Reading to learn: Constructing features from semantic abstracts

Jacob Eisenstein, James Clarke, Dan Goldwasser, Dan Roth

Research output: Contribution to conferencePaper

Abstract

Machine learning offers a range of tools for training systems from data, but these methods are only as good as the underlying representation. This paper proposes to acquire representations for machine learning by reading text written to accommodate human learning. We propose a novel form of semantic analysis called reading to learn, where the goal is to obtain a high-level semantic abstract of multiple documents in a representation that facilitates learning. We obtain this abstract through a generative model that requires no labeled data, instead leveraging repetition across multiple documents. The semantic abstract is converted into a transformed feature space for learning, resulting in improved generalization on a relational learning task.

Original languageEnglish (US)
Pages958-967
Number of pages10
StatePublished - Dec 1 2009
Event2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, Held in Conjunction with ACL-IJCNLP 2009 - Singapore, Singapore
Duration: Aug 6 2009Aug 7 2009

Other

Other2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, Held in Conjunction with ACL-IJCNLP 2009
CountrySingapore
CitySingapore
Period8/6/098/7/09

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Reading to learn: Constructing features from semantic abstracts'. Together they form a unique fingerprint.

  • Cite this

    Eisenstein, J., Clarke, J., Goldwasser, D., & Roth, D. (2009). Reading to learn: Constructing features from semantic abstracts. 958-967. Paper presented at 2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, Held in Conjunction with ACL-IJCNLP 2009, Singapore, Singapore.