AmritaNLP at SemEval-2018 Task 10: Capturing discriminative attributes using convolution neural network over global vector representation.

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 1003–1007 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics AmritaNLP at SemEval-2018 Task 10: Capturing discriminative attributes using convolution neural network over global vector representation. Vivek Vinayan, Anand Kumar M, Soman K P Center for Computational Engineering and Networking (CEN) Amrita School of Engineering, Coimbatore Amrita Vishwa Vidyapeetham, India cb.en.p2cen16018@cb.students.amrita.edu, m anandkumar@cb.amrita.edu Abstract The ”Capturing Discriminative Attributes” sharedtask is the tenth task, conjoint with Se- mEval2018. The task is to predict if a word can capture distinguishing attributes of one word from another. We use GloVe word em- bedding, pre-trained on openly sourced cor- pus for this task. A base representation is initially established over varied dimensions. These representations are evaluated based on validation scores over two models, first on an SVM based classifier and second on a one di- mension CNN model. The scores are used to further develop the representation with vector combinations, by considering various distance measures. These measures correspond to off- set vectors which are concatenated as features, mainly to improve upon the F1score, with the best accuracy. The features are then further tuned on the validation scores, to achieve high- est F1score. Our evaluation narrowed down to two representations, classified on CNN mod- els, having a total dimension length of 1204 & 1203 for the final submissions. Of the two, the latter feature representation delivered our best F1score of 0.658024 (as per result1.) 1 Introduction As famously quoted by firth ”You shall know a word by the company it keeps” that is, the se- mantic information embedded in a representation can only be described by the words surrounding it. This can only get you somewhere when, company itself is unambiguous and a representation goes through capturing ”hypothetically” every sense of the word over a corpus. The capturing discrim- inative attributes sharedtask, conducted with Se- mEval(2018) is a task proposed by alicia kerbs and denis paperno (2016). It describes, how lexi- cal similarity may not be enough to access qualita- tively, the semantic information for a multitude of tasks. Wherein they propose that, with this task, a 1Results/Evaluation under the team name ”AmritaNLP” system can be modelled for effectively extracting certain semantic differences in the words for un- derstanding the sense embedded within them. This is provided as a proof of concept dataset for this sharedtask, where a certain word is used to check if it can distinguish between a pair of words. The dataset in itself seems simple where, in the training set a label information for the two classes, positive or negative are provided making this a binary clas- sification task. The three words that are provided in each instance are given in the order as, a pivot word followed by a compare word and ending with a attribute or feature word, that may or may not be associated with the pivot word. Based on the last word it is decided, if that attribute word actually is a dis- tinguishing …

Content truncated to 500 words