Simple and Effective Text Matching with Richer Alignment Features
This work addresses the need for efficient text matching models in applications like natural language inference and paraphrase identification, though it is incremental in its approach.
The authors tackled the problem of building a fast and effective neural model for general text matching by simplifying components while retaining key alignment features, achieving state-of-the-art performance on four benchmark datasets with much fewer parameters and at least 6 times faster inference speed.
In this paper, we present a fast and strong neural approach for general purpose text matching applications. We explore what is sufficient to build a fast and well-performed text matching model and propose to keep three key features available for inter-sequence alignment: original point-wise features, previous aligned features, and contextual features while simplifying all the remaining components. We conduct experiments on four well-studied benchmark datasets across tasks of natural language inference, paraphrase identification and answer selection. The performance of our model is on par with the state-of-the-art on all datasets with much fewer parameters and the inference speed is at least 6 times faster compared with similarly performed ones.