Bilateral Multi-Perspective Matching for Natural Language Sentences

Code

• github.com/TieDanCuihua/Bilateral-Multi-Perspective-Matching-for-Natural-Language-Sentences
  tf★ 0
• github.com/galsang/BIMPM-pytorch
  pytorch★ 0
• github.com/gprateek-iitk/Quora-question-pair-matching
  tf★ 0
• github.com/zhiguowang/BiMPM
  tf★ 0
• github.com/meghu2791/DeepLearningModels
  pytorch★ 0
• github.com/MariBax/Paraphrase-Identification
  tf★ 0
• github.com/Elvirasun28/quora-question-duplicate
  tf★ 0
• github.com/vaibhav4595/BiMPM_PyTorch
  pytorch★ 0
• github.com/google-research-datasets/paws
  none★ 0
• github.com/kunj17/keras-quora-question-pair
  tf★ 0

Abstract

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 Q and P 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.

Tasks

Benchmark Results

Reproductions