@inproceedings{L16-1474,
 abstract = {In this paper we consider the problem of out-of-vocabulary term classification in web forum text from the automotive domain. We develop a set of nine domain- and application-specific categories for out-of-vocabulary terms. We then propose a supervised approach to classify out-of-vocabulary terms according to these categories, drawing on features based on word embeddings, and linguistic knowledge of common properties of out-of-vocabulary terms. We show that the features based on word embeddings are particularly informative for this task. The categories that we predict could serve as a preliminary, automatically-generated source of lexical knowledge about out-of-vocabulary terms. Furthermore, we show that this approach can be adapted to give a semi-automated method for identifying out-of-vocabulary terms of a particular category, automotive named entities, that is of particular interest to us.
},
 address = {Portorož, Slovenia},
 author = {SoHyun Park and Afsaneh Fazly and Annie Lee and Brandon Seibel and Wenjie Zi and Paul Cook},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {2971--2975},
 publisher = {European Language Resources Association (ELRA)},
 title = {Classifying Out-of-vocabulary Terms in a Domain-Specific Social Media Corpus},
 url = {https://www.aclweb.org/anthology/L16-1474},
 year = {2016}
}