XTM: A Robust Temporal Text Processor

Hagège, Caroline; Tannier, Xavier

doi:10.1007/978-3-540-78135-6_20

Cited by 5 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is the origin of the endothermic peak and it offers a molecular interpretation of the two phonon modes of the phenomenolog~cal theory of Choy and Young [21]. Some times ago Hagege [22] already interpreted the endothermic peak in the DSC curve of sub-T, annealed…”

mentioning

confidence: 85%

The concept of cohesional entanglement

Qian

1997

Macromolecular Symposia

View full text Add to dashboard Cite

A concept of cohesional entanglement through local nematic interaction of neighboring chain segments has been introduced in addition to the usual topological entanglement of chains. As topological entanglement is important to properties of the polymer in the rubbery and flowing states at temperatures well above its Tg, the cohesional entanglement is important to properties at temperatures around and below Tg. Evidences for the existence of cohesional entanglements are presented. From the point of view of cohesional entanglement the DSC curves of glass transition and the effect of sub‐Tg annealing are discussed. Finally the stress peak on yielding during uni‐axial drawing, rejuvenation of sub‐Tg annealed polymer by drawing and anti‐plasticization of plastics are discussed based on the concept of cohesional entanglement.

show abstract

mentioning

confidence: 85%

The concept of cohesional entanglement

Qian

1997

Macromolecular Symposia

View full text Add to dashboard Cite

show abstract

“…In the case of complex, eventually ambiguous sequences, the following segmentation criteria, defined in [Hagège and Tannier 2008] …”

Section: Segmentationmentioning

confidence: 99%

“…Unfortunately, temporally anotated corpora are only available for English (namely TimeBank which is provided by the TimeML [Saurí et al 2006] effort, and they are very time-consuming to build. More recently, [Parent et al 2008] and [Hagège and Tannier 2008] presented rulebased systems annotating and normalizing temporal expressions for French and English. For Portuguese, a first step towards temporal annotation has been performed in the context of the Second HAREM competition [Mota and Santos 2008].…”

Section: Introductionmentioning

confidence: 99%

Portuguese Temporal Expressions Recognition: From TE Characterization to an Effective TER Module Implementation

Hagège

Baptista

Mamede

2009

2009 Seventh Brazilian Symposium in Information and Human Language Technology

Self Cite

View full text Add to dashboard Cite

Taking into account the temporal dimension conveyed in texts is a challenge to natural language processing. At the same time this task is of great importance for a wide range of natural language processing applications. The goal of this paper is twofold. First a characterization of Portuguese temporal expressions as they appear in texts is presented. This classification is intended to meet the requirements of high inter-agreement between annotators of temporal expressions. Second, relying on this characterization, an effective temporal expression annotation tool is described. Results from its evaluation are reported. Resumo.A dimensão temporalé um elemento estruturante fundamental para a informação veiculada em textos e constitui um desafio para o processamento de língua natural, sendo igualmente importante para muitas aplicações do processamento das línguas. Este artigo apresenta uma classificação das expressões temporais do português que permite esclarecer algumas incertezas relativas ao estatuto das diferentes expressões temporais e constitui uma base para a anotação intersubjectiva destas expressões. Utilizando esta classificação, foi desenvolvida uma ferramenta de anotação automática das expressões temporais do português, cujo desempenho foi avaliado.

show abstract

“…As in [11] we define these time points as unique and stand for corresponding points on the timeline. A temporal graph is computed within each document using Allen's temporal relations with a forward reasoning engine [12] while all instants are normalised by changing their granularity to that of a day (that granularity was selected as the most suitable according to our objectives and the data being available). Posing queries over temporally related sequences of events thus becomes possible, bearing in mind that the temporal information may be over or under-specified.…”

Section: Knowledge Integration Componentmentioning

confidence: 99%

Event Extraction for Legal Case Building and Reasoning

Lagos

Segond

Castellani

et al. 2010

Intelligent Information Processing V

View full text Add to dashboard Cite

We are interested in developing tools to support the activities of lawyers in corporate litigation. In current applications, information such as characters that have played a significant role in a case, events in which they have participated, people they have been in contact, etc., have to be manually identified. There is little in the way of support to help them identify the relevant information in the first place. In this paper, we describe an approach to semiautomatically extracting such information from the collection of documents the lawyers are searching. Our approach is based on Natural Language Processing techniques and it enables the use of entity related information corresponding to the relations among the key players of a case, extracted in the form of events.

show abstract

XTM: A Robust Temporal Text Processor

Cited by 5 publications

References 6 publications

The concept of cohesional entanglement

The concept of cohesional entanglement

Portuguese Temporal Expressions Recognition: From TE Characterization to an Effective TER Module Implementation

Event Extraction for Legal Case Building and Reasoning

Contact Info

Product

Resources

About