REGMAPR - Text Matching Made Easy
arXiv:1808.04343
Abstract
Text matching is a fundamental problem in natural language processing. Neural models using bidirectional LSTMs for sentence encoding and inter-sentence attention mechanisms perform remarkably well on several benchmark datasets. We propose REGMAPR - a simple and general architecture for text matching that does not use inter-sentence attention. Starting from a Siamese architecture, we augment the embeddings of the words with two features based on exact and para- phrase match between words in the two sentences. We train the model using three types of regularization on datasets for textual entailment, paraphrase detection and semantic related- ness. REGMAPR performs comparably or better than more complex neural models or models using a large number of handcrafted features. REGMAPR achieves state-of-the-art results for paraphrase detection on the SICK dataset and for textual entailment on the SNLI dataset among models that do not use inter-sentence attention.
References in corpus (10)
- A Deep Relevance Matching Model for Ad-hoc Retrieval
- Regularizing and Optimizing LSTM Language Models
- Machine Comprehension Using Match-LSTM and Answer Pointer
- Natural Language Inference over Interaction Space
- Distance-based Self-Attention Network for Natural Language Inference
- Enhancing Sentence Embedding with Generalized Pooling
- Shortcut-Stacked Sentence Encoders for Multi-Domain Inference
- Learning Semantic Textual Similarity from Conversations
- Modelling Sentence Pairs with Tree-structured Attentive Encoder
- Task-Specific Attentive Pooling of Phrase Alignments Contributes to Sentence Matching