Bilateral Multi-Perspective Matching for Natural Language Sentences

13 Feb 2017  ·  Zhiguo Wang, Wael Hamza, Radu Florian ·

Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching... In this work, we propose a bilateral multi-perspective matching (BiMPM) model under the "matching-aggregation" framework. Given two sentences $P$ and $Q$, our model first encodes them with a BiLSTM encoder. Next, we match the two encoded sentences in two directions $P \rightarrow Q$ and $P \leftarrow Q$. In each matching direction, each time step of one sentence is matched against all time-steps of the other sentence from multiple perspectives. Then, another BiLSTM layer is utilized to aggregate the matching results into a fix-length matching vector. Finally, based on the matching vector, the decision is made through a fully connected layer. We evaluate our model on three tasks: paraphrase identification, natural language inference and answer sentence selection. Experimental results on standard benchmark datasets show that our model achieves the state-of-the-art performance on all tasks. read more

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Paraphrase Identification Quora Question Pairs BiMPM Accuracy 88.17 # 14
Natural Language Inference SNLI BiMPM % Test Accuracy 87.5 # 38
% Train Accuracy 90.9 # 39
Parameters 1.6m # 3
Natural Language Inference SNLI BiMPM Ensemble % Test Accuracy 88.8 # 22
% Train Accuracy 93.2 # 23
Parameters 6.4m # 3