Alert button
Picture for Lizhen Qu

Lizhen Qu

Alert button

Collective Vertex Classification Using Recursive Neural Network

Jan 24, 2017
Qiongkai Xu, Qing Wang, Chenchen Xu, Lizhen Qu

Figure 1 for Collective Vertex Classification Using Recursive Neural Network
Figure 2 for Collective Vertex Classification Using Recursive Neural Network
Figure 3 for Collective Vertex Classification Using Recursive Neural Network
Figure 4 for Collective Vertex Classification Using Recursive Neural Network

Collective classification of vertices is a task of assigning categories to each vertex in a graph based on both vertex attributes and link structure. Nevertheless, some existing approaches do not use the features of neighbouring vertices properly, due to the noise introduced by these features. In this paper, we propose a graph-based recursive neural network framework for collective vertex classification. In this framework, we generate hidden representations from both attributes of vertices and representations of neighbouring vertices via recursive neural networks. Under this framework, we explore two types of recursive neural units, naive recursive neural unit and long short-term memory unit. We have conducted experiments on four real-world network datasets. The experimental results show that our frame- work with long short-term memory model achieves better results and outperforms several competitive baseline methods.

* 7 pages, 5 figures 
Viaarxiv icon

Named Entity Recognition for Novel Types by Transfer Learning

Oct 31, 2016
Lizhen Qu, Gabriela Ferraro, Liyuan Zhou, Weiwei Hou, Timothy Baldwin

Figure 1 for Named Entity Recognition for Novel Types by Transfer Learning
Figure 2 for Named Entity Recognition for Novel Types by Transfer Learning

In named entity recognition, we often don't have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly. In this paper, we propose a method where, given training data in a related domain with similar (but not identical) named entity (NE) types and a small amount of in-domain training data, we use transfer learning to learn a domain-specific NE model. That is, the novelty in the task setup is that we assume not just domain mismatch, but also label mismatch.

* EMNLP 2016  
Viaarxiv icon

Big Data Small Data, In Domain Out-of Domain, Known Word Unknown Word: The Impact of Word Representation on Sequence Labelling Tasks

May 20, 2015
Lizhen Qu, Gabriela Ferraro, Liyuan Zhou, Weiwei Hou, Nathan Schneider, Timothy Baldwin

Figure 1 for Big Data Small Data, In Domain Out-of Domain, Known Word Unknown Word: The Impact of Word Representation on Sequence Labelling Tasks
Figure 2 for Big Data Small Data, In Domain Out-of Domain, Known Word Unknown Word: The Impact of Word Representation on Sequence Labelling Tasks
Figure 3 for Big Data Small Data, In Domain Out-of Domain, Known Word Unknown Word: The Impact of Word Representation on Sequence Labelling Tasks
Figure 4 for Big Data Small Data, In Domain Out-of Domain, Known Word Unknown Word: The Impact of Word Representation on Sequence Labelling Tasks

Word embeddings -- distributed word representations that can be learned from unlabelled data -- have been shown to have high utility in many natural language processing applications. In this paper, we perform an extrinsic evaluation of five popular word embedding methods in the context of four sequence labelling tasks: POS-tagging, syntactic chunking, NER and MWE identification. A particular focus of the paper is analysing the effects of task-based updating of word representations. We show that when using word embeddings as features, as few as several hundred training instances are sufficient to achieve competitive results, and that word embeddings lead to improvements over OOV words and out of domain. Perhaps more surprisingly, our results indicate there is little difference between the different word embedding methods, and that simple Brown clusters are often competitive with word embeddings across all tasks we consider.

Viaarxiv icon

Estimating Maximally Probable Constrained Relations by Mathematical Programming

Aug 04, 2014
Lizhen Qu, Bjoern Andres

Figure 1 for Estimating Maximally Probable Constrained Relations by Mathematical Programming
Figure 2 for Estimating Maximally Probable Constrained Relations by Mathematical Programming
Figure 3 for Estimating Maximally Probable Constrained Relations by Mathematical Programming
Figure 4 for Estimating Maximally Probable Constrained Relations by Mathematical Programming

Estimating a constrained relation is a fundamental problem in machine learning. Special cases are classification (the problem of estimating a map from a set of to-be-classified elements to a set of labels), clustering (the problem of estimating an equivalence relation on a set) and ranking (the problem of estimating a linear order on a set). We contribute a family of probability measures on the set of all relations between two finite, non-empty sets, which offers a joint abstraction of multi-label classification, correlation clustering and ranking by linear ordering. Estimating (learning) a maximally probable measure, given (a training set of) related and unrelated pairs, is a convex optimization problem. Estimating (inferring) a maximally probable relation, given a measure, is a 01-linear program. It is solved in linear time for maps. It is NP-hard for equivalence relations and linear orders. Practical solutions for all three cases are shown in experiments with real data. Finally, estimating a maximally probable measure and relation jointly is posed as a mixed-integer nonlinear program. This formulation suggests a mathematical programming approach to semi-supervised learning.

* 16 pages 
Viaarxiv icon