45 Hits in 1.9 sec

Chinese Temporal Tagging with HeidelTime

Hui Li, Jannik Strötgen, Julian Zell, Michael Gertz
2014 Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers  
approaches for temporal tagging Our Contributions • extend Heideltime to Chinese • first publicly available Chinese temporal tagger • improvements of Chinese TempEval-2 corpus Key Features  ...  temporal tagger Temporal Taggers • focus on English • sentence, token, POS information• HeidelTime uses TreeTagger [2] • no Chinese temporal tagger is publicly available • machine learning & rule-based  ... 
doi:10.3115/v1/e14-4026 dblp:conf/eacl/LiSZG14 fatcat:qd44xuze4fhxri7yasxtgjxyk4

A Baseline Temporal Tagger for all Languages

Jannik Strötgen, Michael Gertz
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
Temporal taggers are usually developed for a certain language. Besides English, only few languages have been addressed, and only the temporal tagger HeidelTime covers several languages.  ...  In this paper, we present an approach to extend HeidelTime to all languages in the world.  ...  The resources for 200+ languages are available with HeidelTime 2.0 at http://github. com/HeidelTime/heideltime.  ... 
doi:10.18653/v1/d15-1063 dblp:conf/emnlp/StrotgenG15 fatcat:45ncsdgjxzf6phg23uigfzmupu

A pattern learning-based method for temporal expression extraction and normalization from multi-lingual heterogeneous clinical texts

Tianyong Hao, Xiaoyi Pan, Zhiying Gu, Yingying Qu, Heng Weng
2018 BMC Medical Informatics and Decision Making  
TEER was compared with six state-of-the-art baselines.  ...  Results: Based on two heterogeneous clinical text datasets: 400 actual clinical requests in English and 1459 clinical discharge summaries in Chinese.  ...  [26] proposed a Chinese temporal tagging (extraction and normalization) method by developing Chinese HeidelTime resources. Shen et al.  ... 
doi:10.1186/s12911-018-0595-9 pmid:29589563 pmcid:PMC5872502 fatcat:jjux5wwb4jfcxlz32jo6ndfpku

Multilingual and cross-domain temporal tagging

Jannik Strötgen, Michael Gertz
2012 Language Resources and Evaluation  
In this paper, we describe the challenges of temporal tagging in different domains, give an overview of existing annotated corpora, and survey existing approaches for temporal tagging.  ...  Finally, we present our publicly available temporal tagger HeidelTime, which is easily extensible to further languages due to its strict separation of source code and language resources like patterns and  ...  As annotation format, HeidelTime uses the TimeML annotation standard of TIMEX3 tags for temporal expressions.  ... 
doi:10.1007/s10579-012-9179-y fatcat:nti3o5mtw5av7b5hheyx3qnlxu

Añotador: a Temporal Tagger for Spanish

María Navas-Loro, Víctor Rodríguez-Doncel
2019 Zenodo  
Slides presented in the LKE 2019 conference about the temporal tagger Añotador, used in the TIMEX service of the Lynx Project. Also previously available in SlideShare, full paper in IOS Press.  ...  PEOPLE part: o Sentences from contributors with different backgrounds and from different Spanishspeaking countries. o Also tagged and annotated following the standards, as well as with the register of  ...  These contributors: o Short texts annotated with TimeML. o It includes additional tags in order to facilitate the evaluation of different temporal expressions, such as "Dates", "Fractions" or "False" (  ... 
doi:10.5281/zenodo.4756856 fatcat:abkntvjz2ndlnk5ecehymmsxfq

Improved Recognition and Normalisation of Polish Temporal Expressions

Jan Kocoń, Michał Marcińczuk
2017 RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning  
In this article we present the result of the recent research in the recognition and normalisation of Polish temporal expressions.  ...  The temporal information extracted from the text plays major role in many information extraction systems, like question answering, event recognition or discourse analysis.  ...  , Chinese, Russian, Croatian, Estonian and Portuguese.  ... 
doi:10.26615/978-954-452-049-6_051 dblp:conf/ranlp/KoconM17 fatcat:bb2pn3l3xjfklbr4bjcjdw4xli

Research on Temporal Expression Recognition: A Case Study of Uyghur

Alim Murat, Xiao Li, Tonghai Jiang, Yating Yang, Xi Zhou, Lei Wang
2017 Innovative Computing Information and Control Express Letters, Part B: Applications  
A CRF classifier is trained with human annotated data, and different feature sets are combined and used in order to achieve the best performance on this task.  ...  Temporal Expression Recognition (TER) was proven to help natural language tasks like information extraction and question answering to obtain a higher performance.  ...  Many work has been done and achieved the desired temporal annotation in English, Italian, Spanish, German and Chinese [1] .  ... 
doi:10.24507/icicelb.08.04.703 fatcat:yofegibcxvgx7gfpbo35xxnbba

SemEval 2018 Task 6: Parsing Time Normalizations

Egoitz Laparra, Dongfang Xu, Ahmed Elsayed, Steven Bethard, Martha Palmer
2018 Proceedings of The 12th International Workshop on Semantic Evaluation  
HEIDELTIME (Strötgen and Gertz, 2015) 6 is rule-based temporal tagger with multilingual support that includes English, German, Dutch, Vietnamese, Arabic, Spanish, Italian, French, Chinese and Russian  ...  In Track 2 (Table 4) the best system is the Character-based baseline with 0.76 F 1 , followed by HEIDELTIME with 0.74 F 1 .  ... 
doi:10.18653/v1/s18-1011 dblp:conf/semeval/LaparraXEBP18 fatcat:jflrt7v7ynb5rc4pr3see2cw2m

