Author name cluster

Xiaohua Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

1 author row

IJCAI Conference 2019 Conference Paper

Dynamic Item Block and Prediction Enhancing Block for Sequential Recommendation

Guibing Guo
Shichang Ouyang
Xiaodong He
Fajie Yuan
Xiaohua Liu

Sequential recommendation systems have become a research hotpot recently to suggest users with the next item of interest (to interact with). However, existing approaches suffer from two limitations: (1) The representation of an item is relatively static and fixed for all users. We argue that even a same item should be represented distinctively with respect to different users and time steps. (2) The generation of a prediction for a user over an item is computed in a single scale (e. g. , by their inner product), ignoring the nature of multi-scale user preferences. To resolve these issues, in this paper we propose two enhancing building blocks for sequential recommendation. Specifically, we devise a Dynamic Item Block (DIB) to learn dynamic item representation by aggregating the embeddings of those who rated the same item before that time step. Then, we come up with a Prediction Enhancing Block (PEB) to project user representation into multiple scales, based on which many predictions can be made and attentively aggregated for enhanced learning. Each prediction is generated by a softmax over a sampled itemset rather than the whole item space for efficiency. We conduct a series of experiments on four real datasets, and show that even a basic model can be greatly enhanced with the involvement of DIB and PEB in terms of ranking accuracy. The code and datasets can be obtained from https: //github. com/ouououououou/DIB-PEB-Sequential-RS

PDF Details

AAAI Conference 2017 Conference Paper

Neural Machine Translation with Reconstruction

Zhaopeng Tu
Yang Liu
Lifeng Shang
Xiaohua Liu
Hang Li

Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that NMT tends to repeatedly translate some source words while mistakenly ignoring other words. To alleviate this problem, we propose a novel encoder-decoder-reconstructor framework for NMT. The reconstructor, incorporated into the NMT model, manages to reconstruct the input source sentence from the hidden layer of the output target sentence, to ensure that the information in the source side is transformed to the target side as much as possible. Experiments show that the proposed framework signiﬁcantly improves the adequacy of NMT output and achieves superior translation result over state-of-theart NMT and statistical MT systems.

PDF Details

AAAI Conference 2014 Conference Paper

Compact Aspect Embedding for Diversified Query Expansions

Xiaohua Liu
Arbi Bouchoucha
Alessandro Sordoni
Jian-Yun Nie

Diversified query expansion (DQE) based approaches aim to select a set of expansion terms with less redundancy among them while covering as many query aspects as possible. Recently they have experimentally demonstrate their effectiveness for the task of search result diversification. One challenge faced by existing DQE approaches is to ensure the aspect coverage. In this paper, we propose a novel method for DQE, called compact aspect embedding, which exploits trace norm regularization to learn a low rank vector space for the query, with each eigenvector of the learnt vector space representing an aspect, and the absolute value of its corresponding eigenvalue representing the association strength of that aspect to the query. Meanwhile, each expansion term is mapped into the vector space as well. Based on this novel representation of the query aspects and expansion terms, we design a greedy selection strategy to choose a set of expansion terms to explicitly cover all possible aspects of the query. We test our method on several TREC diversification data sets, and show that our method significantly outperforms the state-of-the-art search result diversification approaches.

PDF Details

TIST Journal 2013 Journal Article

Named entity recognition for tweets

Xiaohua Liu
Furu Wei
Shaodian Zhang
Ming Zhou

Two main challenges of Named Entity Recognition (NER) for tweets are the insufficient information in a tweet and the lack of training data. We propose a novel method consisting of three core elements: (1) normalization of tweets; (2) combination of a K-Nearest Neighbors (KNN) classifier with a linear Conditional Random Fields (CRF) model; and (3) semisupervised learning framework. The tweet normalization preprocessing corrects common ill-formed words using a global linear model. The KNN-based classifier conducts prelabeling to collect global coarse evidence across tweets while the CRF model conducts sequential labeling to capture fine-grained information encoded in a tweet. The semisupervised learning plus the gazetteers alleviate the lack of training data. Extensive experiments show the advantages of our method over the baselines as well as the effectiveness of normalization, KNN, and semisupervised learning.

Details DOI

AAAI Conference 2013 Conference Paper

The Automated Acquisition of Suggestions from Tweets

Li Dong
Furu Wei
Yajuan Duan
Xiaohua Liu
Ming Zhou
Ke Xu

This paper targets at automatically detecting and classifying user’s suggestions from tweets. The short and informal nature of tweets, along with the imbalanced characteristics of suggestion tweets, makes the task extremely challenging. To this end, we develop a classification framework on Factorization Machines, which is effective and efficient especially in classification tasks with feature sparsity settings. Moreover, we tackle the imbalance problem by introducing cost-sensitive learning techniques in Factorization Machines. Extensively experimental studies on a manually annotated real-life data set show that the proposed approach significantly improves the baseline approach, and yields the precision of 71. 06% and recall of 67. 86%. We also investigate the reason why Factorization Machines perform better. Finally, we introduce the first manually annotated dataset for suggestion classification.

