Workshops at IWCS 2015
IWCS 2015 will include 5 associated workshops, held on 14th April 2015. Attendance at workshops will be included in the main conference registration - see Registration for details.
|Organisers:||Harry Bunt, Nancy Ide, Kiyong Lee, James Pustejovsky, Laurent Romary|
ISA-11 is the eleventh edition of a series of joint workshops of the ACL Special Interest Group in Semantics (SIGSEM) and the International Organization of Standards ISO. ISA-workshops bring together experts in the annotation of semantic information as expressed in text, speech, gestures, graphics, video, images, and in communicative behaviour where multiple modalities are combined. Examples of semantic annotation include the markup of events, time, space, dialogue acts, discourse relations, semantic roles, coreference and named entities, for which the ISO organization pursues the establishment of annotation standards in order to support the creation of interoperable semantic resources.
|Organisers:||Malvina Nissim, Paola Pietandrea|
The notion of modality involves a spectrum of phenomena that are pervasive in language but far from being formalised. For an exhaustive formalisation, a joint effort by computational, corpus, and formal linguists as well as language typologists is required. The main aim of this workshop is bringing together researchers from such fields, towards the development of shared, stable annotation standards.
Beside the contribution of peer-reviewed research papers, we envisage a truly hands-on event as part of this workshop, where we would like to encourage participants to possibly try each other's annotation tools and schemes, and set up a roadmap for reaching shared standards in the annotation of modality.
|Organisers:||Roman Kutlák, Artemis Parvizi, Christina Unger|
With the growing importance of Semantic Web technologies, formal ontologies are increasingly used by people with limited or no background in formal logic, creating a significant interest in natural and easily accessible front ends. In addition, the role of ontologies in computational linguistics is recognised as crucial. Global interest in these topics is witnessed by recent projects such as NeOn (Lifecycle Support for Networked Ontologies), LEGO (Lexicon Enhancement via the GOLD Ontology), SWAT (Semantic Web Authoring Tool), PESCaDO (Personalized Environmental Service Configuration and Delivery Orchestration), CO-ODE, and WhatIf (What if... questions for Ontology Authoring).
This workshop aims to create a forum for the many ways in which research on ontologies and research in computational linguistics relate to each other. It aims at bringing together researchers from different communities, including controlled languages and natural language interfaces as well as ontology languages and linguistic ontologies, in order to identify common interests, exploit synergies, and share methods, tools and resources.
|Organisers:||Ruth Kempson, Robin Cooper, Matthew Purver|
Despite being the mainstay of our language experience, the data of conversational dialogue pose very considerable challenges for semantic modelling. They violate expectations provided by standard frameworks, with apparently incomplete and/or highly context-dependent fragments widespread. Conventional grammar frameworks are poorly set up to reflect these dynamics, but the goal of defining models able to reflect them is an active research area. However, dialogue phenomena and data provide us with evidence about intended and understood meaning which can help define more suitable approaches, either through inspection or through computational methods (especially given the recent progress in distributional and inferential methods for deriving semantic representations and parsers from context). This workshop brings together researchers addressing these issues and assesses the significance of this ongoing work both for approaches to semantics and for computational modelling.
|Organisers:||Eva Maria Vecchi, Mehrnoosh Sadrzadeh|
Distributional semantics is based on the idea that words that often occur in the same context have similar meanings; this idea is formalised using vector spaces and reasoned about using linear algebra and statistical methods. In such models, basis vectors are contexts and vectors represent meanings of words. Various distance measures between the word vectors (e.g. geometric and Euclidean) are used to reason about word similarity. Recently there has been a lot of focus on a number of extensions: integrating machine learning techniques (e.g. neural networks) to improve vector estimation; compositionality of phrases and sentences; extended experimental tasks; and extended mathematical models and algorithms. This workshop aims to bring together researchers of the field who have answers for the above questions, who have either advanced experience with the experimental side of the field, or have worked on the more complex composition operators, their ramifications, and the optimisation techniques that would help implement them.