Figure 5 - uploaded by Matt Selway
Content may be subject to copyright.
6: Definition of “would” from The Free Dictionary (Farlex 2010) 

6: Definition of “would” from The Free Dictionary (Farlex 2010) 

Source publication
Thesis
Full-text available
The majority of current Natural Language Processing (NLP) methods and research is based on statistical analysis and machine learning. While these methods are quite effective, they are not perfect and the search continues for better and more accurate methods for NLP. The work of Kleiner et al. (Kleiner et al. 2009) takes a very different approach. T...

Context in source publication

Context 1
... category or equivalent is associated with these words. An example can be seen in the definition of “would” shown in Figure 5.6 where the category is denoted by “aux. v.” and therefore not identified by the parser (displayed in Figure 5.7). The expected category is an ordinary verb , however, depending on how specific the usage information needs to be then an extra category for auxiliary verb may need to be added to the Lexicon Model. In this case it could be discounted from the results as not being supported along with the other categories such as conjunction and preposition ; however, this is something for future work to investigate as either adding support for auxiliary verbs to the Lexicon Model or updating the parser to identify “aux. v.” (and possibly “v. aux.”) as a verb would improve the number of words with correctly identified categories and help towards completely automating the development of lexicons. The third main problem is phrases and proper nouns consisting of multiple words, for example, the phrase “such as” and the proper noun “Natural Language Processing”. As mentioned above for “at least” from the SBVR word list, The Free Dictionary does support phrase searches although it has mixed results. Some phrase searches may be successful, such as “Natural Language” (shown in Figure 5.8), however, many more are not. This is more of an issue for general language than SBVR as phrases such as “such as” are quite commonly used and, while it may be practical to manually develop ...

Similar publications

Technical Report
Full-text available
This paper presents the development of FProvW3C framework, next to a multi-agent system where the framework is responsible for collecting and storing the provenance data. We describe the data structures of the framework, following the W3C PROV model, the UML diagrams of the framework and the application developed with the use of the framework, the...