39 citations · 307 across the 48 of their papers we have counts for
7 papers · 2 filters
Generating Diverse Translation by Manipulating Multi-Head Attention
Zewei Sun, Shujian Huang, Hao-Ran Wei +2
Transformer model has been widely used on machine translation tasks and obtained state-of-the-art results. In this paper, we report an interesting phenomenon in its encoder-decoder…
Multi-Perspective Inferrer: Reasoning Sentences Relationship from Holistic Perspective
Zhen Cheng, Zaixiang Zheng, Xin-Yu Dai +2
Natural Language Inference (NLI) aims to determine the logic relationships (i.e., entailment, neutral and contradiction) between a pair of premise and hypothesis. Recently, the ali…
A Reinforced Generation of Adversarial Examples for Neural Machine Translation
Wei Zou, Shujian Huang, Jun Xie +2
Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this systems-fathoming how a…
Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation
Huiyun Yang, Shujian Huang, Xinyu Dai +1
In sequence labeling, previous domain adaptation methods focus on the adaptation from the source domain to the entire target domain without considering the diversity of individual…
GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level
Zixian Huang, Yulin Shen, Xiao Li +5
Scenario-based question answering (SQA) has attracted increasing research attention. It typically requires retrieving and integrating knowledge from multiple sources, and applying…
Generating Sentences from Disentangled Syntactic and Semantic Spaces
Yu Bao, Hao Zhou, Shujian Huang +5
Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous lat…
Dynamic Past and Future for Neural Machine Translation
Zaixiang Zheng, Shujian Huang, Zhaopeng Tu +2
Previous studies have shown that neural machine translation (NMT) models can benefit from explicitly modeling translated (Past) and untranslated (Future) to groups of translated an…