Filters








121 Hits in 1.6 sec

TimeML-Compliant Text Analysis for Temporal Reasoning

Branimir Boguraev, Rie Kubota Ando
2005 International Joint Conference on Artificial Intelligence  
We address this problem with a hybrid TimeML annotator, which uses cascaded finite-state grammars (for temporal expression analysis, shallow syntactic parsing, and feature generation) together with a machine  ...  TimeML-an emerging standard for temporal annotation as a language capturing properties and relationships among timedenoting expressions and events in text-is a good starting point for bridging the gap  ...  Unfortunately, the small size of the TimeBank corpus prevents its straightforward use as a training resource, a problem further exacerbated by the inherent complexity of TimeMLcompliant analysis.  ... 
dblp:conf/ijcai/BoguraevA05 fatcat:rjcfavayhbfjzfmzmmycuaa26q

Massively Increasing TIMEX3 Resources: A Transduction Approach [article]

Leon Derczynski and Héctor Llorens and Estela Saquete
2012 arXiv   pre-print
Using this, we evaluate our conversion process by using it as training data for an existing TimeML annotation tool, achieving a 0.87 F1 measure -- better than any system in the TempEval-2 timex recognition  ...  Automatic annotation of temporal expressions is a research challenge of great interest in the field of information extraction.  ...  Acknowledgments The authors would like to thank Lisa Ferro of the MITRE Corporation for kind help with corralling TIMEX2 resources.  ... 
arXiv:1203.5076v1 fatcat:z6i6hbonrfdx7oqqa3souz2xje

Constructing a Temporal Relation Tagged Corpus of Chinese Based on Dependency Structure Analysis

Yuchang Cheng, Masayuki Asahara, Yuji Matsumoto
2007 14th International Symposium on Temporal Representation and Reasoning (TIME'07)  
Our goal is construction of corpora to be used for a corpus-based analysis of temporal relations among events.  ...  This paper describes an annotation guideline for a temporal relation-tagged corpus of Chinese.  ...  Dependency Structure Analysis Resources TimeML is a corpus guideline of temporal information for English news articles. Table 1 lists the definition of the tags.  ... 
doi:10.1109/time.2007.47 dblp:conf/time/ChengAM07 fatcat:ehpfyp7fl5dlzkuqqvct5pfjai

KTimeML: Specification of Temporal and Event Expressions in Korean Text

Seohyun Im, Hyun-Jo You, Hayun Jang, Seungho Nam, Hyopil Shin
2009 Workshop on Asian Language Resources  
TimeML is a specification language for events and temporal expressions in text. This paper presents the problems and solutions for porting TimeML to Korean as a part of the Korean TARSQI Project.  ...  TimeML, TimeBank, and TTK (TARSQI Project) have been playing an important role in enhancement of IE, QA, and other NLP applications.  ...  This work will be a help for QA, IE, and other robust performance for Korean. In addition, KTimeML will be, hopefully, a model for porting TimeML to other agglutinative languages such as Japanese.  ... 
dblp:conf/acl-alr/ImYJNS09 fatcat:lait6m6v4fe5pk7ggcyv7pt4dy

Extracting Temporal and Causal Relations between Events [article]

Paramita Mirza
2016 arXiv   pre-print
Structured information resulting from temporal information processing is crucial for a variety of natural language processing tasks, for instance to generate timeline summarization of events from news  ...  We first develop a robust extraction component for each type of relations, i.e. temporal order and causality.  ...  Syntactic Analysis syntactic parsing Parsing means taking an input and producing some sort of linguistic structure for it.  ... 
arXiv:1604.08120v1 fatcat:fmd7z6hwyjhgphbrnc3mgpifde

From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations

Egoitz Laparra, Dongfang Xu, Steven Bethard
2018 Transactions of the Association for Computational Linguistics  
This novel schema favors machine learning approaches, as it can be viewed as a semantic parsing task.  ...  To compare predictions of systems that follow both SCATE and TimeML, we present a new scoring metric for time intervals.  ...  Acknowledgements We thank the anonymous reviewers as well as the action editor, Mona Diab, for helpful comments on an earlier draft of this paper.  ... 
doi:10.1162/tacl_a_00025 pmid:32432133 pmcid:PMC7236559 fatcat:zngqwhh5xvbu3dsnymzmdup7ee

Classifying Temporal Relations with Simple Features

Paramita Mirza, Sara Tonelli
2014 Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics  
Approaching temporal link labelling as a classification task has already been explored in several works.  ...  We find that using a simple feature set results in a better performance than using more sophisticated features based on semantic role labelling and deep semantic parsing.  ...  Our features include some basic information on the position, the attributes and the PoS tags of events and timexes, as well as other information obtained from external lexical resources such as a list  ... 
doi:10.3115/v1/e14-1033 dblp:conf/eacl/MirzaT14 fatcat:ocu7rutoirgubja62q6wymbrzu

ISO-TimeML Event Extraction in Persian Text

Yadollah Yaghoobzadeh, Gholamreza Ghassem-Sani, Seyed Abolghasem Mirroshandel, Mahbaneh Eshaghzadeh
2012 International Conference on Computational Linguistics  
For this purpose, a corpus of events has been built based on a specific version of ISO-TimeML for Persian.  ...  Existing methods developed for this task are restricted to limited number of languages, and for many other languages including Persian, there has not been any effort yet.  ...  For adjectives, the cases that have been annotated in TimeBank are considered as events. The heads of the predicative complements are also regarded as events.  ... 
dblp:conf/coling/YaghoobzadehGME12 fatcat:koaqbetogzdr5p3xptwt4glht4

