Neobility at SemEval-2017 Task 1: An Attention-based Sentence Similarity Model

TL;DR

This paper presents an attention-based neural network model for cross-lingual semantic textual similarity, achieving top-tier performance in the SemEval-2017 task across multiple languages.

Contribution

It introduces a novel attention-based RNN model specifically designed for multilingual sentence similarity tasks.

Findings

Achieved top 6 performance at SemEval-2017 STS task.

Effective cross-lingual sentence similarity measurement across English, Spanish, and Arabic.

Demonstrated competitive results with neural network approaches.

Abstract

This paper describes a neural-network model which performed competitively (top 6) at the SemEval 2017 cross-lingual Semantic Textual Similarity (STS) task. Our system employs an attention-based recurrent neural network model that optimizes the sentence similarity. In this paper, we describe our participation in the multilingual STS task which measures similarity across English, Spanish, and Arabic.