, Tiejun Zhao

Pivot language is employed as a way to solve the data sparseness problem in machine translation, especially when the data for a particular language pair does not exist.

Machine Translation Translation

Building A Case-based Semantic English-Chinese Parallel Treebank

no code implementations LREC 2016 Huaxing Shi, Tiejun Zhao, Keh-Yih Su

This Treebank is a part of a semantic corpus building project, which aims to build a semantic bilingual corpus annotated with syntactic, semantic cases and word senses.

Machine Translation POS +2

Constraint-Based Question Answering with Knowledge Graph

1 code implementation COLING 2016 Junwei Bao, Nan Duan, Zhao Yan, Ming Zhou, Tiejun Zhao

WebQuestions and SimpleQuestions are two benchmark data-sets commonly used in recent knowledge-based question answering (KBQA) work.

Question Answering

Automatic Dataset Augmentation

no code implementations28 Aug 2017 Yalong Bai, Kuiyuan Yang, Tao Mei, Wei-Ying Ma, Tiejun Zhao

Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years.

Object Recognition

Context-Aware Smoothing for Neural Machine Translation

no code implementations IJCNLP 2017 Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao

In Neural Machine Translation (NMT), each word is represented as a low-dimension, real-value vector for encoding its syntax and semantic information.

Machine Translation NMT +3

Syntax-Directed Attention for Neural Machine Translation

no code implementations12 Nov 2017 Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao

In this paper, we extend local attention with syntax-distance constraint, to focus on syntactically related source words with the predicted target word, thus learning a more effective context vector for word prediction.

Machine Translation NMT +1

Table-to-Text: Describing Table Region with Natural Language

no code implementations29 May 2018 Junwei Bao, Duyu Tang, Nan Duan, Zhao Yan, Yuanhua Lv, Ming Zhou, Tiejun Zhao

The model maps a row from a table to a continuous vector and then generates a natural language sentence by leveraging the semantics of a table.

Language Modelling Sentence

Forest-Based Neural Machine Translation

no code implementations ACL 2018 Chunpeng Ma, Akihiro Tamura, Masao Utiyama, Tiejun Zhao, Eiichiro Sumita

Tree-based neural machine translation (NMT) approaches, although achieved impressive performance, suffer from a major drawback: they only use the 1-best parse tree to direct the translation, which potentially introduces translation mistakes due to parsing errors.

Machine Translation NMT +1

Deep Attention Neural Tensor Network for Visual Question Answering

no code implementations ECCV 2018 Yalong Bai, Jianlong Fu, Tiejun Zhao, Tao Mei

First, we model one of the pairwise interaction (e. g., image and question) by bilinear features, which is further encoded with the third dimension (e. g., answer) to be a triplet by bilinear tensor product.

Deep Attention Question Answering +1

Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets

2 code implementations ACL 2019 Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Shiyu Chang, Mo Yu, Conghui Zhu, Tiejun Zhao

Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process.

Selection bias Sentence

Sentence-Level Agreement for Neural Machine Translation

no code implementations ACL 2019 Mingming Yang, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Min Zhang, Tiejun Zhao

The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references.

Machine Translation NMT +2

Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation

no code implementations ACL 2019 Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao

In previous methods, UBWE is first trained using non-parallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT.

Denoising Machine Translation +1

Revisiting Simple Domain Adaptation Methods in Unsupervised Neural Machine Translation

no code implementations26 Aug 2019 Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao, Chenhui Chu

However, it has not been well-studied for unsupervised neural machine translation (UNMT), although UNMT has recently achieved remarkable results in several domain-specific language pairs.

Domain Adaptation Machine Translation +1

Duality Regularization for Unsupervised Bilingual Lexicon Induction

no code implementations3 Sep 2019 Xuefeng Bai, Yue Zhang, Hailong Cao, Tiejun Zhao

Unsupervised bilingual lexicon induction naturally exhibits duality, which results from symmetry in back-translation.

Bilingual Lexicon Induction Translation

Multimodal Matching Transformer for Live Commenting

no code implementations7 Feb 2020 Chaoqun Duan, Lei Cui, Shuming Ma, Furu Wei, Conghui Zhu, Tiejun Zhao

In this work, we aim to improve the relevance between live comments and videos by modeling the cross-modal interactions among different modalities.

