activity
20162022
most citedMachine Comprehension Using Match-LSTM and Answer Pointer

414 citations · 881 across the 23 of their papers we have counts for

collaborators
Showing 2019Show all

5 papers · 1 filter

cs.CL2019

Hierarchical Graph Network for Multi-hop Question Answering

Yuwei Fang, Siqi Sun, Zhe Gan +3

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical grap…

cs.CL2019★ 31 cited

What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?

Chenglei Si, Shuohang Wang, Min-Yen Kan +1

Multiple-Choice Reading Comprehension (MCRC) requires the model to read the passage and question, and select the correct answer among the given options. Recent state-of-the-art mod…

cs.CL2019★ 17 cited

Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks

Yi Tay, Aston Zhang, Luu Anh Tuan +5

Many state-of-the-art neural models for NLP are heavily parameterized and thus memory inefficient. This paper proposes a series of lightweight and memory efficient neural architect…

cs.CL2019★ 16 cited

Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives

Yi Tay, Shuohang Wang, Luu Anh Tuan +6

This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Point…

cs.CL2019★ 1 cited

Unsupervised Deep Structured Semantic Models for Commonsense Reasoning

Shuohang Wang, Sheng Zhang, Yelong Shen +4

Commonsense reasoning is fundamental to natural language understanding. While traditional methods rely heavily on human-crafted features and knowledge bases, we explore learning co…