A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
A Spatial‐Temporal Model for Event Detection in Social Media
2020
Procedia Computer Science
Preserved Fulltext
We propose a review of the best models and techniques applied for social media data processing to formalize a novel theory of action and time. ...
Moreover, a wide variety of applications, such as social network data, need to be done to study spatiotemporal patterns. ...
The available corpus annotated in TimeML standard are numerous (e.g. TimeBank 1.2 and TimeBank 1.1) [13; 14] . ...
doi:10.1016/j.procs.2020.08.056
pmid:33042295
pmcid:PMC7531980
fatcat:5ceuscqcszhshdfmseugbdmjs4
Temporal data representation, normalization, extraction, and reasoning: A review from clinical domain
2016
Computer Methods and Programs in Biomedicine
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Results-the main findings of this review is revealing the importance of time processing not only in constructing timelines and clinical decision support systems but also as a vital component of EHR data ...
Health Level Seven [54] [55] [56] is an international organization developing standards to provide a comprehensive frameworks for the exchange, integration, sharing, and retrieval of Madkour et al. ...
The TimeML specification has been illustrated and proven for the first time using TimeBank [64] , an English corpus of 186 news articles. ...
doi:10.1016/j.cmpb.2016.02.007
pmid:27040831
pmcid:PMC4837648
fatcat:a75g25csqzdvlkfusbbgwmxigq
TimeBank-Driven TimeML Analysis
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
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 ...
A reference corpus, such as TimeBank, is an invaluable asset in this situation; however, certain characteristics of TimeBank-size and consistency, primarily-present challenges of their own. ...
to create a sizable TimeBank for the use by the larger NLP community. ...
fatcat:onpta37jtvdrvm2omx7a3gn4zm
The EVALITA Dependency Parsing Task: From 2007 to 2011
[chapter]
2013
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
establish a reference forum for research on Computational Linguistics of the Italian community with contributions from a wide range of disciplines going from Computational Linguistics, Linguistics and ...
EVALITA's shared tasks are aimed at contributing to the development and dissemination of natural language resources and technologies by proposing a shared context for training and evaluation. ...
This work is partially supported by a public grant overseen by the French National Research Agency (ANR) as part of the progam "Investissements d'Avenir" (reference: ANR-10-LABX-0083). ...
doi:10.1007/978-3-642-35828-9_1
fatcat:p6dyjaxm4zbitfajtciwclwipu
2003 AAAI Spring Symposium Series
2003
The AI Magazine
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Systems can leverage a range of annotation standards (for example, TIMEML), data (for example, TIMEBANK, "Perspectives" Bank), 2 dictionaries (for example, WORD-NET), knowledge sources (for example, CYC ...
of goals and the development of shared resources, and encouraging the formation of a sense of commu- nity. ...
A AAI and ACM/SIGART invite students to apply for the Ninth AAAI/SIGART Doctoral Consortium. ...
doi:10.1609/aimag.v24i3.1723
dblp:journals/aim/AbeckerACDDEFFGJKKMMMRSW03
fatcat:b7s542czdfdlnbjlvaxhxgb7dy
A survey on question answering technology from an information retrieval perspective
2011
Information Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
., representations of queries and information documents, and retrieval functions which are used for estimating the relevance between a query and an answer candidate. ...
This article provides a comprehensive and comparative overview of question answering technology. ...
Resources with temporal information include the TimeBank corpus annotated with the TimeML temporal markup language [111] , [113] . ...
doi:10.1016/j.ins.2011.07.047
fatcat:se6dcorj2jbidath35go5wi5yy
Content Selection for Timeline Generation from Single History Articles
2017
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
A main focus of this thesis is the development of evaluation methodologies and resources, as no suitable corpora existed when work began. ...
For the initial experiment on important historical figures, I construct a corpus of existing timelines and textual articles, and devise a method for evaluating algorithms based on this resource. ...
community has marked as lowquality. ...
doi:10.17863/cam.14427
fatcat:6vmptfwbsjaipmwivx3gynb4jq
Shallow features as indicators of English–German contrasts in lexical cohesion
2017
Languages in Contrast: International Journal for Contrastive Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper contrasts lexical cohesion between English and German spoken and written registers, reporting findings from a quantitative lexical analysis. ...