Mining medical related temporal information from patients' self-description

Lichao Zhu, Hangzhou Yang, Zhijun Yan
2017 International Journal of Crowd Science  
Purpose -The purpose of this paper is to develop a new method to extract medical temporal information from online health communities.  ...  Design/methodology/approach -The authors trained a conditional random-filed model for the extraction of temporal expressions.  ...  The following example shows a segmented Chinese sentence with POS tags: Segmented sentence: "In August, MRI scan showed that the shape of both legs was basically symmetrical".  ... 
doi:10.1108/ijcs-08-2017-0018 fatcat:qnex3c34zfhvno4whsyfuyapjy

Basic Building Blocks for Clinical Text Processing [chapter]

Hercules Dalianis
2018 Clinical Text Mining  
Sentence based methods such as part-of-speech tagging, syntactical analysis or parsing, semantic analysis such as named entity recognition, negation detection, relation extraction, temporal processing  ...  HeidelTime is currently available for 13 languages: English, German, Dutch, Vietnamese, Arabic, Spanish, Italian, French, Chinese, Russian, Croatian, Estonian and Portuguese.  ...  HeidelTime was adapted to English clinical text tagging in the i2b2 challenge and obtained the best results of all systems (Sun et al. 2013a).  ... 
doi:10.1007/978-3-319-78503-5_7 fatcat:pqwyc2vm2zh2vlky7bzo5da3pa

Reconstructing the Patient's Natural History from Electronic Health Records

Marjan Najafabadipour, Massimiliano Zanin, Alejandro Rodríguez-González, Maria Torrente, Beatriz Nuñez García, Juan Luis Cruz Bermudez, Mariano Provencio, Ernestina Menasalvas
2020 Zenodo  
Any intelligent system should then be able to extract medical concepts, date expressions, temporal relations and the temporal ordering of medical events from the free texts of EHRs; yet, this task is hard  ...  Although EHRs contain a large amount of valuable information about the patient's medical care, this information can only be fully understood when analyzed in a temporal context.  ...  Figure 8 . 8 Comparison of the results of our Temporal Tagger with SUTime and HeidelTime Table 1.  ... 
doi:10.5281/zenodo.3765826 fatcat:ir32plqjzfawhpach7cpzvsa7e

TNorm: A Pattern Learning Approach for Temporal Expression Classification and Normalization from Chinese Narrative Clinical Texts (Preprint)

Xiaoyi Pan, Boyu Chen, Heng Weng, Yongyi Gong, Yingying Qu
2019 JMIR Medical Informatics  
The results show that TNorm, combined with temporal expressions extraction and temporal types prediction, achieves a precision of 0.8491, a recall of 0.8328, and a F1 score of 0.8409 in temporal expressions  ...  Finally, the features are combined with the rule-based and a pattern learning-based approach to normalize the extracted temporal expressions.  ...  Li et al [28] further developed Chinese HeidelTime recourses to solve problems in Chinese temporal tagging (extraction and normalization).  ... 
doi:10.2196/17652 pmid:32716307 fatcat:3dvqvqev2rf2jopuvyf27yjlj4

Language-Independent Discriminative Parsing of Temporal Expressions

Gabor Angeli, Jakob Uszkoreit
2013 Annual Meeting of the Association for Computational Linguistics  
Temporal resolution systems are traditionally tuned to a particular language, requiring significant human effort to translate them to new languages.  ...  We present a language independent semantic parser for learning the interpretation of temporal phrases given only a corpus of utterances and the times they reference.  ...  Chinese The Chinese dataset consists of 744 training examples, and 190 test examples.  ... 
dblp:conf/acl/AngeliU13 fatcat:vbbfky3jqba2xoagevkl53n7ke

The EVALITA Dependency Parsing Task: From 2007 to 2011 [chapter]

Cristina Bosco, Alessandro Mazzei
2013 Lecture Notes in Computer Science  
The co-location with CLiC-it potentially widens the potential audience of EVALITA.  ...  Following the success of previous editions, we organized EVALITA 2014, the fourth evaluation campaign with the aim of continuing to provide a forum for the comparison and evaluation of research outcomes  ...  This research is part of the HDOMO 2.0 project founded by the National Research Centre on Aging (INRCA) in partnership with the Government of the Marche region under the action "Smart Home for Active and  ... 
doi:10.1007/978-3-642-35828-9_1 fatcat:p6dyjaxm4zbitfajtciwclwipu

A hybrid system for temporal information extraction from clinical text

Buzhou Tang, Yonghui Wu, Min Jiang, Yukun Chen, Joshua C Denny, Hua Xu
2013 JAMIA Journal of the American Medical Informatics Association  
We subsequently investigated different strategies for TLink extraction, and were able to marginally improve performance with an F-measure of 0.6943 for TLink-only track. Tang B, et al.  ...  Objective To develop a comprehensive temporal information extraction system that can identify events, temporal expressions, and their temporal relations in clinical text.  ...  TIE work began primarily with temporal representation in the 1980s.  ... 
doi:10.1136/amiajnl-2013-001635 pmid:23571849 pmcid:PMC3756274 fatcat:c2punx4abngdlp2mjveldyuriu
« Previous Showing results 1 — 15 out of 45 results