@inproceedings{L16-1174,
 abstract = {The paper introduces a ``train once, use many'' approach for the syntactic analysis of phrasal compounds (PC) of the type XP+N like ``Would you like to sit on my knee?'' nonsense. PCs are a challenge for NLP tools since they require the identification of a syntactic phrase within a morphological complex. We propose a method which uses a state-of-the-art dependency parser not only to analyse sentences (the environment of PCs) but also to compound the non-head of PCs in a well-defined particular condition which is the analysis of the non-head spanning from the left boundary (mostly marked by a determiner) to the nominal head of the PC. This method contains the following steps: (a) the use an English state-of-the-art dependency parser with data comprising sentences with PCs from the British National Corpus (BNC), (b) the detection of parsing errors of PCs, (c) the separate treatment of the non-head structure using the same model, and (d) the attachment of the non-head to the compound head. The evaluation of the method showed that the accuracy of 76\% could be improved by adding a step in the PC compounder module which specified user-defined contexts being sensitive to the part of speech of the non-head parts and by using TreeTagger, in line with our approach.
},
 address = {Portorož, Slovenia},
 author = {Carola Trips},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {1092--1097},
 publisher = {European Language Resources Association (ELRA)},
 title = {Syntactic Analysis of Phrasal Compounds in Corpora: a Challenge for NLP Tools},
 url = {https://www.aclweb.org/anthology/L16-1174},
 year = {2016}
}