Identification of Multiword Expressions in Technical Domains: Investigating Statistical and Alignment-Based Approaches. Villavicencio, A., Caseli, H., D., M., & Machado, A. 2009.
Identification of Multiword Expressions in Technical Domains: Investigating Statistical and Alignment-Based Approaches [link]Website  abstract   bibtex   
Multiword Expressions (MWEs) are one of the stumbling blocks for more precise Natural Language Processing (NLP) systems. The lack of coverage of MWEs in resources can impact negatively on the performance of tasks and applications, and can lead to loss of information or communication errors; especially in technical domains where MWE are frequent. This paper investigates some approaches to the identification of MWEs in technical corpora based on: association measures, part-of-speech and lexical alignment information. We examine the influence of some factors on their performance such as sources of information for identification and evaluation. While the association measures emphasize recall, the alignment method focuses on precision.
@misc{
 title = {Identification of Multiword Expressions in Technical Domains: Investigating Statistical and Alignment-Based Approaches},
 type = {misc},
 year = {2009},
 source = {Information and Human Language Technology STIL 2009 Seventh Brazilian Symposium in},
 identifiers = {[object Object]},
 keywords = {lexical acquisition,multiword expressions,natural language processing},
 pages = {27-35},
 websites = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5532435},
 publisher = {Ieee},
 id = {05438d2c-4856-392d-871a-6af464b72038},
 created = {2013-10-13T02:10:23.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 tags = {multiword expressions},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Villavicencio2009},
 private_publication = {false},
 abstract = {Multiword Expressions (MWEs) are one of the stumbling blocks for more precise Natural Language Processing (NLP) systems. The lack of coverage of MWEs in resources can impact negatively on the performance of tasks and applications, and can lead to loss of information or communication errors; especially in technical domains where MWE are frequent. This paper investigates some approaches to the identification of MWEs in technical corpora based on: association measures, part-of-speech and lexical alignment information. We examine the influence of some factors on their performance such as sources of information for identification and evaluation. While the association measures emphasize recall, the alignment method focuses on precision.},
 bibtype = {misc},
 author = {Villavicencio, Aline and Caseli, Helena De Medeiros and Machado, André}
}

Downloads: 0