Question Classification using Head Words and their Hypernyms
By Zhiheng Huang, Marcus Thint, Zengchang Qin. 2008
225 citations recorded by the source corpus.
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%.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoav Goldberg
- Phil Blunsom
- Willem H. Zuidema
- Edward Grefenstette
- Kyunghyun Cho
- Mohit Bansal
- Yoshua Bengio
- Yonatan Belinkov
In Natural Language Processing
- Phil Blunsom
- Yoav Goldberg
- Edward Grefenstette
- Willem H. Zuidema
- Nal Kalchbrenner
- Phong Le
- Yoon Kim
- Kyunghyun Cho
Citations in the corpus
- A Convolutional Neural Network for Modelling Sentences (2014, methodology): “We then relate the results of the experiments and we inspect the learnt feature detectors.”
- Question Classification by Weighted Combination of Lexical, Syntactic and Semantic Features (2011, methodology): “Similar to [6,13], we extracted the head word based on the syntactical structure of the question.”
- The Forest Convolutional Network: Compositional Distributional Semantics with a Neural Chart and without Binarization (2015, methodology): “, 2014), MaxEntH (Huang et al., 2008) (which uses MaxEnt with uni-bi-trigrams,”
- High Accuracy Rule-based Question Classification using Question Syntax and Semantics (2016, methodology): “Previous work by (Huang et al., 2008), which also makes use of both headwords and WordNet, while using slightly different methods, achieves an accuracy of 89.2%.”
- From symbolic to sub-symbolic information in question classification (2011, methodology): “2005) and (Huang et al. 2008; Metzler and Croft 2005), respectively, as features to train a SVM.”