Finding temporal structure in text: Machine learning of syntactic temporal relations

Steven Bethard, James H. Martin, Sara Klingenstein

Research output: Contribution to journalArticlepeer-review

13 Scopus citations


This research proposes and evaluates a linguistically motivated approach to extracting temporal structure from text. Pairs of events in a verb-clause construction were considered, where the first event is a verb and the second event is the head of a clausal argument to that verb. All pairs of events in the TimeBank that participated in verb-clause constructions were selected and annotated with the labels BEFORE, OVERLAP and AFTER. The resulting corpus of 895 event-event temporal relations was then used to train a machine learning model. Using a combination of event-level features like tense and aspect with syntax-level features like the paths through the syntactic tree, support vector machine (SVM) models were trained which could identify new temporal relations with 89.2% accuracy. High accuracy models like these are a first step towards automatic extraction of temporal structure from text.

Original languageEnglish (US)
Pages (from-to)441-457
Number of pages17
JournalInternational Journal of Semantic Computing
Issue number4
StatePublished - Dec 1 2007
Externally publishedYes


  • Timelines
  • corpus annotation
  • machine learning
  • temporal relations

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Linguistics and Language
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence


Dive into the research topics of 'Finding temporal structure in text: Machine learning of syntactic temporal relations'. Together they form a unique fingerprint.

Cite this