After an overview of research aims and motivations we formulate hypotheses on distributions of shallow features as indicators of lexical cohesion across languages and modes and with respect to register ...
We focus on the constituents that may play a role as ...
doi:10.1075/lic.16005.kun
fatcat:p7pa2crm6rgkrfmsdf7m5265ea
Discourse-level features for statistical machine translation
2015
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The resources are freely available to the community for further research and replicability 5 . Moreover, Chapter 4 presents the evaluation metrics used in this thesis.
Chapter 5. ...
Although there are a number of existing and annotated resources for the automatic processing of verbs and VPs (TimeML http://timeml.org/site/index.html, FrameNet (Baker et al. [1998] ), VerbNet (Kipper ...
In the baseline MT output for Example 2, the direct lexical equivalent for whenlorsque is generated, which is correct, although the translation has other mistakes such as the wrong verb semblait and the ...
doi:10.5075/epfl-thesis-6501
fatcat:4f4aapg45nck5bpz32ekv4z6vq
Reassessing inflectional regularity in Modern Greek conjugation
[chapter]
Proceedings of the Third Italian Conference on Computational Linguistics CLiC-it 2016
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
This analysis is useful to identify features for the development of an automatic tool for sentiment-related classification tasks in this domain. The gold standard is available to the community. ...
A multilayered manual annotation for exploring attitudes on fertility and parenthood has been applied. ...
to the text genre and interaction with discourse relations, not addressed in the TimeML Guidelines nor in the TimeBank corpus. ...
doi:10.4000/books.aaccademia.1721
fatcat:6mvr6rntdnhrlgxyqoqrvasc6u
Evolution of Italian Treebank and Dependency Parsing towards Universal Dependencies
[chapter]
Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
MF would also like to thank the EPSRC for its support in the form of a doctoral training grant. ...
Acknowledgements The authors thank all the persons who supported the work, and in particular Federica Ramires that meaningfully contributed to the annotation and analysis of the corpus as part of her Bachelor's ...
They perform their analysis for English as well as for low resources languages, i.e., Swedish. ...
doi:10.4000/books.aaccademia.1295
fatcat:rys2m47xezcjjlpnibjq37v644
Tracking the Evolution of Written Language Competence: an NLP–based Approach
[chapter]
Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
MF would also like to thank the EPSRC for its support in the form of a doctoral training grant. ...
Acknowledgements The authors thank all the persons who supported the work, and in particular Federica Ramires that meaningfully contributed to the annotation and analysis of the corpus as part of her Bachelor's ...
They perform their analysis for English as well as for low resources languages, i.e., Swedish. ...
doi:10.4000/books.aaccademia.1542
fatcat:ixjjm6gvzrbrxg23bqqmexmg2u
Improved Written Arabic Word Parsing through Orthographic, Syntactic and Semantic constraints
[chapter]
Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
MF would also like to thank the EPSRC for its support in the form of a doctoral training grant. ...
Acknowledgements The authors thank all the persons who supported the work, and in particular Federica Ramires that meaningfully contributed to the annotation and analysis of the corpus as part of her Bachelor's ...
They perform their analysis for English as well as for low resources languages, i.e., Swedish. ...
doi:10.4000/books.aaccademia.1527
fatcat:o5453kzmpzavfljlr4w732ignm
Parsing Events: a New Perspective on Old Challenges
[chapter]
Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
MF would also like to thank the EPSRC for its support in the form of a doctoral training grant. ...
Acknowledgements The authors thank all the persons who supported the work, and in particular Federica Ramires that meaningfully contributed to the annotation and analysis of the corpus as part of her Bachelor's ...
They perform their analysis for English as well as for low resources languages, i.e., Swedish. ...
doi:10.4000/books.aaccademia.1551
fatcat:wr3xqyo7izentn7biz63o4kklu
Digging in the Dirt: Extracting Keyphrases from Texts with KD
[chapter]
Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
MF would also like to thank the EPSRC for its support in the form of a doctoral training grant. ...
Acknowledgements The authors thank all the persons who supported the work, and in particular Federica Ramires that meaningfully contributed to the annotation and analysis of the corpus as part of her Bachelor's ...
They perform their analysis for English as well as for low resources languages, i.e., Swedish. ...
doi:10.4000/books.aaccademia.1518
fatcat:m77guqgmcbaulghujyirrmryva
« Previous
Showing results 1 — 15 out of 47 results