ALB at SemEval-2018 Task 10: A System for Capturing Discriminative Attributes

Abstract

Semantic difference detection attempts to capture whether a word is a discriminative attribute between two other words. For example, the discriminative feature red characterizes the first word from the (apple, banana) pair, but not the second. Modeling semantic difference is essential for language understanding systems, as it provides useful information for identifying particular aspects of word senses. This paper describes our system implementation (the ALB system of the NLP@Unibuc team) for the 10th task of the Semaval 2018 workshop, "Capturing Discriminative Attributes". We propose a method for semantic difference detection that uses an SVM classifier with features based on co-occurrence counts and shallow semantic parsing, achieving 0.63 F1 score in the competition.

Identifying and Explaining Discriminative Attributes

“…(No expl.) 0.63 (Dumitru et al, 2018) SVM for all categories. Excluding the relative category (in which all models perform poorly), there is little variance in the overlap between the pairwise models (where the intersection between DBM and VFM is the largest for each category).…”

“…With regard to interpretability and explainability we can classify IDA approaches into three categories. Frequency-based models over textbased features, heavily relying on textual features and frequency-based methods (Gamallo, 2018;González et al, 2018) ; ML over Textual features (Dumitru et al, 2018;Sommerauer et al, 2018;King et al, 2018;Mao et al, 2018) and ML over dense vectors and textual features (Brychcín et al, 2018;Attia et al, 2018;Dumitru et al, 2018;Arroyo-Fernández et al, 2018;Speer and Lowry-Duda, 2018;Santus et al, 2018;Grishin, 2018;Zhou et al, 2018;Vinayan et al, 2018;Kulmizev et al, 2018;Zhang and Carpuat, 2018;Shiue et al, 2018). While the first category concentrates on models with higher interpretability, none of these models provide explanations.…”

“…(No expl.) 0.63 (Dumitru et al, 2018) SVM with word co-occurrence None 0.63 (Mao et al, 2018) CBOW and skip-gram with WordNet definitions Transp. (No expl.)…”

SEMIE: SEMantically Infused Embeddings with Enhanced Interpretability for Domain-specific Small Corpus

“…For example, the word "buckle" is a discriminative feature in the triplet ("seat belt", "tires", "buckle") that characterizes the first concept but not the second. Researchers have formulated this property as a binary classification task and proposed machine learning and similarity-based methods to evaluate the word embeddings (Zhang and Carpuat, 2018;Dumitru et al, 2018;Grishin, 2018). However, to perform these evaluations for a domain-specific small corpus, we would need a manually curated set of discriminative (positive) and non-discriminative (negative) triples, which can be costly and timeconsuming to curate.…”