Search Results for author: Xiang Ao

Found 29 papers, 11 papers with code

Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension

no code implementations Findings (EMNLP) 2021 Guoxin Yu, Jiwei Li, Ling Luo, Yuxian Meng, Xiang Ao, Qing He

In this paper, we investigate the unified ABSA task from the perspective of Machine Reading Comprehension (MRC) by observing that the aspect and the opinion terms can serve as the query and answer in MRC interchangeably.

Aspect-Based Sentiment Analysis Machine Reading Comprehension +2

Selective Fairness in Recommendation via Prompts

no code implementations10 May 2022 Yiqing Wu, Ruobing Xie, Yongchun Zhu, Fuzhen Zhuang, Xiang Ao, Xu Zhang, Leyu Lin, Qing He

In this work, we define the selective fairness task, where users can flexibly choose which sensitive attributes should the recommendation model be bias-free.

Fairness Sequential Recommendation

User-Centric Conversational Recommendation with Multi-Aspect User Modeling

1 code implementation20 Apr 2022 Shuokai Li, Ruobing Xie, Yongchun Zhu, Xiang Ao, Fuzhen Zhuang, Qing He

In this work, we highlight that the user's historical dialogue sessions and look-alike users are essential sources of user preferences besides the current dialogue session in CRS.

Dialogue Generation Dialogue Understanding +1

Multi-view Multi-behavior Contrastive Learning in Recommendation

1 code implementation20 Mar 2022 Yiqing Wu, Ruobing Xie, Yongchun Zhu, Xiang Ao, Xin Chen, Xu Zhang, Fuzhen Zhuang, Leyu Lin, Qing He

We argue that MBR models should: (1) model the coarse-grained commonalities between different behaviors of a user, (2) consider both individual sequence view and global graph view in multi-behavior modeling, and (3) capture the fine-grained differences between multiple behaviors of a user.

Contrastive Learning

Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement

no code implementations27 Dec 2021 Fuwei Zhang, Zhao Zhang, Xiang Ao, Dehong Gao, Fuzhen Zhuang, Yi Wei, Qing He

The proposed model encodes the textual information in queries, documents and the KG with multilingual BERT, and incorporates the KG information in the query-document matching process with a hierarchical information fusion mechanism.

Information Retrieval

Rethinking Pareto Approaches in Constrained Reinforcement Learning

no code implementations29 Sep 2021 Mengda Huang, Feiyang Pan, Jia He, Xiang Ao, Qing He

Constrained Reinforcement Learning (CRL) burgeons broad interest in recent years, which pursues both goals of maximizing long-term returns and constraining costs.

reinforcement-learning

Layer-wise Model Pruning based on Mutual Information

no code implementations EMNLP 2021 Chun Fan, Jiwei Li, Xiang Ao, Fei Wu, Yuxian Meng, Xiaofei Sun

The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level.

Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback

1 code implementation13 Aug 2021 Haoming Li, Feiyang Pan, Xiang Ao, Zhao Yang, Min Lu, Junwei Pan, Dapeng Liu, Lei Xiao, Qing He

The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days.

online learning

PENS: A Dataset and Generic Framework for Personalized News Headline Generation

no code implementations ACL 2021 Xiang Ao, Xiting Wang, Ling Luo, Ying Qiao, Qing He, Xing Xie

To build up a benchmark for this problem, we publicize a large-scale dataset named PENS (PErsonalized News headlineS).

Headline generation

GuideBoot: Guided Bootstrap for Deep Contextual Bandits

no code implementations18 Jul 2021 Feiyang Pan, Haoming Li, Xiang Ao, Wei Wang, Yanrong Kang, Ao Tan, Qing He

The proposed method is efficient as it can make decisions on-the-fly by utilizing only one randomly chosen model, but is also effective as we show that it can be viewed as a non-Bayesian approximation of Thompson sampling.

Multi-Armed Bandits

ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information

3 code implementations ACL 2021 Zijun Sun, Xiaoya Li, Xiaofei Sun, Yuxian Meng, Xiang Ao, Qing He, Fei Wu, Jiwei Li

Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding.

Language Modelling Machine Reading Comprehension +3

Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification

1 code implementation21 Jun 2021 Binzong Geng, Min Yang, Fajie Yuan, Shupeng Wang, Xiang Ao, Ruifeng Xu

In this paper, we propose a novel iterative network pruning with uncertainty regularization method for lifelong sentiment classification (IPRLS), which leverages the principles of network pruning and weight regularization.

