First Call for Papers

Workshop on South and Southeast Asian Natural Language Processing (WSSANLP)

www.sanlp.org/wssanlp2011

a collocated event at

International Joint Conference on Natural Language Processing (IJCNLP)

www.ijcnlp2011.org

Motivation

The main motive behind the organization of South and Southeast Asian Natural Languages Processing (SSANLP) workshop is to bring together the community working on the South and Southeast Asian languages covering all aspects of natural language processing and computational linguistics such as development of computational resources, morphology, syntax, semantics and machine translation. This is a long term commitment and goal, which cannot be achieved through a single workshop. Hence, we are planning to make this workshop an annual event collocated with one of the major Computational Linguistics conferences and focusing on certain specific NLP issues. We have successfully organized the 1^st Workshop on South and Southeast Asian NLP at COLING 2010 in Beijing, China. The current workshop again focuses on the phenomena of rich Morphology of South and South East Asian languages and the complex segmentation in these languages. More details about the current workshop are available at www.sanlp.org/wssanlp2011

Topics

Morphology is one of the core processes of Natural Language Processing (NLP). With the knowledge of rules for inflection, derivation, and compounding, we are able to generate and understand the word forms that are mandatory to communicate, including the creation of new words from existing words. To be acquainted with a language, we have to master the rules of syntax and morphology as these are crucial rudiments for dealing with semantics or even pragmatics. In NLP, morphological resources are the basis for all higher level developments and applications. It is especially true for languages with rich morphology like Bengali, Hindi, Punjabi, Urdu, etc. A morphological analysis component is crucial for analyzing word forms in the whole corpus. Generation of surface forms corresponding to a root is also essential from practical point of view. Another major challenge for understanding the word forms is the segmentation of the source text. The task of morphology, however, is intimately linked with segmentation for said languages. Apart from the uses in NLP, there are useful practical applications where morphological analysis and/or generation are required, e.g., in text processing, user interfaces, and information retrieval.

The topics of interest for SSANLP workshop include (but not limited to) the following related to the morphology and segmentation of South and Southeast Asian languages:

The complexity of word level processing

Frameworks for morphological processing

Universal morphotactic phenomena across South and Southeast Asian languages

Lexicon and Rule-basis for morphological analysis

New formalisms, or computational treatments of existing linguistic formalisms for the said languages

Probabilistic models and machine learning for morphology and segmentation

Analysis or exploitation of multilingual, multi-dialectal, and diachronic data

Algorithms, including finite-state methods

Algorithms and methods for automatic development of morphological analysis from the corpus

Generic morphological analyzer for South and Southeast Asian Languages

Communication of morpho-tactics with its neighboring layers in the linguistic process (i.e. Morpho-syntactics and Morpho-phonemics) for the said languages

Usability or extensibility of existing tools like KIMMO, XFST, ATEF, etc. for the development of morphological analyzer for South and Southeast Asian languages

Tools and resources

Author Instructions

Authors are invited to submit substantial, original and completed research work relevant to the topics of the workshop in form of regular papers. Authors are also invited to submit a small, focused contribution, work in progress, a negative result and an opinion piece in form of short papers. More detailed paper format guidelines will be provided, once we get these information from IJCNLP – main conference organizers.

Reviewing of papers will be double-blind. Therefore, the paper must not include the authors' names and affiliations. Furthermore, self-references that reveal the author's identity, e.g., 'We previously showed (Smith, 1991) ...', must be avoided. Instead, citations such as 'Smith (1991) previously showed ...', must be used. Papers that do not conform to these requirements will be rejected without review.

Dual submission policy: If you have submitted or plan to submit your paper in other venues, then you must indicate this fact during submission to SSANLP. Note that if your paper is accepted in SSANLP then you must withdraw the same paper from other venues in order to get it published in the proceedings of SSANLP.

Important Dates

Journal Special Issue

The organizers plan to publish selected high quality submissions to SSANLP as a special issue of a reputed scientific journal.

Any query can be sent on wssanlp2011@sanlp.org

Please feel free to forward this call for paper to all interested people, thank you.

---
M. G. Abbas Malik
Assistant Professor

COMSATS Institute of Information Technology
Lahore - Campus

Department of Computer Science,

Muhammad Ali Jinnah Building,

Defence Road, Off Raiwind Road,

Lahore, Pakistan
E-mail: abbas.malik at ciitlahore.edu.pk

             abbas.malik at imag.fr

             abbas.malik at gmail.com