Temporal expressions
{{Short description|Text that denote time}}
A temporal expression in a text is a sequence of tokens (words, numbers and characters) that denote time, that is express a point in time, a duration or a frequency.
Examples:
:A point in time:
He was born on6 May, 1980 .
:A duration:
The show lasted7 minutes .
:A frequency:
The pump circulates the waterevery 2 hours .
Initially, temporal expressions were considered a type of named entities and their identification was part of the named entity recognition task. Since the Automatic Content Extraction program in 2004 there has been a separate task identified and called Temporal Expression Recognition and Normalisation (TERN). Timex evaluation is now evaluated in two major temporal annotation challenges: TempEval and i2b2, both of which prefer the TimeML-level TIMEX3 standard.See [http://timeml.org/site/publications/timeMLdocs/timeml_1.2.1.html#timex3 TIMEX3 at timeml.org]
Approaches
Similarly to NER systems, temporal expression taggers have been created either using linguistic grammar-based techniques or statistical models. Hand-crafted grammar-based systems typically obtained better results, but at the cost of months of work by experienced linguists. There are many such systems available now,{{cite journal|last=Strötgen|first=Jannik|author2=Michael Gertz |title=HeidelTime: High quality rule-based extraction and normalization of temporal expressions|journal=Proceedings of the 5th International Workshop on Semantic Evaluation|year=2010|publisher=ACL}}{{cite journal|last=Llorens|first=Hector|author2=Leon Derczynski |author3=Robert Gaizauskas |author4=Estela Saquete |title=TIMEN: An Open Temporal Expression Normalisation Resource|journal=LREC|year=2012|pages=3044–3051 |publisher=ACL|url=https://aclanthology.org/L12-1015/}}{{cite journal|last=Filannino|first=Michele|author2=Gavin Brown |author3=Goran Nenadic |title=ManTIME: Temporal identification and normalization in the TempEval-3 challenge|journal=Proceedings of the 7th International Workshop on Semantic Evaluation|year=2013|publisher=ACL}} so creating a temporal expression recognizer from scratch is generally an undesirable duplication of effort. Instead, current approaches focus on novel subclasses of timex.{{cite journal|last=Brucato|first=Matteo|author2=Leon Derczynski |author3=Hector Llorens |author4=Kalina Bontcheva |author5=Christian S. Jensen |title=Recognising and Interpreting Named Temporal Expressions|journal=Proceedings of the International Conference on Recent Advances in Natural Language Processing|year=2013|publisher=ACL|url=https://aclanthology.org/R13-1015.pdf}}
Statistical systems typically require a large amount of manually annotated training data and are usually applied to the recognition task only (although there is work done using machine learning algorithms to resolve certain ambiguities in the interpretation step).See, for example, {{Harvnb|Ahn|van Rantwijk|de Rijke|2007}}{{cite journal|last=Angeli|first=Gabor|author2=Christoper Manning |author3=Daniel Jurafsky |title=Parsing time: Learning to interpret time expressions|journal=Proceedings of NAACL|year=2012|page=446|publisher=ACL|url=https://aclanthology.org/N12-1049.pdf}}
Notes
{{reflist}}
References
- {{Citation
| first1=David | last1=Ahn | author-link=David Ahn
| first2= Joris | last2=van Rantwijk | author2-link=Joris van Rantwijk
| first3= Maarten | last3=de Rijke | author3-link=Maarten de Rijke
| year=2007
| journal=Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2007)
| title=A Cascaded Machine Learning Approach to Interpreting Temporal Expressions
| publisher=ACL
| url=http://www.aclweb.org/anthology-new/N/N07/N07-1053.pdf}}
- {{Citation
| last1=Filannino | first1=Michele | author-link=Michele Filannino
| last2=Brown | first2=Gavin | author2-link=Gavin Brown (computer scientist)
| last3=Nenadic | first3=Goran | author3-link=Goran Nenadic
| year=2013
| title=ManTIME: Temporal identification and normalization in the TempEval-3 challenge
| journal=Proceedings of the 7th International Workshop on Semantic Evaluation
| publisher=ACL
| url=https://www.cs.york.ac.uk/semeval-2013/accepted/37_Paper.pdf}}
{{DEFAULTSORT:Temporal Expressions}}
Category:Computational linguistics