Question Classification using Head Words and their Hypernyms
Zhiheng Huang,Marcus Thint,Zengchang Qin +2 more
- pp 927-936
Reads0
Chats0
TLDR
This work proposes head word feature and present two approaches to augment semantic features of such head words using WordNet and proposes a compact yet effective feature set.Abstract:
Question classification plays an important role in question answering. Features are the key to obtain an accurate question classifier. In contrast to Li and Roth (2002)'s approach which makes use of very rich feature space, we propose a compact yet effective feature set. In particular, we propose head word feature and present two approaches to augment semantic features of such head words using WordNet. In addition, Lesk's word sense disambiguation (WSD) algorithm is adapted and the depth of hypernym feature is optimized. With further augment of other standard features such as unigrams, our linear SVM and Maximum Entropy (ME) models reach the accuracy of 89.2% and 89.0% respectively over a standard benchmark dataset, which outperform the best previously reported accuracy of 86.2%.read more
Citations
More filters
Proceedings ArticleDOI
A Convolutional Neural Network for Modelling Sentences
TL;DR: A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.
Journal ArticleDOI
From symbolic to sub-symbolic information in question classification
TL;DR: This paper presents and evaluates a rule-based question classifier that partially founds its performance in the detection of the question headword and in its mapping into the target category through the use of WordNet, and uses the rule-base classifier as a features’ provider of a machine learning-basedquestion classifier.
Proceedings ArticleDOI
Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware
TL;DR: Surprisingly, it is found that short synaptic delays are sufficient to implement the dynamic (temporal) aspect of the RNN in the question classification task and the discretization of the neural activities is beneficial to the train-and-constrain approach.
Journal ArticleDOI
Expert Finding for Question Answering via Graph Regularized Matrix Completion
TL;DR: This paper considers the problem of expert finding from the viewpoint of missing value estimation, and develops a novel graph-regularized matrix completion algorithm for inferring the user model and develops two efficient iterative procedures, GRMC-EGM andGRMC-AGM, to solve the optimization problem.
Journal ArticleDOI
Beyond Text QA: Multimedia Answer Generation by Harvesting Web Information
TL;DR: This paper proposes a scheme that is able to enrich textual answers in cQA with appropriate media data and can enable a novel multimedia question answering (MMQA) approach as users can find multimedia answers by matching their questions with those in the pool.
References
More filters
Journal ArticleDOI
LIBSVM: A library for support vector machines
Chih-Chung Chang,Chih-Jen Lin +1 more
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Book
The Nature of Statistical Learning Theory
TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
Journal ArticleDOI
A maximum entropy approach to natural language processing
TL;DR: A maximum-likelihood approach for automatically constructing maximum entropy models is presented and how to implement this approach efficiently is described, using as examples several problems in natural language processing.
Proceedings ArticleDOI
Accurate Unlexicalized Parsing
Dan Klein,Christopher D. Manning +1 more
TL;DR: It is demonstrated that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence assumptions latent in a vanilla treebank grammar.