CASSA: A Context-Aware Synonym Simplification Algorithm

Human Language Technologies: The 2015 Annual Conference of the North American Chapter of the ACL, pages 1380–1385, Denver, Colorado, May 31 – June 5, 2015. c⃝2015 Association for Computational Linguistics CASSA: A Context-Aware Synonym Simplification Algorithm Ricardo Baeza-Yates Yahoo Labs & Web Research Group Universitat Pompeu Fabra, Barcelona, Spain rbaeza@acm.org Luz Rello Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh, PA, USA luzrello@acm.org Julia Dembowski Department of Computational Linguistics Saarland University, Germany juliad@coli.uni-saarland.de Abstract We present a new context-aware method for lexical simplification that uses two free lan- guage resources and real web frequencies. We compare it with the state-of-the-art method for lexical simplification in Spanish and the es- tablished simplification baseline, that is, the most frequent synonym. Our method im- proves upon the other methods in the detection of complex words, in meaning preservation, and in simplicity. Although we use Spanish, the method can be extended to other languages since it does not require alignment of parallel corpora. 1 Introduction Simplified text is crucial for some populations to read effectively, especially for cognitively impaired people such as people with autism spectrum disor- der (Evans et al., 2014; Orasan et al., 2013), aphasia (Carroll et al., 1999), dyslexia (Rello et al., 2013a), Down syndrome (Saggion et al., 2015; Saggion et al., 2011), or other intellectual disabilities (Huener- fauth et al., 2009). In fact, the United Nations (1994) proposed a set of standard rules to leverage document accessibility for persons with disabilities. Text simplification at- tempts to solve this problem automatically by reduc- ing the complexity of the lexicon, syntax, or seman- tics while attempting to preserve its meaning and in- formation content (Siddharthan, 2006). Among all the types of text simplification this paper focuses on lexical simplification. Lexical simplification methods require language resources, such as simplified corpora or synonyms dictionaries. For languages with less resources than English, e.g. no Simple Wikipedia (Biran et al., 2011; Yatskar et al., 2010) or less representation in WordNet, such as Spanish,1 the creation of lexical simplification methods is more challenging. Our approach makes use of two free resources, Google Books Ngram Corpus and the Spanish OpenThesaurus, as well as real web frequencies to create a lexical simplification system. Our system improves upon the state of the art for lexical simpli- fication in Spanish and the established simplification baseline, i.e., the most frequent synonym, in several aspects: complex word detection, meaning preser- vation, and simplicity. We also show the coverage of our technique in a collection of books in Spanish, as this is another relevant measure of a simplifica- tion algorithm. The method is language independent and given that these resources are available in other languages, it could be easily extended to other lan- guages with similar language resources. The rest of the paper is organized as follows. The next section presents related work. Then in Section 3 we present the simplification algorithm while in Sec- tions 4 and 5 we present our experimental evalua- tion. Finally, in Section 6 we discuss our results, ex- tensions …

Content truncated to 500 words