* * * * * * * * * * * * * * * * * * * * * * * *
LINGUIST List logo Eastern Michigan University Wayne State University *
* People & Organizations * Jobs * Calls & Conferences * Publications * Language Resources * Text & Computer Tools * Teaching & Learning * Mailing Lists * Search *
* *


LINGUIST List 23.2636

Thu Jun 07 2012

Confs: Computational Ling, Discourse Analysis/ South Korea

Editor for this issue: Xiyan Wang <xiyanlinguistlist.org>


LINGUIST is pleased to announce the launch of an exciting new feature: Easy Abstracts! Easy Abs is a free abstract submission and review facility designed to help conference organizers and reviewers accept and process abstracts online. Just go to: http://www.linguistlist.org/confcustom, and begin your conference customization process today! With Easy Abstracts, submission and review will be as easy as 1-2-3!
Date: 07-Jun-2012
From: Agnes Sandor <agnes.sandorxrce.xerox.com>
Subject: Detecting Structure in Scholarly Discourse
E-mail this message to a friend

Detecting Structure in Scholarly Discourse
Short Title: DSSD2012


Date: 12-Jul-2012 - 12-Jul-2012
Location: Jeju Island, Korea, South
Contact: Anita de Waard
Contact Email: < click here to access email >
Meeting URL: http://www.nactem.ac.uk/dssd/index.php

Linguistic Field(s): Computational Linguistics; Discourse Analysis

Meeting Description:

ACL 2012 Workshop on Detecting Structure in Scholarly Discourse, DSSD2012
Web: http://www.nactem.ac.uk/dssd/index.php
July 12, 2012
International Convention Center Jeju
Jeju Island, Republic of Korea

Discourse structure, as a field of research within computational linguistics, is attracting renewed research interest, due to its increasing relevance to diverse fields such as bio-medical text analysis, ethnography, and scientific publishing. Much effort is directed at detecting and modeling a range of discourse elements at different levels of granularity and for different purposes. Such elements include: the statement of facts, claims, and hypotheses; the identification of methods and protocols; and the detection of novelty in contrast to the re-stating of previous existing work. More ambitious long-term goals include the modeling of argumentation, rhetorical structure, and narrative structure. A broad variety of approaches and of features are used to identify discourse elements, including verb tense/mood/voice, semantic verb class, speculative language or negation, various classes of stance markers, text-structural components, or the location of references. The choice of features is often motivated by linguistic inquiry into the detection of subjectivity, opinion, entailment, inference, as well as author stance, author disagreement, motif and focus.

Six submissions were selected for presentation at the workshop. The submissions represent three fundamental perspectives of research concerning discourse structure: taxonomy and annotation, exploiting cross-document structure in text mining, and detecting discourse elements in scholarly texts. Further development of discourse models and of systems is likely to bring together and integrate aspects from all three. At the same time, these three perspectives give rise to interesting contrasts and different research questions, for instance: Are explicit taxonomies and annotation levels necessary for text mining and for the identification of particular types of discourse elements? or, more generally: How do these different perspectives all relate to a central theory of discourse? The workshop aims to be a forum for discussion of these exciting questions.

During the panel discussion time, we wish to summarize the state of the art and brainstorm on areas for development pertaining to the three main workshop topics: Exploiting Discourse Structure, Detecting Discourse Elements, and Taxonomies and Annotation.

We are happy to announce that the program for the ACL workshop 'Detecting Structure in Scholarly Discourse' has now been finalized, to be held on Jeju Island, Korea, on July 12, 2012 - for an online version, see:

http://www.nactem.ac.uk/dssd/programme.php

Workshop Programme:

Time Presentation

9:00-10:30
Session 1: Exploiting Discourse Structure

9:00-9:45
Dae Hoon Park and Catherine Blake
Identifying Comparative Claim Sentences in Full-Text Scientific Articles

09:45-10:30
Ágnes Sándor and Anita de Waard
Identifying Claimed Knowledge Updates in Biomedical Research Articles

10:30-11:00
Coffee break


11:00-12:30
Session 2: Detecting Discourse Elements

11:00-11:45
Awais Athar and Simone Teufel
Detection of Implicit Citations for Sentiment Detection

11:45-12:30
Tomoko Ohta, Sampo Pyysalo, Jun'ichi Tsujii and Sophia Ananiadou
Open-domain Anatomical Entity Mention Detection

12:30-14:00
Lunch break


14:00-15:30
Session 3: Taxonomies and Annotation

14:00-14:45
Maria Liakata, Paul Thompson, Anita de Waard, Raheel Nawaz, Henk Pander Maat and Sophia Ananiadou
A Three-Way Perspective on Scientific Discourse Annotation for Knowledge Extraction

14:45-15:30
Anita de Waard and Henk Pander Maat
Epistemic Modality and Knowledge Attribution in Scientific Discourse: A taxonomy of types and overview of features

15:30-16:00
Coffee break

16:00-17:00
Panel discussion on detecting and using discourse structure for scholarly text

17:00-17:30
Wrap-up and close

We greatly look forward to seeing you in Korea!


The DSSD Organising Committee:

Sophia Ananiadou
School of Computer Science
University of Manchester, UK

Antal van den Bosch
Centre for Language Studies
Radboud University Nijmegen, The Netherlands

Ágnes Sándor
Xerox Research Europe
Grenoble, France

Hagit Shatkay
Dept. of Computer and Information Sciences, College of Engineering
University of Delaware, USA

Anita de Waard
Disruptive Technologies Director
Elsevier Labs, USA
Elsevier B.V. Registered Office: Radarweg 29, 1043 NX Amsterdam, The Netherlands, Registration No. 33156677 (The Netherlands)



Read more issues|LINGUIST home page|Top of issue



Page Updated: 07-Jun-2012

Supported in part by the National Science Foundation       About LINGUIST    |   Contact Us       ILIT Logo
While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed on its pages, it cannot vouch for their contents.