• Publications
  • Influence
Relation Classification via Convolutional Deep Neural Network
TLDR
In this paper, we exploit a convolutional deep neural network (DNN) to extract lexical and sentence level features for relation classification. Expand
  • 1,039
  • 183
  • PDF
Learning Continuous Word Embedding with Metadata for Question Retrieval in Community Question Answering
TLDR
We propose to learn continuous word embeddings with metadata of category information within cQA pages for question retrieval. Expand
  • 149
  • 11
  • PDF
Phrase-Based Translation Model for Question Retrieval in Community Question Answer Archives
TLDR
We propose a novel phrase-based translation model for question retrieval that captures contextual information in modeling the translation of phrases as a whole. Expand
  • 140
  • 9
  • PDF
Scalable tag recommendation for software information sites
TLDR
TagMulRec is the first tool to automatically recommend tags for largescale evolving software information sites. Expand
  • 29
  • 9
  • PDF
Topic-sensitive probabilistic model for expert finding in question answer communities
TLDR
We propose a topic-sensitive probabilistic model to find experts in CQA by taking into account both the link structure and the topical similarity among users. Expand
  • 78
  • 6
  • PDF
Learning semantic representation with neural networks for community question answering retrieval
TLDR
We propose a novel approach to learn the semantic representation of queries and answers by using a neural network architecture. Expand
  • 64
  • 6
Improving Question Retrieval in Community Question Answering Using World Knowledge
TLDR
We propose a way to build a concept thesaurus based on the semantic relations extracted from the world knowledge of Wikipedia. Expand
  • 90
  • 5
  • PDF
CASIA@QALD-3: A Question Answering System over Linked Data
TLDR
We present a question answering system (CASIA) over Linked Data (DBpedia), which focuses on construct a bridge between the users and the Linked data. Expand
  • 27
  • 5
  • PDF
Exploiting Web-Derived Selectional Preference to Improve Statistical Dependency Parsing
TLDR
In this paper, we present a novel approach which incorporates the web-derived selectional preferences to improve statistical dependency parsing. Expand
  • 48
  • 4
  • PDF
Cross-domain sentiment classification via topical correspondence transfer
TLDR
We propose a novel algorithm, called topical correspondence transfer (TCT) for cross-domain sentiment classification. Expand
  • 27
  • 4