416 citations · 1.6k across the 85 of their papers we have counts for
7 papers · 2 filters
Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System
Ze Yang, Linjun Shou, Ming Gong +2
Deep pre-training and fine-tuning models (such as BERT and OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model pa…
Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base
Tao Shen, Xiubo Geng, Tao Qin +5
We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural sema…
Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
Yibo Sun, Duyu Tang, Nan Duan +4
Neural semantic parsing has achieved impressive results in recent years, yet its success relies on the availability of large amounts of supervised data. Our goal is to learn a neur…
Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks
Haoyang Huang, Yaobo Liang, Nan Duan +4
We present Unicoder, a universal language encoder that is insensitive to different languages. Given an arbitrary NLP task, a model can be trained with Unicoder using training data…
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
Shangwen Lv, Daya Guo, Jingjing Xu +7
Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evid…
Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System
Ze Yang, Linjun Shou, Ming Gong +2
Deep pre-training and fine-tuning models (like BERT, OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model paramete…
NeuronBlocks: Building Your NLP DNN Models Like Playing Lego
Ming Gong, Linjun Shou, Wutao Lin +5
Deep Neural Networks (DNN) have been widely employed in industry to address various Natural Language Processing (NLP) tasks. However, many engineers find it a big overhead when the…