Unveiling the relationship between complex networks metrics and word senses
arXiv:1302.4465 · doi:10.1209/0295-5075/98/18002
Abstract
The automatic disambiguation of word senses (i.e., the identification of which of the meanings is used in a given context for a word that has multiple meanings) is essential for such applications as machine translation and information retrieval, and represents a key step for developing the so-called Semantic Web. Humans disambiguate words in a straightforward fashion, but this does not apply to computers. In this paper we address the problem of Word Sense Disambiguation (WSD) by treating texts as complex networks, and show that word senses can be distinguished upon characterizing the local structure around ambiguous words. Our goal was not to obtain the best possible disambiguation system, but we nevertheless found that in half of the cases our approach outperforms traditional shallow methods. We show that the hierarchical connectivity and clustering of words are usually the most relevant features for WSD. The results reported here shine light on the relationship between semantic and structural parameters of complex networks. They also indicate that when combined with traditional techniques the complex network approach may be useful to enhance the discrimination of senses in large texts
The Supplementary Information (SI) is available from http://dl.dropbox.com/u/2740286/epl_SI.pdf
References in corpus (8)
- Universal Behavior of Load Distribution in Scale-free Networks
- Global Organization of the Lexicon
- Hierarchical characterization of complex networks
- Correlations between structure and dynamics in complex networks
- Comparing intermittency and network measurements of words and their dependency on authorship
- Beyond the average: Detecting global singular nodes from local features in complex networks
- Network Discovery by Generalized Random Walks
- Using Complex Networks to Quantify Consistency in the Use of Words
Cited by in corpus (18)
- Distance to the scaling law: a useful approach for unveiling relationships between crime and urban metrics
- Patterns of authors contribution in scientific manuscripts
- A complex network approach to stylometry
- Word sense disambiguation: a complex network approach
- Classifying informative and imaginative prose using complex networks
- Concentric network symmetry grasps authors' styles in word adjacency networks
- Authorship recognition via fluctuation analysis of network topology and word intermittency
- On the use of topological features and hierarchical characterization for disambiguating names in collaborative networks
- Word sense induction using word embeddings and community detection in complex networks
- Representation of texts as complex networks: a mesoscopic approach
- Connecting Network Science and Information Theory
- Network analysis of named entity co-occurrences in written texts
- On predicting research grants productivity
- Semantic flow in language networks
- An Image Analysis Approach to the Calligraphy of Books
- Discriminating word senses with tourist walks in complex networks
- A perspective on the advancement of natural language processing tasks via topological analysis of complex networks
- Extractive Multi Document Summarization using Dynamical Measurements of Complex Networks