Open AccessProceedings Article
TimeBank-Driven TimeML Analysis
Branimir Boguraev,Rie Kubota Ando +1 more
- pp 0
Reads0
Chats0
TLDR
The design, implementation, and implementation of an automatic TimeML-compliant annotator, trained on TimeBank, and deploying a hybrid analytical strategy of mixing aggressive finite- state processing over linguistic annotations with a state-of-the-art learning technique capable of leveraging large amounts of unan- notated data are discussed.Abstract:
The design of TimeML as an expressive language for temporal information brings promises, and challenges; in particular, its representa- tional properties raise the bar for traditional information extraction meth- ods applied to the task of text-to-TimeML analysis. A reference corpus, such as TimeBank, is an invaluable asset in this situation; however, certain characteristics of TimeBank—size and consistency, primarily—present chal- lenges of their own. We discuss the design, implementation, and perfor- mance of an automatic TimeML-compliant annotator, trained on TimeBank, and deploying a hybrid analytical strategy of mixing aggressive finite- state processing over linguistic annotations with a state-of-the-art ma- chine learning technique capable of leveraging large amounts of unan- notated data. The results we report are encouraging in the light of a close analysis of TimeBank; at the same time they are indicative of the need for more infrastructure work, especially in the direction of creating a larger and more robust reference corpus. 1read more
Citations
More filters
Journal ArticleDOI
Multilingual and cross-domain temporal tagging
Jannik Strötgen,Michael Gertz +1 more
TL;DR: The authors' publicly available temporal tagger HeidelTime is presented, which is easily extensible to further languages due to its strict separation of source code and language resources like patterns and rules.
Journal ArticleDOI
Dense Event Ordering with a Multi-Pass Architecture
TL;DR: New experiments on strongly connected event graphs that contain ∼10 times more relations per document than the TimeBank are presented and a shift away from the single learner to a sieve-based architecture that naturally blends multiple learners into a precision-ranked cascade of sieves is described.
Proceedings ArticleDOI
Learning Semantic Links from a Corpus of Parallel Temporal and Causal Relations
Steven Bethard,James Martin +1 more
TL;DR: This work annotated 1000 conjoined event pairs and trained machine learning models using features derived from WordNet and the Google N-gram corpus, and they outperformed a variety of baselines, suggesting that additional data will improve performance, and that temporal information is crucial to causal relation identification.
Proceedings ArticleDOI
CU-TMP: Temporal Relation Classification Using Syntactic and Semantic Features
Steven Bethard,James Martin +1 more
TL;DR: A variety of syntactically and semantically motivated features are introduced, including temporal-logic-based features derived from running the Task B system on the Task A and C data, to approach the temporal relation identification tasks of TempEval 2007 as pair-wise classification tasks.
Proceedings Article
Towards Temporal Relation Discovery from the Clinical Narrative
Guergana Savova,Steven Bethard,Will Styler,James Martin,Martha Palmer,James J. Masanz,Wayne H. Ward +6 more
TL;DR: This paper evaluates enabling methods from the general natural language processing domain - deep parsing and semantic role labeling in predicate-argument structures - to explore their portability to the clinical domain and develops an annotation schema for temporal relations based on TimeML.
References
More filters
TimeML: Robust Specification of Event and Temporal Expressions in Text
James Pustejovsky,José M. Castaño,Robert Ingria,Roser Saurí,Robert Gaizauskas,Andrea Setzer,Graham Katz,Dragomir R. Radev +7 more
TL;DR: TimeML is described, 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 demonstrated for a delayed (underspecified) interpretation of partially determined temporal expressions.
Proceedings ArticleDOI
Named entity recognition through classifier combination
TL;DR: A classifier-combination experimental framework for named entity recognition in which four diverse classifiers (robust linear classifier, maximum entropy, transformation-based learning, and hidden Markov model) are combined under different conditions is presented.
Journal ArticleDOI
An ontology of time for the semantic web
Jerry R. Hobbs,Feng Pan +1 more
TL;DR: An ontology of time is being developed for describing the temporal content of Web pages and the temporal properties of Web services, which covers topological properties of instants and intervals, measures of duration, and the meanings of clock and calendar terms.
Proceedings ArticleDOI
Anaphora for everyone: pronominal anaphora resoluation without a parser
TL;DR: Evaluation of the results of the implementation demonstrates that accurate anaphora resolution can be realized within natural language processing frameworks which do not---or cannot--- employ robust and reliable parsing components.
ReportDOI
A Statistical Model for Multilingual Entity Detection and Tracking
Radu Florian,Hany Hassan,Abraham Ittycheriah,Hongyan Jing,Nanda Kambhatla,Xiaoqiang Luo,H. Nicolov,Salim Roukos +7 more
TL;DR: This paper presents a statistical language-independent framework for identifying and tracking named, nominal and pronominal references to entities within unrestricted text documents, and chaining them into clusters corresponding to each logical entity present in the text.