Zhiguo Wang

Bilateral Multi-Perspective Matching for Natural Language Sentences

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

Coverage Embedding Models for Neural Machine Translation.

P

Vocabulary Manipulation for Neural Machine Translation

and

Joint POS Tagging and Transition-based Constituent Parsing in Chinese with Non-local Features

Q

Supervised Attentions for Neural Machine Translation

, our model first encodes them with a BiLSTM encoder. Next, we match the two encoded sentences in two directions

Semi-supervised Clustering for Short Text via Deep Representation Learning

P rightarrow Q

Feature Optimization for Constituent Parsing via Neural Networks

and

AMR-to-text generation as a Traveling Salesman Problem

P leftarrow Q

AMR-to-text Generation with Synchronous Node Replacement Grammar

. 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.

Sense Embedding Learning for Word Sense Induction

In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT. For each source word, our model starts with a full coverage embedding vector to track the coverage status, and then keeps updating it with neural networks as the translation goes. Experiments on the large-scale Chinese-to-English task show that our enhanced model improves the translation quality significantly on various test sets over the strong large vocabulary NMT system.