Text Generation

Modeling Future Cost for Neural Machine Translation

no code implementations28 Feb 2020 Chaoqun Duan, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Conghui Zhu, Tiejun Zhao

Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the references as consistent as possible.

Machine Translation NMT +1

Look-into-Object: Self-supervised Structure Modeling for Object Recognition

2 code implementations CVPR 2020 Mohan Zhou, Yalong Bai, Wei zhang, Tiejun Zhao, Tao Mei

Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category.

Fine-Grained Image Classification Image Recognition +7

Understanding Learning Dynamics for Neural Machine Translation

no code implementations5 Apr 2020 Conghui Zhu, Guanlin Li, Lemao Liu, Tiejun Zhao, Shuming Shi

Despite the great success of NMT, there still remains a severe challenge: it is hard to interpret the internal dynamics during its training process.

Machine Translation NMT +1

Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios

no code implementations NAACL 2021 Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao

Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks.

Machine Translation Translation

Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting

1 code implementation ACL 2020 Guanhua Zhang, Bing Bai, Junqi Zhang, Kun Bai, Conghui Zhu, Tiejun Zhao

In this paper, we formalize the unintended biases in text classification datasets as a kind of selection bias from the non-discrimination distribution to the discrimination distribution.

Abusive Language General Classification +3

End-to-End Speech Translation with Adversarial Training

no code implementations WS 2020 Xuancai Li, Chen Kehai, Tiejun Zhao, Muyun Yang

End-to-End speech translation usually leverages audio-to-text parallel data to train an available speech translation model which has shown impressive results on various speech translation tasks.

Translation

Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark

no code implementations15 Oct 2020 Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Conghui Zhu, Tiejun Zhao

Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts.

Natural Language Inference

Cross Copy Network for Dialogue Generation

1 code implementation EMNLP 2020 Changzhen Ji, Xin Zhou, Yating Zhang, Xiaozhong Liu, Changlong Sun, Conghui Zhu, Tiejun Zhao

In the past few years, audiences from different fields witness the achievements of sequence-to-sequence models (e. g., LSTM+attention, Pointer Generator Networks, and Transformer) to enhance dialogue content generation.

Dialogue Generation

AI-lead Court Debate Case Investigation

no code implementations22 Oct 2020 Changzhen Ji, Xin Zhou, Conghui Zhu, Tiejun Zhao

The multi-role judicial debate composed of the plaintiff, defendant, and judge is an important part of the judicial trial.

Question Generation Question-Generation +1

Robust Machine Reading Comprehension by Learning Soft labels

no code implementations COLING 2020 Zhenyu Zhao, Shuangzhi Wu, Muyun Yang, Kehai Chen, Tiejun Zhao

Neural models have achieved great success on the task of machine reading comprehension (MRC), which are typically trained on hard labels.

Machine Reading Comprehension

Document-Level Relation Extraction with Reconstruction

1 code implementation21 Dec 2020 Wang Xu, Kehai Chen, Tiejun Zhao

In document-level relation extraction (DocRE), graph structure is generally used to encode relation information in the input document to classify the relation category between each entity pair, and has greatly advanced the DocRE task over the past several years.

Document-level Relation Extraction Relation +1

Discriminative Reasoning for Document-level Relation Extraction

2 code implementations Findings (ACL) 2021 Wang Xu, Kehai Chen, Tiejun Zhao

Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i. e., pattern recognition, logical reasoning, coreference reasoning, etc.)

Document-level Relation Extraction Logical Reasoning +1

Issues with Entailment-based Zero-shot Text Classification

1 code implementation ACL 2021 Tingting Ma, Jin-Ge Yao, Chin-Yew Lin, Tiejun Zhao

The general format of natural language inference (NLI) makes it tempting to be used for zero-shot text classification by casting any target label into a sentence of hypothesis and verifying whether or not it could be entailed by the input, aiming at generic classification applicable on any specified label space.

