XRCE at SemEval-2016 Task 5: Feedbacked Ensemble Modeling on Syntactico-Semantic Knowledge for Aspect Based Sentiment Analysis

Proceedings of SemEval-2016, pages 277–281, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics XRCE at SemEval-2016 Task 5: Feedbacked Ensemble Modelling on Syntactico-Semantic Knowledge for Aspect Based Sentiment Analysis Caroline Brun and Julien Perez and Claude Roux Xerox Research Centre Europe 6, chemin de Maupertuis 38240 Meylan, France {caroline.brun, julien.perez, claude.roux}@xrce.xerox.com Abstract This paper presents our contribution to the Se- mEval 2016 task 5: Aspect-Based Sentiment Analysis. We have addressed Subtask 1 for the restaurant domain, in English and French, which implies opinion target expression detec- tion, aspect category and polarity classifica- tion. We describe the different components of the system, based on composite models com- bining sophisticated linguistic features with Machine Learning algorithms, and report the results obtained for both languages. 1 Introduction and Related Work Sentiment Analysis is an important topic in natural language processing, and Aspect Based Sentiment Analysis (ABSA), i.e. detection of sentiments ex- pressed on different aspects of a given entity, con- stitute a very interesting but quite challenging task (Liu, 2012; Ganu et al., 2009). ABSA is a task first introduced at SemEval in 2014 (Pontiki et al., 2014), continued in 2015 (Pontiki et al., 2015) and now, in 2016 (Pontiki et al., 2016). Our team has partici- pated to the first edition, with good results on the restaurant domain (Brun et al., 2014) and decided to reiterate the participation in 2016, on the same do- main but on English and French, as the challenge has become multilingual. While relatively similar, the task has evolved since 2014: aspect targets and categories are annotated together instead of sepa- rately; only opinionated terms (Opinion Target Ex- pressions, OTE) are annotated, and aspect categories are finer grained (12 classes instead of 5), which makes the subtasks even more challenging. In the previous challenges, most systems, includ- ing ours, use state-of-the art machine learning al- gorithms such as SVMs (Wagner et al., 2014; Kir- itchenko et al., 2014; Brun et al., 2014; Brychc´ın et al., 2014) or CRFs (Toh and Wang, 2014; Ham- dan et al., 2015), with lexical information, bigrams and POS as features. In 2014, (Kiritchenko et al., 2014) had particularly good results on aspect cat- egory and aspect polarity detection, using SVMs combined with rich linguistic features including de- pendency parsing. In 2015, the system presented by (Saias, 2015) reported the best result for polar- ity classification, using a maximum entropy clas- sifier, having bag-of-words, lemmas, bigrams after verbs, and punctuation based features, along with sentiment lexicon-based features. Our system shares whith these ones the use of syntactic features to ad- dress the different ABSA tasks. For the present challenge, we addressed substask 1, which implies target terms detection, aspect cate- gory and polarity classification. In the remaining of the paper, we describe the different components of our system which combine rich linguistic features and machine learning algorithms (CRF, Ensemble models for classification). We then present and dis- cuss our results on the different subtasks. We finally conclude and propose future directions. …

Content truncated to 500 words