Unsupervised Parsing for Generating Surface-Based Relation Extraction Patterns

Finding the right features and patterns for identifying relations in natural language is one of the most pressing research questions for relation extraction. In this paper, we compare patterns based on supervised and unsupervised syntactic parsing and present a simple method for extracting surface patterns from a parsed training set. Results show that the use of surfacebased patterns not only increases extraction speed, but also improves the quality of the extracted relations. We find that, in this setting, unsupervised parsing, besides requiring less resources, compares favorably in terms of extraction quality.

• Publication year

  2014

• Venue

  Conference of the European Chapter of the Association for Computational Linguistics

• Publication date

  2014-04-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/v1/E14-4020
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Unsupervised Methods for Determining Object and Relation Synonyms on the Web

  2014cited by this paper
• A survey of noise reduction methods for distant supervision

  2013influential reference
• Multilingual Joint Parsing of Syntactic and Semantic Dependencies with a Latent Variable Model

  2013cited by this paper
• Pattern Learning for Relation Extraction with a Hierarchical Topic Model

  2012cited by this paper
• New York University 2012 System for KBP Slot Filling

  2012cited by this paper
• Unsupervised Bayesian Lexicalized Dependency Grammar Induction

  2012cited by this paper
• Generalizing from Freebase and Patterns using Cluster-Based Distant Supervision for TAC KBP Slotfilling 2012

  2012cited by this paper
• Overview of the TAC 2010 Knowledge Base Population Track

  2010cited by this paper
• Distant supervision for relation extraction without labeled data

  2009influential reference
• Unsupervised Semantic Parsing

  2009cited by this paper
• Shared Logistic Normal Distributions for Soft Parameter Tying in Unsupervised Grammar Induction

  2009cited by this paper
• Automatic Selection of High Quality Parses Created By a Fully Unsupervised Parser

  2009cited by this paper
• Open Information Extraction from the Web

  2007cited by this paper
• MaltParser: A language-independent system for data-driven dependency parsing

  2007influential reference
• A Composite Kernel to Extract Relations between Entities with Both Flat and Structured Features

  2006cited by this paper
• The unsupervised learning of natural language structure

  2005cited by this paper
• A Shortest Path Dependency Kernel for Relation Extraction

  2005cited by this paper
• Learning Syntactic Patterns for Automatic Hypernym Discovery

  2004cited by this paper
• Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency

  2004cited by this paper
• An Efficient Algorithm for Projective Dependency Parsing

  2003cited by this paper
• DIRT – Discovery of Inference Rules from Text

  2001cited by this paper
• DIRT @SBT@discovery of inference rules from text

  2001cited by this paper
• Building a Large Annotated Corpus of English: The Penn Treebank

  1993cited by this paper

• Effective distant supervision for end-to-end knowledge base population systems

  2014cites this paper