• Publications
  • Influence
Inner Attention based Recurrent Neural Networks for Answer Selection
TLDR
We present three new RNN models that add attention information before RNN hidden representation, which shows advantage in representing sentence and achieves stateof-art results in answer selection task. Expand
  • 159
  • 28
  • PDF
Conditional Generative Adversarial Networks for Commonsense Machine Comprehension
TLDR
We proposed a Conditional GANs (CGANs) in which the generator is conditioned by the context and achieve state-of-the-art results in commonsense story reading comprehension task. Expand
  • 27
  • 2
  • PDF
Employing External Rich Knowledge for Machine Comprehension
TLDR
We build an attention-based recurrent neural network model, train it with the help of external knowledge which is semantically relevant to machine comprehension, and achieves a new state-of-the-art result. Expand
  • 14
  • 2
  • PDF
Sogou Machine Reading Comprehension Toolkit
TLDR
We present a Sogou Machine Reading Comprehension (SMRC) toolkit that can be used to provide the fast and efficient development of modern machine comprehension models, including both published models and original prototypes. Expand
  • 3
  • 1
  • PDF
Document Gated Reader for Open-Domain Question Answering
TLDR
We propose a document-level gate operation to determine the question-document relevance and embed it into the answer generation process, and optimize it with the global normalization objective. Expand
  • 3
Neural Question Generation with Answer Pivot
TLDR
The answer-agnostic NQG methods reduce the bias towards named entities and increasing the model's degrees of freedom, but sometimes result in generating unanswerable questions which are not valuable for the subsequent machine reading comprehension system. Expand
  • 2
  • PDF
Deep Semantic Hashing with Multi-Adversarial Training
TLDR
In this paper, to generate desirable binary codes, we introduce two adversarial training procedures to the hashing process. Expand
  • 2
  • PDF
ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion
TLDR
This paper presents the ReCO, a human-curated Chinese Reading Comprehension dataset on opinion based queries issued to commercial search engine. Expand
  • 2
  • PDF
SenSeNet: Neural Keyphrase Generation with Document Structure
TLDR
We propose a new method called Sentence Selective Network (SenSeNet) to incorporate the meta-sentence inductive bias into KG. Expand
Unsupervised Story Comprehension with Hierarchical Encoder-Decoder
TLDR
In this paper, we propose an unsupervised sequence-to-sequence method for story reading comprehension, we only adopt the unlabeled story and directly model the context-target inference probability. Expand