Natural Language Inference Sentence +3

A Neural Conversation Generation Model via Equivalent Shared Memory Investigation

1 code implementation20 Aug 2021 Changzhen Ji, Yating Zhang, Xiaozhong Liu, Adam Jatowt, Changlong Sun, Conghui Zhu, Tiejun Zhao

Nevertheless, few works utilized the knowledge extracted from similar conversations for utterance generation.

Text Generation

Responsive Listening Head Generation: A Benchmark Dataset and Baseline

no code implementations27 Dec 2021 Mohan Zhou, Yalong Bai, Wei zhang, Ting Yao, Tiejun Zhao, Tao Mei

Automatically synthesizing listening behavior that actively responds to a talking head, is critical to applications such as digital human, virtual agents and social robots.

Talking Head Generation Translation

OPERA:Operation-Pivoted Discrete Reasoning over Text

no code implementations29 Apr 2022 Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao

To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability.

Machine Reading Comprehension Semantic Parsing

UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation

1 code implementation15 Oct 2022 Yongwei Zhou, Junwei Bao, Chaoqun Duan, Youzheng Wu, Xiaodong He, Tiejun Zhao

Question answering requiring discrete reasoning, e. g., arithmetic computing, comparison, and counting, over knowledge is a challenging task.

Question Answering Semantic Parsing

MuGER$^2$: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering

1 code implementation19 Oct 2022 Yingyao Wang, Junwei Bao, Chaoqun Duan, Youzheng Wu, Xiaodong He, Tiejun Zhao

To preserve the advantage and eliminate the disadvantage of different granularity evidence, we propose MuGER$^2$, a Multi-Granularity Evidence Retrieval and Reasoning approach.

Navigate Question Answering +1

Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers

no code implementations20 Oct 2022 Wanjun Zhong, Tingting Ma, Jiahai Wang, Jian Yin, Tiejun Zhao, Chin-Yew Lin, Nan Duan

This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making.

Decision Making

CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition

1 code implementation24 May 2023 Tingting Ma, Qianhui Wu, Huiqiang Jiang, Börje F. Karlsson, Tiejun Zhao, Chin-Yew Lin

Cross-lingual named entity recognition (NER) aims to train an NER system that generalizes well to a target language by leveraging labeled data in a given source language.

Denoising Knowledge Distillation +3

Visual-Aware Text-to-Speech

no code implementations21 Jun 2023 Mohan Zhou, Yalong Bai, Wei zhang, Ting Yao, Tiejun Zhao, Tao Mei

Dynamically synthesizing talking speech that actively responds to a listening head is critical during the face-to-face interaction.

Speech Synthesis

Interactive Conversational Head Generation

no code implementations5 Jul 2023 Mohan Zhou, Yalong Bai, Wei zhang, Ting Yao, Tiejun Zhao

Based on ViCo and ViCo-X, we define three novel tasks targeting the interaction modeling during the face-to-face conversation: 1) responsive listening head generation making listeners respond actively to the speaker with non-verbal signals, 2) expressive talking head generation guiding speakers to be aware of listeners' behaviors, and 3) conversational head generation to integrate the talking/listening ability in one interlocutor.

Sentence Talking Head Generation

Learning and Evaluating Human Preferences for Conversational Head Generation

no code implementations20 Jul 2023 Mohan Zhou, Yalong Bai, Wei zhang, Ting Yao, Tiejun Zhao, Tao Mei

In this paper, we propose a novel learning-based evaluation metric named Preference Score (PS) for fitting human preference according to the quantitative evaluations across different dimensions.

HopPG: Self-Iterative Program Generation for Multi-Hop Question Answering over Heterogeneous Knowledge

no code implementations22 Aug 2023 Yingyao Wang, Yongwei Zhou, Chaoqun Duan, Junwei Bao, Tiejun Zhao

To alleviate these challenges, we propose a self-iterative framework for multi-hop program generation (HopPG) over heterogeneous knowledge, which leverages the previous execution results to retrieve supporting facts and generate subsequent programs hop by hop.