PDF Details

AAAI Conference 2012 Conference Paper

Collective Nominal Semantic Role Labeling for Tweets

Xiaohua Liu
Zhongyang Fu
Furu Wei
Ming Zhou

Tweets have become an increasingly popular source of fresh information. We investigate the task of Nominal Semantic Role Labeling (NSRL) for tweets, which aims to identify predicate-argument structures defined by nominals in tweets. Studies of this task can help fine-grained information extraction and retrieval from tweets. There are two main challenges in this task: 1) The lack of information in a single tweet, rooted in the short and noisy nature of tweets; and 2) recovery of implicit arguments. We propose jointly conducting NSRL on multiple similar tweets using a graphical model, leveraging the redundancy in tweets to tackle these challenges. Extensive evaluations on a human annotated data set demonstrate that our method outperforms two baselines with an absolute gain of 2. 7% in F1.

PDF Details

AAAI Conference 2012 Conference Paper

Exacting Social Events for Tweets Using a Factor Graph

Xiaohua Liu
Xiangyang Zhou
Zhongyang Fu
Furu Wei
Ming Zhou

Social events are events that occur between people where at least one person is aware of the other and of the event taking place. Extracting social events can play an important role in a wide range of applications, such as the construction of social network. In this paper, we introduce the task of social event extraction for tweets, an important source of fresh events. One main challenge is the lack of information in a single tweet, which is rooted in the short and noise-prone nature of tweets. We propose to collectively extract social events from multiple similar tweets using a novel factor graph, to harvest the redundance in tweets, i. e. , the repeated occurrences of a social event in several tweets. We evaluate our method on a human annotated data set, and show that it outperforms all baselines, with an absolute gain of 21% in F1.

PDF Details

IJCAI Conference 2011 Conference Paper

Collective Semantic Role Labeling for Tweets with Clustering

Xiaohua Liu
Kuan Li
Ming Zhou
Zhongyang Xiong

As tweets has become a comprehensive repository of fresh information, Semantic Role Labeling (SRL) for tweets has aroused great research interests because of its center role in a wide range of tweet related studies such as fine-grained information extraction, sentiment analysis and summarization. However, the fact that a tweet is often too short and informal to provide sufficient information poses a main challenge. To tackle this challenge, we propose a new method to collectively label similar tweets. The underlying idea is to exploit similar tweets to make up for the lack of information in a tweet. Specifically, similar tweets are first grouped together by clustering. Then for each cluster a two-stage labeling is conducted: One labeler conducts SRL to get statistical information, such as the predicate/argument/role triples that occur frequently, from its highly confidently labeled results; then in the second stage, another labeler performs SRL with such statistical information to refine the results. Experimental results on a human annotated dataset show that our approach remarkably improves SRL by 3. 1% F1.

PDF Details DOI

AAAI Conference 2011 Conference Paper

Enhancing Semantic Role Labeling for Tweets Using Self-Training

Xiaohua Liu
Li Kuan
Ming Zhou
Zhongyang Xiong

Semantic Role Labeling (SRL) for tweets is a meaningful task that can beneﬁt a wide range of applications such as ﬁnegrained information extraction and retrieval from tweets. One main challenge of the task is the lack of annotated tweets, which is required to train a statistical model. We introduce self-training to SRL, leveraging abundant unlabeled tweets to alleviate its depending on annotated tweets. A novel strategy of tweet selection is presented, ensuring the chosen tweets are both correct and informative. More speciﬁcally, the correctness is estimated according to the labeling conﬁdences and agreement of two Conditional Random Fields based labelers, which are trained on the randomly evenly spitted labeled data; while the informativeness is in proportion to the maximum distance between the tweet and the already selected tweets. We evaluate our method on a human annotated data set and show that bootstrapping improve a baseline by 3. 4% F1.

PDF Details

AAAI Conference 2007 Conference Paper

Mining Sequential Patterns and Tree Patterns to Detect Erroneous Sentences

Guihua Sun
Xiaohua Liu

An important application area of detecting erroneous sentences is to provide feedback for writers of English as a Second Language. This problem is difﬁcult since both erroneous and correct sentences are diversiﬁed. In this paper, we propose a novel approach to identifying erroneous sentences. We ﬁrst mine labeled tree patterns and sequential patterns to characterize both erroneous and correct sentences. Then the discovered patterns are utilized in two ways to distinguish correct sentences from erroneous sentences: (1) the patterns are transformed into sentence features for existing classiﬁcation models, e. g. , SVM; (2) the patterns are used to build a rulebased classiﬁcation model. Experimental results show that both techniques are promising while the second technique outperforms the ﬁrst approach. Moreover, the classiﬁcation model in the second proposal is easy to understand, and we can provide intuitive explanation for classiﬁcation results.

PDF Details