• Publications
  • Influence
Learning to classify short text from scientific documents using topic models with various types of knowledge
TLDR
Topic models from various types of knowledge were used for enhancing features in documents.Proposed methods are shown to outperform related work. Expand
  • 60
  • 4
Open Information Extraction
TLDR
Open Information Extraction (Open IE) systems aim to obtain relation tuples with highly scalable extraction in portable across domain by identifying a variety of relation phrases and arguments in arbitrary sentences. Expand
  • 27
  • 2
  • PDF
Self-training on refined clause patterns for relation extraction
TLDR
We use the English clause structure and clause types in an effort to generate propositions that can be deemed as extractable relations. Expand
  • 13
  • 2
  • PDF
Vietnamese Open Information Extraction
TLDR
We propose a system named vnOIE for Vietnamese open information extraction that can generate open relations and their arguments from Vietnamese text with highly scalable extraction while being domain independent. Expand
  • 6
  • 1
  • PDF
Exploiting Language Models to Classify Events from Twitter
TLDR
We firstly find the distinguishing terms between tweets in events and measure their similarities with learning language models such as ConceptNet and a latent Dirichlet allocation method. Expand
  • 11
  • PDF
Feature-enriched matrix factorization for relation extraction
TLDR
We define the problem of information extraction as a matrix completion problem where we employ the notion of universal schemas formed as a collection of patterns derived from open information extraction systems as well as additional features derived from grammatical clause patterns and statistical topic models. Expand
  • 11
  • PDF
Extracting Temporal Event Relations Based on Event Networks
TLDR
We present an unsupervised method that operates at the document level for temporal event relation extraction and compare it with several strong baselines. Expand
  • 1
Extraction of Semantic Relation Based on Feature Vector from Wikipedia
TLDR
In this paper, we propose a feature vector to extract semantic relations using dependency tree and parse tree. Expand
  • 4
A Hybrid Approach of Pattern Extraction and Semi-supervised Learning for Vietnamese Named Entity Recognition
TLDR
We propose a hybrid approach of pattern extraction and semi-supervised learning for NER in Vietnamese text. Expand
  • 5
Syntactic and Semantic Structures for Relation Extraction
TLDR
This study proposes to employ syntactic and semantic knowledge from the rich relations within a tree kernel structure for relation extraction. Expand
  • 2
  • PDF
...
1
2
...