147 citations · 1k across the 56 of their papers we have counts for
11 papers · 1 filter
Self-Explaining Structures Improve NLP Models
Zijun Sun, Chun Fan, Qinghong Han +4
Existing approaches to explaining deep learning models in NLP usually suffer from two major drawbacks: (1) the main model and the explaining model are decoupled: an additional prob…
OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
Yuxian Meng, Shuhe Wang, Qinghong Han +4
When humans converse, what a speaker will say next significantly depends on what he sees. Unfortunately, existing dialogue models generate dialogue utterances only based on precedi…
Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining
Zijun Sun, Chun Fan, Xiaofei Sun +3
The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-…
Pair the Dots: Jointly Examining Training History and Test Stimuli for Model Interpretability
Yuxian Meng, Chun Fan, Zijun Sun +3
Any prediction from a model is made by a combination of learning history and test stimuli. This provides significant insights for improving model interpretability: {\it because of…
Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries
Xiaofei Sun, Zijun Sun, Yuxian Meng +2
The difficulty of generating coherent long texts lies in the fact that existing models overwhelmingly focus on predicting local words, and cannot make high level plans on what to g…
Improving Robustness and Generality of NLP Models Using Disentangled Representations
Jiawei Wu, Xiaoya Li, Xiang Ao +3
Supervised neural networks, which first map an input to a single representation , and then map to the output label , have achieved remarkable success in a wide range…
Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions
Xiaoya Li, Mingxin Zhou, Jiawei Wu +3
At the time of writing, the ongoing pandemic of coronavirus disease (COVID-19) has caused severe impacts on society, economy and people's daily lives. People constantly express the…
SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
Xiaoya Li, Yuxian Meng, Mingxin Zhou +3
While the self-attention mechanism has been widely used in a wide variety of tasks, it has the unfortunate property of a quadratic cost with respect to the input length, which make…
Non-Autoregressive Neural Dialogue Generation
Qinghong Han, Yuxian Meng, Fei Wu +1
Maximum Mutual information (MMI), which models the bidirectional dependency between responses () and contexts (), i.e., the forward probability and the backward…
LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention
Xiaoya Li, Yuxian Meng, Arianna Yuan +2
Non-autoregressive translation (NAT) models generate multiple tokens in one forward pass and is highly efficient at inference stage compared with autoregressive translation (AT) me…
Description Based Text Classification with Reinforcement Learning
Duo Chai, Wei Wu, Qinghong Han +2
The task of text classification is usually divided into two stages: {\it text feature extraction} and {\it classification}. In this standard formalization categories are merely rep…