Network Pruning online learning +1

Defending against Backdoor Attacks in Natural Language Generation

1 code implementation3 Jun 2021 Chun Fan, Xiaoya Li, Yuxian Meng, Xiaofei Sun, Xiang Ao, Fei Wu, Jiwei Li, Tianwei Zhang

To defend against these attacks, we propose to detect the attack trigger by examining the effect of deleting or replacing certain words on the generation outputs, which we find successful for certain types of attacks.

Backdoor Attack Dialogue Generation +2

Sentence Similarity Based on Contexts

no code implementations17 May 2021 Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan

The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context.

Language Modelling Semantic Similarity +2

Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection

1 code implementation The Web Conference 2021 Yang Liu1, Xiang Ao, Zidi Qin, Jianfeng Chi, Jinghua Feng, Hao Yang, Qing He

Graph-based fraud detection approaches have escalated lots of attention recently due to the abundant relational information of graph-structured data, which may be beneficial for the detection of fraudsters.

Fraud Detection Node Classification

Meet Changes with Constancy: Learning Invariance in Multi-Source Translation

no code implementations COLING 2020 Jianfeng Liu, Ling Luo, Xiang Ao, Yan Song, Haoran Xu, Jian Ye

Multi-source neural machine translation aims to translate from parallel sources of information (e. g. languages, images, etc.)

Machine Translation Translation

Interactive Key-Value Memory-augmented Attention for Image Paragraph Captioning

no code implementations COLING 2020 Chunpu Xu, Yu Li, Chengming Li, Xiang Ao, Min Yang, Jinwen Tian

In this paper, we propose an Interactive key-value Memory- augmented Attention model for image Paragraph captioning (IMAP) to keep track of the attention history (salient objects coverage information) along with the update-chain of the decoder state and therefore avoid generating repetitive or incomplete image descriptions.

Image Paragraph Captioning

Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information

1 code implementation Findings of the Association for Computational Linguistics 2020 Yuyang Nie, Yuanhe Tian, Yan Song, Xiang Ao, Xiang Wan

Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the running text.

Chinese Named Entity Recognition NER

Improving Robustness and Generality of NLP Models Using Disentangled Representations

no code implementations21 Sep 2020 Jiawei Wu, Xiaoya Li, Xiang Ao, Yuxian Meng, Fei Wu, Jiwei Li

We show that models trained with the proposed criteria provide better robustness and domain adaptation ability in a wide range of supervised learning tasks.

Domain Adaptation Representation Learning

Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge

1 code implementation ACL 2020 Yuanhe Tian, Yan Song, Xiang Ao, Fei Xia, Xiaojun Quan, Tong Zhang, Yonggang Wang

Chinese word segmentation (CWS) and part-of-speech (POS) tagging are important fundamental tasks for Chinese language processing, where joint learning of them is an effective one-step solution for both tasks.

Chinese Word Segmentation Part-Of-Speech Tagging +1

Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network

no code implementations23 Dec 2019 Chi Xu, Hao Feng, Guoxin Yu, Min Yang, Xiting Wang, Xiang Ao

In this paper, we aim to improve ATSA by discovering the potential aspect terms of the predicted sentiment polarity when the aspect terms of a test sentence are unknown.

Sentiment Analysis

Field-aware Calibration: A Simple and Empirically Strong Method for Reliable Probabilistic Predictions

no code implementations26 May 2019 Feiyang Pan, Xiang Ao, Pingzhong Tang, Min Lu, Dapeng Liu, Lei Xiao, Qing He

It is often observed that the probabilistic predictions given by a machine learning model can disagree with averaged actual outcomes on specific subsets of data, which is also known as the issue of miscalibration.

Click-Through Rate Prediction

Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings

1 code implementation25 Apr 2019 Feiyang Pan, Shuokai Li, Xiang Ao, Pingzhong Tang, Qing He

We propose Meta-Embedding, a meta-learning-based approach that learns to generate desirable initial embeddings for new ad IDs.

Click-Through Rate Prediction Meta-Learning

Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents

no code implementations22 Aug 2018 Ganbin Zhou, Rongyu Cao, Xiang Ao, Ping Luo, Fen Lin, Leyu Lin, Qing He

Additionally, a "low-level sharing, high-level splitting" structure of CNN is designed to handle the documents from different content domains.

Free-rider Episode Screening via Dual Partition Model

no code implementations19 May 2018 Xiang Ao, Yang Liu, Zhen Huang, Luo Zuo, Qing He

An effective technique for filtering free-rider episodes is using a partition model to divide an episode into two consecutive subepisodes and comparing the observed support of such episode with its expected support under the assumption that these two subepisodes occur independently.

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