Neural Paraphrase Identification of Questions with Noisy Pretraining

2017/04/15 by Gaurav Singh Tomar, Thyago Duque, Tomar, Gaurav Singh +7
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL

paper · pdf · doi:10.48550/arxiv.1704.04565

arxiv created 2017/08/20 · arxiv updated 2017/08/22

Abstract

We present a solution to the problem of paraphrase identification of questions. We focus on a recent dataset of question pairs annotated with binary paraphrase labels and show that a variant of the decomposable attention model (Parikh et al., 2016) results in accurate performance on this task, while being far simpler than many competing neural architectures. Furthermore, when the model is pretrained on a noisy dataset of automatically collected question paraphrases, it obtains the best reported performance on the dataset.

Related

• Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering
• Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification
• Discriminative Phrase Embedding for Paraphrase Identification
• Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
• Neural Paraphrase Generation with Stacked Residual LSTM Networks