• Publications
  • Influence
Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering
TLDR
This paper describes a novel hierarchical attention network for reading comprehension style question answering, which aims to answer questions for a given narrative paragraph. Expand
  • 95
  • 13
  • PDF
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
TLDR
We introduce a new type of contextual representation, StructBERT, which incorporates language structures into BERT pre-training by proposing two novel linearization strategies. Expand
  • 40
  • 7
  • PDF
Session-aware Information Embedding for E-commerce Product Recommendation
TLDR
We propose a list-wise deep neural network based architecture to model the limited user behaviors within each session, which incorporates different kinds of user search behaviors such as clicks and views. Expand
  • 25
  • 4
  • PDF
A Deep Cascade Model for Multi-Document Reading Comprehension
TLDR
We develop a novel deep cascade learning model, which progressively evolves from the documentlevel and paragraph-level ranking of candidate texts to more precise answer extraction with machine reading comprehension. Expand
  • 19
  • 2
  • PDF
Incorporating External Knowledge into Machine Reading for Generative Question Answering
TLDR
We propose a new neural model, Knowledge-Enriched Answer Generator (KEAG), which is able to compose a natural answer by exploiting and aggregating evidence from all four information sources available: question, passage, vocabulary and knowledge. Expand
  • 12
  • 2
  • PDF
Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning
TLDR
This paper focuses on how to take advantage of external relational knowledge to improve machine reading comprehension (MRC) with multi task learning. Expand
  • 9
  • 1
  • PDF
Ensemble Methods for Personalized E-Commerce Search Challenge at CIKM Cup 2016
TLDR
This paper describes our solution to tackle the challenge of personalized e-commerce search at CIKM Cup 2016. Expand
  • 11
  • 1
  • PDF
Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
TLDR
The ability of semantic reasoning over the sentence pair is essential for many natural language understanding tasks, e.g., natural language inference and machine reading comprehension. Expand
  • 4
  • 1
  • PDF
Optimizing Seed Inputs in Fuzzing with Machine Learning
  • L. Cheng, Y. Zhang, +4 authors H. Li
  • Computer Science
  • IEEE/ACM 41st International Conference on…
  • 7 February 2019
TLDR
We present a machine learning based framework to improve the quality of seed inputs for fuzzing programs that take PDF files as input, which could significantly increase the code coverage of the target program and the likelihood of detecting program crashes. Expand
  • 7
  • 1
  • PDF
Efficient P-CSCF discovery through NASS-IMS
  • Chen Wu
  • Computer Science
  • 2nd International Conference on Education…
  • 22 June 2010
TLDR
We propose a ‘nearest contact retrieval’ method based on improved quad-tree to obtain the P-CSCF in Connectivity Session Location and Repository Function of IMS and transmit it to SIP terminal by enhancing the communication interface. Expand
  • 1
  • 1