Abstract
In this paper we present a previously unexplored approach to recognizing the textual extent of temporal expressions. Based on the observation that temporal expressions are syntactic constituents, we use functional dependency relations between tokens in a sentence to determine which words in addition to a trigger word belong to the extent of the expression. This method is particularly attractive for the recognition of expressions with complex syntactic structure, for which state-of-the-art pattern-based taggers are not effective.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Our review of the literature identified 27 temporal expression tagging systems, of which 19 are rule-based.
- 2.
We use the notation head: \(>\) child to represent a dependency.
- 3.
- 4.
- 5.
- 6.
We used the Penn Treebank tokenizer with some minor modifications (e.g. to not break numbers like 3,000 into separate tokens).
- 7.
See corpus LDC2006T06 in the LDC catalogue.
- 8.
Note that restricting years in this way damages performance on WikiWars, which also contains bare year references to earlier periods.
- 9.
Growing the extent may impact the scoring of the detection task if the new extents impact the matching of system and gold standard annotations and, in consequence, the number of detected, missing, or spurious expressions.
- 10.
The ACE corpus contains a number of documents with automatically transcribed speech, weblogs entries and UseNet discussions; these genres are challenging to parse well.
- 11.
In the preparation of the WW-Events dataset we did not exactly follow the semantic properties of the definition of event-based expressions: strictly-speaking these are only those expressions which in order to be interpreted require the time of the event which they mention. It really depends on the context whether the eventually of sightseeing in four days of sightseeing is discriminative of the period’s temporal location or not. What we care about in this experiment are the expressions with syntactically complex extents and to simplify things we will just refer to all of them as event-based.
- 12.
We used the web demo of the tagger at http://gplsi.dlsi.ua.es/~stela/TERSEO.
- 13.
However, as we discussed earlier, applying the syntax-based method to these triggers did not improve the overall results, because while some expressions obtain the correct extents, other are damaged by including tokens from outside the correct extent because of parsing errors.
References
Ferro, L., Gerber, L., Mani, I., Sundheim, B., Wilson, G.: TIDES 2005 Standard for the Annotation of Temporal Expressions. Technical report, MITRE (2005)
Ahn, D., Adafre, S.F., de Rijke, M.: Extracting temporal information from open domain text: a comparative exploration. In: Proceedings of the 5th Dutch-Belgian Information Retrieval Workshop, Delft, The Netherlands, March 2005
Hacioglu, K., Chen, Y., Douglas, B.: Automatic time expression labeling for English and Chinese text. In: Gelbukh, A. (ed.) CICLing 2005. LNCS, vol. 3406, pp. 548–559. Springer, Heidelberg (2005)
Ahn, D., van Rantwijk, J., de Rijke, M.: A cascaded machine learning approach to interpreting temporal expressions. In: Proceedings of HLT: The Annual Conference of the North American Chapter of the ACL, Rochester, NY, USA (2007)
de Marneffe, M.C., MacCartney, B., Manning, C.D.: Generating typed dependency parses from phrase structure parses. In: Proceedings of the IEEE/ACL 2006 Workshop on Spoken Language Technology (2006)
Clark, S., Curran, J.R.: Wide-coverage efficient statistical parsing with CCG and log-linear models. Comput. Linguist. 33(4), 493–552 (2007)
Mazur, P., Dale, R.: WikiWars: a new corpus for research on temporal expressions. In: Proceedings of the Conference on Empirical Methods in NLP, pp. 913–922 (2010)
Mazur, P., Dale, R.: The DANTE temporal expression Tagger. In: Vetulani, Z. (ed.) Proceedings of the 3rd Language and Technology Conference, Poznan, Poland (2007)
Saquete, E.: Temporal expression recognition and resolution applied to event ordering. Ph.D. thesis, Departamento de Lenguages y Sistemas Informaticos, Univ. de Alicante (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Mazur, P., Dale, R. (2014). Temporal Expression Recognition Using Dependency Trees. In: Vetulani, Z., Mariani, J. (eds) Human Language Technology Challenges for Computer Science and Linguistics. LTC 2011. Lecture Notes in Computer Science(), vol 8387. Springer, Cham. https://doi.org/10.1007/978-3-319-08958-4_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-08958-4_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08957-7
Online ISBN: 978-3-319-08958-4
eBook Packages: Computer ScienceComputer Science (R0)