AI-KU: Using Co-Occurrence Modeling for Semantic Similarity

Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 92–96, Dublin, Ireland, August 23-24, 2014. AI-KU: Using Co-Occurrence Modeling for Semantic Similarity Osman Bas¸kaya Artificial Intelligence Laboratory Koc¸ University, Istanbul, Turkey obaskaya@ku.edu.tr Abstract In this paper, we describe our unsupervised method submitted to the Cross-Level Se- mantic Similarity task in Semeval 2014 that computes semantic similarity between two different sized text fragments. Our method models each text fragment by using the co- occurrence statistics of either occurred words or their substitutes. The co-occurrence mod- eling step provides dense, low-dimensional embedding for each fragment which allows us to calculate semantic similarity using various similarity metrics. Although our current model avoids the syntactic infor- mation, we achieved promising results and outperformed all baselines. 1 Introduction Semantic similarity is a measure that specifies the similarity of one text’s meaning to another’s. Se- mantic similarity plays an important role in vari- ous Natural Language Processing (NLP) tasks such as textual entailment (Berant et al., 2012), summa- rization (Lin and Hovy, 2003), question answering (Surdeanu et al., 2011), text classification (Sebas- tiani, 2002), word sense disambiguation (Sch¨utze, 1998) and information retrieval (Park et al., 2005). There are three main approaches to computing the semantic similarity between two text fragments. The first approach uses Vector Space Models (see Turney & Pantel (2010) for an overview) where each text is represented as a bag-of-word model. The similarity between two text fragments can then be computed with various metrics such as cosine similarity. Sparseness in the input nature is the key problem for these models. Therefore, later works such as Latent Semantic Indexing (?) and This work is licensed under a Creative Commons At- tribution 4.0 International Licence. Page numbers and pro- ceedings footer are added by the organisers. Licence details: http://creativecommons.org/licenses/by/4.0/ Topic Models (Blei et al., 2003) overcome spar- sity problems via reducing the dimensionality of the model by introducing latent variables. The sec- ond approach blends various lexical and syntactic features and attacks the problem through machine learning models. The third approach is based on word-to-word similarity alignment (Pilehvar et al., 2013; Islam and Inkpen, 2008). The Cross-Level Semantic Similarity (CLSS) task in SemEval 20141 (Jurgens et al., 2014) provides an evaluation framework to assess similarity meth- ods for texts in different volumes (i.e., lexical lev- els). Unlike previous SemEval and *SEM tasks that were interested in comparing texts with simi- lar volume, this task consists of four subtasks (para- graph2sentence, sentence2phrase, phrase2word and word2sense) that investigate the performance of systems based on pairs of texts of different sizes. A system should report the similarity score of a given pair, ranging from 4 (two items have very similar meanings and the most important ideas, concepts, or actions in the larger text are repre- sented in the smaller text) to 0 (two items do not mean the same thing and are not on the same topic). In this paper, we describe our two unsupervised systems that are based on co-occurrence statistics of words. The …

Content truncated to 500 words