Search Results for author: Xiaojie Wang

Found 38 papers, 16 papers with code

Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction

1 code implementation ACL 2022 Hao Chen, Zepeng Zhai, Fangxiang Feng, Ruifan Li, Xiaojie Wang

Specifically, we first define ten types of relations for ASTE task, and then adopt a biaffine attention module to embed these relations as an adjacent tensor between words in a sentence.

Aspect Sentiment Triplet Extraction

Learn to Adapt for Generalized Zero-Shot Text Classification

1 code implementation ACL 2022 Yiwen Zhang, Caixia Yuan, Xiaojie Wang, Ziwei Bai, Yongbin Liu

Generalized zero-shot text classification aims to classify textual instances from both previously seen classes and incrementally emerging unseen classes.

Classification Generalized Zero-Shot Learning +2

Grouped-Attention for Content-Selection and Content-Plan Generation

no code implementations Findings (EMNLP) 2021 Bayu Distiawan Trisedya, Xiaojie Wang, Jianzhong Qi, Rui Zhang, Qingjun Cui

A key component of the GSC-attention is grouped-attention, which is token-level attention constrained within each input attribute that enables our proposed model captures both local and global context.

Data-to-Text Generation

Task-Oriented Clustering for Dialogues

1 code implementation Findings (EMNLP) 2021 Chenxu Lv, Hengtong Lu, Shuyu Lei, Huixing Jiang, Wei Wu, Caixia Yuan, Xiaojie Wang

A reliable clustering algorithm for task-oriented dialogues can help developer analysis and define dialogue tasks efficiently.

Representation Learning Text Clustering

GR-GAN: Gradual Refinement Text-to-image Generation

no code implementations23 May 2022 Bo Yang, Fangxiang Feng, Xiaojie Wang

We also introduce a new metric Cross-Model Distance (CMD) for simultaneously evaluating image quality and image-text consistency.

Text Matching Text to image generation +1

Question-Driven Graph Fusion Network For Visual Question Answering

no code implementations3 Apr 2022 Yuxi Qian, Yuncong Hu, Ruonan Wang, Fangxiang Feng, Xiaojie Wang

It first models semantic, spatial, and implicit visual relations in images by three graph attention networks, then question information is utilized to guide the aggregation process of the three graphs, further, our QD-GFN adopts an object filtering mechanism to remove question-irrelevant objects contained in the image.

Graph Attention Object Detection +3

Co-VQA : Answering by Interactive Sub Question Sequence

no code implementations Findings (ACL) 2022 Ruonan Wang, Yuxi Qian, Fangxiang Feng, Xiaojie Wang, Huixing Jiang

Most existing approaches to Visual Question Answering (VQA) answer questions directly, however, people usually decompose a complex question into a sequence of simple sub questions and finally obtain the answer to the original question after answering the sub question sequence(SQS).

Question Answering Visual Question Answering +2

A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots

1 code implementation Findings (ACL) 2022 Sai Zhang, Yuwei Hu, Yuchuan Wu, Jiaman Wu, Yongbin Li, Jian Sun, Caixia Yuan, Xiaojie Wang

We find some new linguistic phenomena and interactive manners in SSTOD which raise critical challenges of building dialog agents for the task.

 Ranked #1 on SSTOD on SSD_NAME


Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene

no code implementations16 Mar 2022 Duo Zheng, Fandong Meng, Qingyi Si, Hairun Fan, Zipeng Xu, Jie zhou, Fangxiang Feng, Xiaojie Wang

Visual dialog has witnessed great progress after introducing various vision-oriented goals into the conversation, especially such as GuessWhich and GuessWhat, where the only image is visible by either and both of the questioner and the answerer, respectively.

Visual Dialog

Deep Keyphrase Completion

no code implementations29 Oct 2021 Yu Zhao, Jia Song, Huali Feng, Fuzhen Zhuang, Qing Li, Xiaojie Wang, Ji Liu

Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval.

Keyphrase Extraction Keyphrase Generation

Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization

1 code implementation Findings (EMNLP) 2021 Junpeng Liu, Yanyan Zou, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Caixia Yuan, Xiaojie Wang

To capture the various topic information of a conversation and outline salient facts for the captured topics, this work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task.

Abstractive Dialogue Summarization Contrastive Learning +3

Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser

1 code implementation Findings (EMNLP) 2021 Duo Zheng, Zipeng Xu, Fandong Meng, Xiaojie Wang, Jiaan Wang, Jie zhou

To enhance VD Questioner: 1) we propose a Related entity enhanced Questioner (ReeQ) that generates questions under the guidance of related entities and learns entity-based questioning strategy from human dialogs; 2) we propose an Augmented Guesser (AugG) that is strong and is optimized for the VD setting especially.

Visual Dialog

Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis

1 code implementation ACL 2021 Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang, Eduard Hovy

To overcome these challenges, in this paper, we propose a dual graph convolutional networks (DualGCN) model that considers the complementarity of syntax structures and semantic correlations simultaneously.

