Learning Sentence-internal Temporal Relations

Research output: Contribution to journalArticlepeer-review


In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either extract or synthesize temporal information (e.g., summarisation, question answering). Our method bypasses the need for manual coding by exploiting the presence of markers like after, which overtly signal a temporal relation. We first show that models trained on main and subordinate clauses connected with a temporal marker achieve good performance on a pseudo-disambiguation task simulating temporal inference (during testing the temporal marker is treated as unseen and the models must select the right marker from a set of possible candidates). Secondly, we assess whether the proposed approach holds promise for the semi-automatic creation of temporal annotations. Specifically, we use a model trained on noisy and approximate data (i.e., main and subordinate clauses) to predict intra-sentential relations present in TimeBank, a corpus annotated rich temporal information. Our experiments compare and contrast several probabilistic models differing in their feature space, Linguistic assumptions and data requirements. We evaluate performance against gold standard corpora and also against human subjects.
Original languageEnglish
Pages (from-to)85-117
Number of pages33
Journal Journal of Artificial Intelligence Research
Publication statusPublished - 2006


Dive into the research topics of 'Learning Sentence-internal Temporal Relations'. Together they form a unique fingerprint.

Cite this