Supervised Machine Learning Techniques to Detect TimeML Events in French and English [chapter]

Béatrice Arnulphy, Vincent Claveau, Xavier Tannier, Anne Vilnat
2015 Lecture Notes in Computer Science  
Through the TimeML specifications and TempEval challenges, it has received some attention in recent years. However, no reference result is available for French.  ...  These systems are evaluated on French corpora and compared with state-of-the-art methods on English. The very good results obtained on both languages validate our approach.  ...  The TimeML annotated corpora are called TimeBank: TimeBank 1.2 [19] for English, FR-TimeBank [7] for French, and so on.  ... 
doi:10.1007/978-3-319-19581-0_2 fatcat:yxfbhvmaprc7xanrp4jz3vum3a

An Analysis of Causality between Events and its Relation to Temporal Information

Paramita Mirza, Sara Tonelli
2014 International Conference on Computational Linguistics  
In this work we present an annotation framework to capture causality between events, inspired by TimeML, and a language resource covering both temporal and causal relations.  ...  The evaluation and analysis of the system's performance provides an insight into explicit causality in text and the connection between temporal and causal relations.  ...  We also thank Rachele Sprugnoli and Manuela Speranza for their contribution in defining the annotation guidelines.  ... 
dblp:conf/coling/MirzaT14 fatcat:l5g33elqu5grli35jzmm2nrskq

CATENA: CAusal and TEmporal relation extraction from NAtural language texts

Paramita Mirza, Sara Tonelli
2016 International Conference on Computational Linguistics  
We evaluate the performance of each sieve, showing that the rule-based, the machinelearned and the reasoning components all contribute to achieving state-of-the-art performance on TempEval-3 and TimeBank-Dense  ...  We present CATENA, a sieve-based system to perform temporal and causal relation extraction and classification from English texts, exploiting the interaction between the temporal and the causal model.  ...  For TimeBank-Dense evaluation, the test set is a subset of TimeBank, so we exclude the 9 test documents from Causal-TimeBank during training.  ... 
dblp:conf/coling/MirzaT16 fatcat:qxlrgypnr5d7hazgy6ykakqmba

Automatically Generated Noun Lexicons for Event Extraction [chapter]

Béatrice Arnulphy, Xavier Tannier, Anne Vilnat
2012 Lecture Notes in Computer Science  
In this paper, we propose a method for creating automatically weighted lexicons of event names.  ...  We also propose a study concerning the necessary size of corpus to be used for creating a valuable lexicon.  ...  is as good as for a whole-corpuslearned lexicon.  ... 
doi:10.1007/978-3-642-28601-8_19 fatcat:2pldskyrtfdgnh5ch55lqegjqe

Using Voting Approach for Event Extraction and Event-DCT, Event-Time Relation Identification

Anup Kumar Kolyal, Asif Ekbal, Sivaji Bandyopadhyay
2013 International Journal of Artificial Intelligence & Applications  
Then, the proposal of a voted approach for event extraction, event-DCT and event-time relation identification by combining the supervised classifiers such as Conditional Random Field (CRF) and Support  ...  Temporal information extraction is a popular and interesting research field in the area of Natural Language Processing (NLP) applications such as summarization, question answering (QA) and information  ...  ACKNOWLEDGEMENTS The work is partially supported by a grant from English to Indian language Machine Translation(EILMT) funded by Department of Information and Technology (DIT), Government of India.  ... 
doi:10.5121/ijaia.2013.4106 fatcat:jt7aeki4kvfsvl7igodzuoiz4q

Task-Oriented Extraction of Temporal Information: The Case of Clinical Narratives

R. Gaizauskas, H. Harkema, M. Hepple, A. Setzer
2006 Thirteenth International Symposium on Temporal Representation and Reasoning (TIME'06)  
annotation schemes such as TimeML.  ...  Overall scores of precision 73.83% and recall 58.70% are promising for a simple baseline approach and suggest that extracting only a restricted subset of the temporal information available in a text may  ...  Acknowledgements This research has been done as part of the CLEF-Services project sponsored by the UK Medical Research Council and has been carried out in collaboration with University of Manchester, University  ... 
doi:10.1109/time.2006.27 dblp:conf/time/GaizauskasHHS06 fatcat:x7fjlgh7aze4phvw25wpcyjal4

Reasoning in Legal Text Documents with Extracted Event Information

Venkateswrlu Naik. M, Vanitha Guda, Inturi Srujana
2011 International Journal of Computer Applications  
Extracting Events, Time Expressions and Named Entities from Legal text is fundamental aspect for deep language understanding and key to various applications such as Temporal Reasoning in Criminal Documents  ...  , Case decisions(Intellectual property and crime) for details, Case Based Reasoning, Ordering of Cases according to their Time lines, Determining Relevancy between Precedent cases and Current cases, Temporal  ...  As for event attributes, TIMEML use seven abstract event classes. order of subdivisions of items in bullet and numbered lists may be presented as follows: Occurrence: die, crash, build;2) State: on board  ... 
doi:10.5120/3402-4742 fatcat:2fs573tbu5hirnniyjkwv4ia3a
« Previous Showing results 1 — 15 out of 121 results