Acl - Ijcnlp 2009 Mwe 2009 2009

Order copies of this and other ACL proceedings from: The workshop focused on Multi-Word Expressions (MWEs), which represent an indispensable part of natural languages and appear steadily on a daily basis, both novel and already existing but paraphrased, which makes them important for many natural language applications. Unfortunately, while easily mastered by native speakers, MWEs are often non-compositional, which poses a major challenge for both foreign language learners and automatic analysis. The growing interest in MWEs in the NLP community has led to many specialized workshops held every year since 2001 in conjunction with ACL, EACL and LREC; there have been also two recent special issues on MWEs published by leading journals: the International Journal of Language Resources and Evaluation, and the Journal of Computer Speech and Language. As a result of the overall progress in the field, the time has come to move from basic preliminary research to actual applications in real-world NLP tasks. Thus, in MWE'09, we were interested in the overall process of dealing with MWEs, asking for original research on the following four fundamental topics: Identification. Identifying MWEs in free text is a very challenging problem. Due to the variability of expression, it does not suffice to collect and use a static list of known MWEs; complex rules and machine learning are typically needed as well. Interpretation. Semantically interpreting MWEs is a central issue. For some kinds of MWEs, e.g., noun compounds, it could mean specifying their semantics using a static inventory of semantic relations, e.g., WordNet-derived. In other cases, MWE's semantics could be expressible by a suitable paraphrase. Disambiguation. Most MWEs are ambiguous in various ways. A typical disambiguation task is to determine whether an MWE is used non-compositionally (i.e., figuratively) or compositionally (i.e., literally) in a particular context. Applications. Identifying MWEs in context and understanding their syntax and semantics is important for many natural language applications, including but not limited to question answering, machine translation, information retrieval, information extraction, and textual entailment. Still, despite the growing research interest, there are not enough successful applications in real NLP problems, which we believe is the key for the advancement of the field. Of course, the above topics largely overlap. For example, identification can require disambiguating between literal and idiomatic uses since MWEs are typically required to be non-compositional by definition. Similarly, interpreting three-word noun compounds like morning flight ticket and plastic water bottle requires disambiguation between …