• Corpus ID: 2552088

TempEval-3: Evaluating Events, Time Expressions, and Temporal Relations

@article{UzZaman2012TempEval3EE,
  title={TempEval-3: Evaluating Events, Time Expressions, and Temporal Relations},
  author={Naushad UzZaman and Hector Llorens and James F. Allen and Leon Derczynski and Marc Verhagen and James Pustejovsky},
  journal={ArXiv},
  year={2012},
  volume={abs/1206.5333}
}
We describe the TempEval-3 task which is currently in preparation for the SemEval-2013 evaluation exercise. The aim of TempEval is to advance research on temporal information processing. TempEval-3 follows on from previous TempEval events, incorporating: a three-part task structure covering event, temporal expression and temporal relation extraction; a larger dataset; and single overall task quality scores. 
SemEval-2013 Task 1: TempEval-3: Evaluating Time Expressions, Events, and Temporal Relations
TLDR
The participants’ approaches, results, and the observations from the results, which may guide future research in this area are described.
FSS-TimEx for TempEval-3: Extracting Temporal Information from Text
TLDR
FSS-TimEx, a module for the recognition and normalization of temporal expressions, is described, which consists of finite-state rule cascades, using minimalistic text processing stages and simple heuristics to model the relations between events and temporal expressions.
Annotating Causality in the TempEval-3 Corpus
TLDR
This work presents some annotation guidelines to capture causality between event pairs, partly inspired by TimeML, and implements a rule-based algorithm to automatically identify explicit causal relations in the TempEval-3 corpus.
Basque Temporal Information Processing Using TimeML and HeidelTime
Temporal information is compulsory for textual comprehension, since it describes when the events in text happen or their duration. In this article temporal information and processing are presented.
Integer programming ensemble of temporal relations classifiers
TLDR
An ensemble method is presented, which reconciles the outputs of multiple heterogenous classifiers of temporal expressions and uses integer programming, a constrained optimisation technique, to improve on the best result of any individual classifier by choosing consistent temporal relations from among those recommended by multiple classifiers.
Integer Programming Ensemble of Classifiers for Temporal Relations
TLDR
An ensemble method is presented, which reconciles the output of multiple classifiers for temporal expressions, subject to consistency constraints across the whole text, with the use of integer programming to enforce the consistency constraints globally.
EusHeidelTime : Time Expression Extraction and Normalisation for Basque
Temporal information helps to organise the information in texts placing the actions and states in time. It is therefore important to identify the time points and intervals in the text, as well as
HeidelTime: Tuning English and Developing Spanish Resources for TempEval-3
TLDR
With the multilingual temporal tagger HeidelTime, this paper addressed task A, the extraction and normalization of temporal expressions for English and Spanish, and tuned Heidel time’s existing English resources and developed new Spanish resources.
ATT1: Temporal Annotation Using Big Windows and Rich Syntactic and Semantic Features
TLDR
It is shown that it is possible for models using only lexical features to approach the performance of models using rich syntactic and semantic feature sets.
ManTIME: Temporal expression identification and normalization in the TempEval-3 challenge
TLDR
It is shown that the use of WordNet-based features in the identification task negatively affects the overall performance, and that there is no statistically significant difference in using gazetteers, shallow parsing and propositional noun phrases labels on top of the morphological features.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 10 REFERENCES
SemEval-2010 Task 13: TempEval-2
Tempeval-2 comprises evaluation tasks for time expressions, events and temporal relations, the latter of which was split up in four sub tasks, motivated by the notion that smaller subtasks would make
The TempEval challenge: identifying temporal relations in text
TLDR
The TempEval task and the systems that participated in the evaluation are described and how further task decomposition can bring even more structure to the evaluation of temporal relations is described.
TRIPS and TRIOS System for TempEval-2: Extracting Temporal Information from Text
TLDR
This paper describes two systems, TRIPS and TRIOS, that were submitted to the TempEval 2 challenge, for extracting temporal information from raw text using a combination of deep semantic parsing, Markov Logic Networks and Conditional Random Field classifiers.
TIPSem (English and Spanish): Evaluating CRFs and Semantic Roles in TempEval-2
TLDR
TIPSem, a system to extract temporal information from natural language texts for English and Spanish, learns CRF models from training data and achieves the best F1 score in all the tasks.
The Specification Language TimeML
TLDR
This paper provides a description of TimeML, a rich specification language for event and temporal expressions in natural language text, developed in the context of the AQUAINT program on Question Answering Systems, and demonstrates the expressiveness of timeML for a broad range of syntactic and semantic contexts.
Temporal Evaluation
TLDR
A new method is proposed for evaluating systems that extract temporal information from text that uses temporal closure to reward relations that are equivalent but distinct, making comparison between different systems straightforward.
Merging Temporal Annotations
TLDR
This work presents automatic algorithms specifically for merging temporal annotations, evaluated merging the annotations of three state-of-the-art systems on the gold standard corpora and the correctness of the merged annotation improved over that of individual annotations and baseline merging algorithms.
The Language of Time: A Reader
TLDR
This is one of the best-structured collections I've ever had the pleasure of reading, and to call it a collection is to diminish it: This is an edited volume, with edit being used in a strong sense of the word.
The TimeBank corpus.
  • In Corpus Linguistics,
  • 2003
“ Merging Temporal Annotations . ” In Proceedings of the TIME Conference