This workshop aims at examining the relationship between linguistics and NLP and determining
Since early 1990s, with the advancement of machine learning methods and the
availability of data resources such as treebanks and parallel corpora,
data-driven approaches to NLP have made significant progress. The success of such data-driven approaches has cast doubt on the relevance of linguistics to
NLP. Conversely, NLP techniques are rarely used to help linguistics studies.
We believe that there is room to expand the involvement of linguistics in NLP,
and likewise, NLP in linguistics, and believe that the cross-pollination of
ideas between the disciplines can greatly benefit both fields.
One common approach to take advantage of linguistic knowledge is to train
a statistical system on linguistically annotated data such as treebanks.
Another approach is to represent linguistic knowledge as rules in a
rule-based approach. This workshop is interested in research that goes BEYOND
these common approaches and explores new methods in incorporating
linguistic knowledge into statistical systems or using
statistical systems for linguistic knowledge discovery.
The workshop will consist of one invited talk, 2-3 panels, group discussion, and paper/poster sessions.
[T1] Research that shows awareness of particular linguistic phenomena
and its effects on statistical systems.
For instance, being aware of syntactic phenomena such as scrambling,
cross-serial dependencies and long-distance movement is very relevant
to parsing (e.g., earlier work on using different grammar formalisms
such as LTAG/CCG/HPSG/LFG to handle these phenomena or more recent
work on non-projective dependency parsing).
Similarly, being aware of word formation patterns (e.g., reduplication
in Chinese) or allomorphic variation patterns (e.g., vowel harmony in
Turkish) could help word segmentation and morphological analysis.
[T2] New methods in incorporating linguistic knowledge into
statistical systems to improve the start of the art.
(e.g., as rules in a preprocessing step, as linguistic features in
a statistical system, as filters for pruning a search space, as priors
in an objective function).
[T3] Research that demonstrates the feasibility of creating NLP systems to
automatically acquire linguistic knowledge for a large number of
languages.
In order to make generalizations about language universals, linguists
need to gather information about as many individual languages as
possible. However, knowledge about most languages is not complete.
Can we use NLP techniques to acquire knowledge (e.g., basic word
order, case marking, tense, aspect, word formation rules, etc.) for
hundreds of languages, which could help in the construction of
resources such as WALS (http://wals.info) (Haspelmath et al., 2005)?
[T4] Research that demonstrates the benefits of using NLP techniques to
help particular linguistic studies. For instance, given some language
data, can the categorization of languages into families be automated?
Can historical interactions between languages be identified
automatically (e.g., areal effects and borrowings, but beyond just
lexical borrowings)? Can NLP tools run over corpora
of different dialects of the same language systematically identify
differences in the two dialects (e.g., not just word choice
differences, but also choice and frequency of particular
constructions)?
On the submission form, please specify the theme that your paper falls into.
The systems described in the paper should be properly evaluated and compared with the start of the art.
The papers should report original and unpublished research on topics of interest for the workshop. Accepted papers are expected to be presented at the workshop, and will be published in the workshop proceedings. They should emphasize obtained results rather than intended work, and should indicate clearly the state of completion of the reported results.
A paper accepted for presentation at the workshop must not be presented or have been presented at any other meeting with publicly available proceedings.
4.1 Submission Format: All submissions must be electronic in PDF and must be
formatted using the ACL 2010 style files, which are available at
http://www.acl2010.org/authors.html
4.2 Maximum Length: The maximum length of a submitted paper is
eight (8) pages of content, excluding references. One additional
page is allowed for the References section. Thus, your PDF file
is limited to eight (8) pages of content and nine (9) pages in total.
4.3 Anonymous Review: 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, use
citations such as "Smith (1991) previously showed ...". Papers that do
not conform to these requirements will be rejected without review.
4.4 Double Submitting: Papers that have been or will be submitted to other
meetings or publications must provide this information on the START
online submission page. If NLPLing 2010 accepts a paper, authors must
notify the program chairs *immediately* indicating which meeting they
choose for presentation of their work. NLPLing 2010 cannot accept for
publication or presentation work that will be (or has been) published
elsewhere.
4.5 Submission site: Authors must submit papers online at
https://www.softconf.com/acl2010/NLPLing/
4.6 Submission deadline is April 7, 2010 23:59 PDT. Papers submitted after the deadline will not be reviewed.
ACL is providing a mentoring (coaching) service for authors from regions of the world where English is less emphasized as a language of scientific exchange. Many authors from these regions, although able to read the scientific literature in English, have little or no experience in writing papers in English for conferences such as the ACL meetings. The service will be arranged as follows. A set of potential mentors will be identified by Mentoring Service Chairs Björn Gambäck (SICS, Sweden and NTNU, Norway) and Diana McCarthy (Lexical Computing Ltd., UK), who will organize this service for ACL 2010. If you would like to take advantage of the service for a submission to this workshop, please upload your paper in PDF format using the paper submission software for the mentoring service available at: https://www.softconf.com/acl2010/acl2010mentor/
The deadline for the mentoring service is six weeks before the workshop submission deadline. An appropriate mentor will be assigned to your paper and the mentor will get back to you no later than two weeks before the submission deadline.
Please note that this service is for the benefit of the authors as described above. It is not a general mentoring service for authors to improve the technical content of their papers.
Questions about the mentoring service should be referred to mentoring@acl2010.org