Kai Sun

We present DREAM, the first dialogue-based multiple-choice reading comprehension data set. Expand

We propose three general strategies aimed to improve non-extractive machine reading comprehension (MRC): (i) BACK AND FORTH READING that considers both the original and reverse order of an input sequence, (ii) HIGHLIGHTING, which adds a trainable embedding to the text embedding of tokens that are relevant to the question and candidate answer, and (iii) SELF-ASSESSMENT that generates practice questions and candidate answers directly from the text. Expand

We focus on extracting evidence sentences that can explain or support the answers of multiple-choice MRC tasks, where the majority of answer options cannot be directly extracted from reference documents. Expand

A novel framework is proposed to formulate rule-based models in a general way. Expand

We present the first collection of Challenging Chinese machine reading Comprehension datasets (C^3) collected from language and professional certification exams, which contains 13,924 documents and their associated 23,990 multiple-choice questions. Expand

In this paper we describe the 2017 system of the CornMich team for the TAC Belief and Sentiment (BeSt) task for Chinese. Expand

This paper describes the SJTU system submitted to the second Dialogue State Tracking Challenge in detail. Expand

In this paper, a novel hybrid framework, constrained Markov Bayesian polynomial (CMBP), is proposed to formulate rule-based DST in a general way and allow data-driven rule generation. Expand

We introduce CLUE, a Chinese Language Understanding Evaluation benchmark that contains eight different natural language understanding tasks, including single-sentence classification, sentence pair classification, and machine reading comprehension. Expand

We present the first human-annotated dialogue-based relation extraction dataset DialogRE, aiming to support the prediction of relation(s) between two arguments that appear in a dialogue. Expand