ECNU at SemEval-2018 Task 10: Evaluating Simple but Effective Features on Machine Learning Methods for Semantic Difference Detection

2018-06-01SEMEVAL 2018Unverified0· sign in to hype

Yunxiao Zhou, Man Lan, Yuanbin Wu

Unverified — Be the first to reproduce this paper.

Abstract

This paper describes the system we submitted to Task 10 (Capturing Discriminative Attributes) in SemEval 2018. Given a triple (word1, word2, attribute), this task is to predict whether it exemplifies a semantic difference or not. We design and investigate several word embedding features, PMI features and WordNet features together with supervised machine learning methods to address this task. Officially released results show that our system ranks above average.

Tasks

Attribute BIG-bench Machine Learning Feature Engineering Machine Translation Semantic Textual Similarity Word Embeddings

ECNU at SemEval-2018 Task 10: Evaluating Simple but Effective Features on Machine Learning Methods for Semantic Difference Detection

Abstract

Tasks

Reproductions