UMD-TTIC-UW at SemEval-2016 Task 1: Attention-Based Multi-Perspective Convolutional Neural Networks for Textual Similarity Measurement

Citations Over TimeTop 10% of 2016 papers

Abstract

We describe an attention-based convolutional neural network for the English semantic textual similarity (STS) task in the SemEval2016 competition (Agirre et al., 2016). We develop an attention-based input interaction layer and incorporate it into our multiperspective convolutional neural network (He et al., 2015), using the PARAGRAM-PHRASE word embeddings (Wieting et al., 2016) trained on paraphrase pairs. Without using any sparse features, our final model outperforms the winning entry in STS2015 when evaluated on the STS2015 data.

Related Papers

• Enlarging Paraphrase Collections through Generalization and Instantiation(2012)
• Finnish Paraphrase Corpus(2021)
• → Chinese Paraphrase Dataset and Detection(2021)2 cited
• Paraphrase extraction from interactive Q&A communities(2012)
• → A Study on the Application of Paraphrase Strategy in the Translation from Chinese to English(2018)1 cited