Special Issue "Advances in Natural Language Processing"
A special issue of Informatics (ISSN 2227-9709).
Deadline for manuscript submissions: 31 March 2014
Prof. Dr. Horacio Saggion
TALN Group, Department of Information and Communication Technologies, Pompeu Fabra University, C/Tànger, 122-134, 4th floor, 08018 Barcelona, Spain
Phone: +34 93 542 1119
Texts are one of the most important records of human expertise, therefore being of paramount importance for mining both general and specific knowledge. Over the past few years the role of Natural Language Processing (NLP) for mining information from textual sources has gained relevance due to the now massive availability of textual information on-line and the need to access, distill, and organize the contents held in this wealth of unstructured information. This special issue of Informatics aims to bring together articles that report advances in Natural Language Processing, both experimental as well practical applications, related to the exploitation and distillation of textual material for information access and knowledge creation. We are therefore calling for contributions in the areas of Automatic Text Summarization, Adaptable Information Extraction and Knowledge Population, Knowledge Induction from Text, Text Simplification, Text Entailment and Learning by Reading, and Natural Language Processing for the Social Media.
Prof. Dr. Horacio Saggion
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. Papers will be published continuously (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are refereed through a peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Informatics is an international peer-reviewed Open Access quarterly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. For the first couple of issues the Article Processing Charge (APC) will be waived for well-prepared manuscripts. English correction and/or formatting fees of 250 CHF (Swiss Francs) will be charged in certain cases for those articles accepted for publication that require extensive additional formatting and/or English corrections.
Informatics 2014, 1(1), 11-31; doi:10.3390/informatics1010011
Received: 1 September 2013; in revised form: 3 October 2013 / Accepted: 16 October 2013 / Published: 25 October 2013| Download PDF Full-text (237 KB)
Article: Using Collaborative Tagging for Text Classification: From Text Classification to Opinion Mining
Informatics 2014, 1(1), 32-51; doi:10.3390/informatics1010032
Received: 24 September 2013; in revised form: 11 November 2013 / Accepted: 21 November 2013 / Published: 28 November 2013| Download PDF Full-text (252 KB)
Authors: E. Charton, M.-J. Meurs and L. Jean-Louis
Affiliation: Centre for Structural and Functional Genomics, Concordia University, Montréal, Québec, H4B 1R6, Canada; E-Mail: firstname.lastname@example.org
Abstract: Numerous initiatives have allow users to share knowledge or opinions using collaborative platforms. In most cases, the users provide a textual description of their knowledge, following very limited or no constraints. Here we tackle the classification of documents written in such environment. We process cooking recipes from a collaborative website. This context makes some of the corpus specificities difficult to model for machine learning based systems and keyword or lexical based systems. In particular, different authors might have different opinions on how to classify a given document. In this paper, we explain our approach for building a relevant and effective system dealing with such a corpus.
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Article: Topic Segmentation in a Multimedia Context Combining Lexical Cohesion and Disruption
Author: Guillaume Gravier, Pascale Sebillot and Anca-Roxana Simon
Affiliation: Institut de Recherche en Informatique et Systèmes Aléatoires, Campus de Beaulieu, 35042 Rennes Cedex, France; E-Mails: email@example.com (G.G.), Pascale.Sebillot@irisa.fr (P.S.), Anca-Roxana.Simon@insa-rennes.fr (A.-R.S.)
Abstract: The paper will report recent results on topic segmentation using a criterion combining both lexical cohesion and disruption, leveraging approaches so far distinct. We demonstrate that this new criterion applies to regular texts but also extends to automatically transcribed spoken content, in spite of transcription errors. We will eventually investigate how the new criterion combines with previous advances on topic segmentation using interpolated language models .
 Camille Guinaudeau, Guillaume Gravier, and Pascale Sébillot. Enhancing lexical cohesion measure with confidence measures, semantic relations and language model interpolation for multimedia spoken content topic segmentation. Computer Speech and Language, 26(2):90-104, 2012.
Review: Information Extraction: Techniques, Advances and Challenges
Author: Heng Ji
Affiliation: Rensselaer Polytechnic Institute, Winslow Building, 110 8th Street, Troy, NY 12180-3590, USA
Abstract: Information Extraction (IE) is a task of identifying “facts”, such as the attack/arrest events, people's jobs, people's whereabouts, merger and acquisition activity from unstructured texts. In this paper we
will give an overview of the most successful techniques for each IE task and point out the remaining challenges. We will also focus on discussing the recent advances in IE in the past decade, such as cross-source IE (e.g. across different documents, genres, languages and data modalities). Traditional IE techniques assess the ability to extract information from individual documents in isolation. However, users need to gather information which may be scattered among a variety of sources. These facts may be redundant, complementary, incorrect or ambiguously worded. Furthermore, the extracted information from a document may need to augment an existing Knowledge Base (KB). We will discuss several new extensions to state-of-the-art IE and systematically present the foundation, methodologies, algorithms, and implementations for these advanced extraction capabilities. This new IE paradigm also presents many unique challenges pertaining to knowledge acquisition and learning framework. We will also provide an overview of these challenges and potential solutions to address them.
Last update: 14 November 2013