Aspect-Based Sentiment Analysis Dependency Parsing

Multi-stage Pre-training over Simplified Multimodal Pre-training Models

1 code implementation ACL 2021 Tongtong Liu, Fangxiang Feng, Xiaojie Wang

Experimental results show that our method achieves comparable performance to the original LXMERT model in all downstream tasks, and even outperforms the original model in Image-Text Retrieval task.

Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue

1 code implementation12 Jul 2021 Zipeng Xu, Fandong Meng, Xiaojie Wang, Duo Zheng, Chenxu Lv, Jie zhou

In Reinforcement Learning, it is crucial to represent states and assign rewards based on the action-caused transitions of states.


Converse, Focus and Guess -- Towards Multi-Document Driven Dialogue

1 code implementation4 Feb 2021 Han Liu, Caixia Yuan, Xiaojie Wang, Yushu Yang, Huixing Jiang, Zhongyuan Wang

We propose a novel task, Multi-Document Driven Dialogue (MD3), in which an agent can guess the target document that the user is interested in by leading a dialogue.

Weakly Supervised Real-time Image Cropping based on Aesthetic Distributions

no code implementations15 Oct 2020 Peng Lu, Jiahui Liu, Xujun Peng, Xiaojie Wang

In order to tackle this problem, a weakly supervised cropping frame- work is proposed, where the distribution dissimilarity between high quality images and cropped images is used to guide the coordinate predictor’s training and the ground truths of cropping windows are not required by the proposed method.

Image Cropping

Answer-Driven Visual State Estimator for Goal-Oriented Visual Dialogue

1 code implementation1 Oct 2020 Zipeng Xu, Fangxiang Feng, Xiaojie Wang, Yushu Yang, Huixing Jiang, Zhongyuan Wang

In this paper, we propose an Answer-Driven Visual State Estimator (ADVSE) to impose the effects of different answers on visual states.

Question Generation Visual Dialog

Label-Wise Document Pre-Training for Multi-Label Text Classification

1 code implementation15 Aug 2020 Han Liu, Caixia Yuan, Xiaojie Wang

A major challenge of multi-label text classification (MLTC) is to stimulatingly exploit possible label differences and label correlations.

 Ranked #1 on Multi-Label Text Classification on AAPD (Micro F1 metric)

Classification Document Classification +3

Connecting Embeddings for Knowledge Graph Entity Typing

1 code implementation ACL 2020 Yu Zhao, Anxiang Zhang, Ruobing Xie, Kang Liu, Xiaojie Wang

In this paper, we propose a novel approach for KG entity typing which is trained by jointly utilizing local typing knowledge from existing entity type assertions and global triple knowledge from KGs.

Entity Typing Knowledge Graph Completion

Cycle-CNN for Colorization towards Real Monochrome-Color Camera Systems

1 code implementation AAAI Technical Track: Vision 2020 Xuan Dong, Weixin Li, Xiaojie Wang, Yunhong Wang

We present a new CNN model, named cycle CNN, which can directly use the real data from monochrome-color camera systems for training.


Guessing State Tracking for Visual Dialogue

no code implementations ECCV 2020 Wei Pang, Xiaojie Wang

This paper proposes a guessing state for the Guesser, and regards guess as a process with change of guessing state through a dialogue.

Visual Grounding

Visual Dialogue State Tracking for Question Generation

no code implementations12 Nov 2019 Wei Pang, Xiaojie Wang

A visual dialogue state is defined as the distribution on objects in the image as well as representations of objects.

Dialogue State Tracking Question Generation +1

Cascaded LSTMs based Deep Reinforcement Learning for Goal-driven Dialogue

1 code implementation31 Oct 2019 Yue Ma, Xiaojie Wang, Zhenjiang Dong, Hong Chen

Dialogue embeddings are learned by a LSTM at the middle of the network, and updated by the feeding of all turn embeddings.

Dialogue Management Natural Language Understanding +1

Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random

no code implementations1 Jun 2019 Xiaojie Wang, Rui Zhang, Yu Sun, Jianzhong Qi

In recommender systems, usually the ratings of a user to most items are missing and a critical problem is that the missing ratings are often missing not at random (MNAR) in reality.

Imputation Recommendation Systems

Deep Reason: A Strong Baseline for Real-World Visual Reasoning

no code implementations24 May 2019 Chenfei Wu, Yanzhao Zhou, Gen Li, Nan Duan, Duyu Tang, Xiaojie Wang

This paper presents a strong baseline for real-world visual reasoning (GQA), which achieves 60. 93% in GQA 2019 challenge and won the sixth place.

Visual Reasoning

KDGAN: Knowledge Distillation with Generative Adversarial Networks

no code implementations NeurIPS 2018 Xiaojie Wang, Rui Zhang, Yu Sun, Jianzhong Qi

An alternative method is to adversarially train the classifier against a discriminator in a two-player game akin to generative adversarial networks (GAN), which can ensure the classifier to learn the true data distribution at the equilibrium of this game.

Knowledge Distillation Multi-Label Learning

Chain of Reasoning for Visual Question Answering

no code implementations NeurIPS 2018 Chenfei Wu, Jinlai Liu, Xiaojie Wang, Xuan Dong

A chain of reasoning (CoR) is constructed for supporting multi-step and dynamic reasoning on changed relations and objects.

Question Answering Relational Reasoning +2

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