Simple and Effective Text Matching with Richer Alignment Features

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.

PDF Abstract ACL 2019 PDF ACL 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering Quora Question Pairs RE2 Accuracy 89.2 % # 13
Natural Language Inference SciTail RE2 Accuracy 86.0 # 5
Natural Language Inference SNLI RE2 % Test Accuracy 88.9 # 22
% Train Accuracy 94.0 # 19
Parameters 2.8m # 3
Question Answering WikiQA RE2 MAP 0.7452 # 9
MRR 0.7618 # 9