Multi-hop Question Answering Question Answering +1

Spot the Error: Non-autoregressive Graphic Layout Generation with Wireframe Locator

1 code implementation29 Jan 2024 Jieru Lin, Danqing Huang, Tiejun Zhao, Dechen Zhan, Chin-Yew Lin

Furthermore, based on our observation that pixel space is more sensitive in capturing spatial patterns of graphic layouts (e. g., overlap, alignment), we propose a learning-based locator to detect erroneous tokens which takes the wireframe image rendered from the generated layout sequence as input.

Attribute

LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation

no code implementations12 Feb 2024 Hongyun Zhou, Xiangyu Lu, Wang Xu, Conghui Zhu, Tiejun Zhao

Low-Rank Adaptation (LoRA) introduces auxiliary parameters for each layer to fine-tune the pre-trained model under limited computing resources.

Self-Evaluation of Large Language Model based on Glass-box Features

no code implementations7 Mar 2024 Hui Huang, Yingqi Qu, Jing Liu, Muyun Yang, Tiejun Zhao

The proliferation of open-source Large Language Models (LLMs) underscores the pressing need for evaluation methods.

Language Modelling Large Language Model

Dual Instruction Tuning with Large Language Models for Mathematical Reasoning

no code implementations27 Mar 2024 Yongwei Zhou, Tiejun Zhao

To alleviate this problem, we propose a dual instruction tuning strategy to meticulously model mathematical reasoning from both forward and reverse directions.

Domain Generalization Mathematical Reasoning

CAN-GRU: a Hierarchical Model for Emotion Recognition in Dialogue

no code implementations CCL 2020 Ting Jiang, Bing Xu, Tiejun Zhao, Sheng Li

In the first layer, in order to extract textual features of utterances, we propose a convolutional self-attention network(CAN).

Emotion Recognition Opinion Mining

Cross-lingual Feature Extraction from Monolingual Corpora for Low-resource Unsupervised Bilingual Lexicon Induction

no code implementations COLING 2022 Zihao Feng, Hailong Cao, Tiejun Zhao, Weixuan Wang, Wei Peng

Despite their progress in high-resource language settings, unsupervised bilingual lexicon induction (UBLI) models often fail on corpora with low-resource distant language pairs due to insufficient initialization.

Bilingual Lexicon Induction Word Embeddings

On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning

1 code implementation NAACL 2022 Tingting Ma, Qianhui Wu, Zhiwei Yu, Tiejun Zhao, Chin-Yew Lin

Recent studies on few-shot intent detection have attempted to formulate the task as a meta-learning problem, where a meta-learning model is trained with a certain capability to quickly adapt to newly specified few-shot tasks with potentially unseen intent categories.

Intent Detection Meta-Learning +5

OPERA: Operation-Pivoted Discrete Reasoning over Text

1 code implementation NAACL 2022 Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao

To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability.

Machine Reading Comprehension Semantic Parsing

基于实体信息增强及多粒度融合的多文档摘要(Multi-Document Summarization Based on Entity Information Enhancement and Multi-Granularity Fusion)

no code implementations CCL 2022 Jiarui Tang, Liu Meiling, Tiejun Zhao, Jiyun Zhou

“神经网络模型的快速发展使得多文档摘要可以获得人类可读的流畅的摘要, 对大规模的数据进行预训练可以更好的从自然语言文本中捕捉更丰富的语义信息, 并更好的作用于下游任务。目前很多的多文档摘要的工作也应用了预训练模型(如BERT)并取得了一定的效果, 但是这些预训练模型不能更好的从文本中捕获事实性知识, 没有考虑到多文档文本的结构化的实体-关系信息, 本文提出了基于实体信息增强和多粒度融合的多文档摘要模型MGNIE, 将实体关系信息融入预训练模型ERNIE中, 增强知识事实以获得多层语义信息, 解决摘要生成的事实一致性问题。进而从多种粒度进行多文档层次结构的融合建模, 以词信息、实体信息以及句子信息捕捉长文本信息摘要生成所需的关键信息点。本文设计的模型, 在国际标准评测数据集MultiNews上对比强基线模型效果和竞争力获得较大提升。”

Document Summarization Multi-Document Summarization

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