Shiva Taslimipoor

MiniExperts: An SVM Approach for Measuring Semantic Textual Similarity

This paper describes the system submitted by the University of Wolverhampton and the University of Malaga for SemEval-2015 Task 2: Semantic Textual Similarity. The system uses a Supported Vector Machine approach based on a number of linguistically motivated features. Our system performed satisfactorily for English and obtained a mean 0.7216 Pearson correlation. However, it performed less adequately for Spanish, obtaining only a mean 0.5158.

Cognitive Processing of Multiword Expressions in Native and Non-native Speakers of English: Evidence from Gaze Data

Gaze data has been used to investigate the cognitive processing of certain types of formulaic language such as idioms and binominal phrases, however, very little is known about the online cognitive processing of multiword expressions. In this paper we use gaze features to compare the processing of verb - particle and verb - noun multiword expressions to control phrases of the same part-of-speech pattern. We also compare the gaze data for certain components of these expressions and the control phrases in order to find out whether these components are processed differently from the whole units. We provide results for both native and non-native speakers of English and we analyse the importance of the various gaze features for the purpose of this study. We discuss our findings in light of the E-Z model of reading.

Using Gaze Data to Predict Multiword Expressions.

In recent years gaze data has been increasingly used to improve and evaluate NLP models due to the fact that it carries information about the cognitive processing of linguistic phenomena. In this paper we conduct a preliminary study towards the automatic identification of multiword expressions based on gaze features from native and non-native speakers of English. We report comparisons between a part-of-speech (POS) and frequency baseline to: i) a prediction model based solely on gaze data and ii) a combined model of gaze data, POS and frequency. In spite of the challenging nature of the task, best performance was achieved by the latter. Furthermore, we explore how the type of gaze data (from native versus non-native speakers) affects the prediction, showing that data from the two groups is discriminative to an equal degree for the task. Finally, we show that late processing measures are more predictive than early ones, which is in line with previous research on idioms and other formulaic structures.

Bilingual Contexts from Comparable Corpora to Mine for Translations of Collocations

Due to the limited availability of parallel data in many languages, we propose a methodology that benefits from comparable corpora to find translation equivalents for collocations (as a specific type of difficult-to-translate multi-word expressions). Finding translations is known to be more difficult for collocations than for words. We propose a method based on bilingual context extraction and build a word (distributional) representation model drawing on these bilingual contexts (bilingual English-Spanish contexts in our case). We show that the bilingual context construction is effective for the task of translation equivalent learning and that our method outperforms a simplified distributional similarity baseline in finding translation equivalents.

Investigating the Opacity of Verb-Noun Multiword Expression Usages in Context.

This study investigates the supervised token-based identification of Multiword Expressions (MWEs). This is an ongoing research to exploit the information contained in the contexts in which different instances of an expression could occur. This information is used to investigate the question of whether an expression is literal or MWE. Lexical and syntactic context features derived from vector representations are shown to be more effective over traditional statistical measures to identify tokens of MWEs.