Seminar — Valia Kordoni
Speaker: | Dr. Valia Kordoni, German Research Centre for Artificial Intelligence (DFKI GmbH) and Dept. of Computational Linguistics, Saarland University |
Title: | Linguistic Knowledge Mining for Improving Performance of Lexicalised Grammars |
Date: | Thursday 8th July 2010 at 12:00 |
Location: | LG.010 in the MIB Building |
Abstract: | In the first part of the talk I focus on the linguistic properties of Multiword Expressions (MWEs), taking a closer look at their lexical, syntactic, as well as semantic characteristics. In the second part of the talk I focus on methods for the automatic acquisition of MWEs for robust grammar engineering. First I investigate the hypothesis that MWEs can be detected by the distinct statistical properties of their component words, regardless of their type, comparing various statistical measures, a procedure which leads to extremely interesting conclusions. I then investigate the influence of the size and quality of different corpora, using the BNC and the Web search engines Google and Yahoo. I conclude that, in terms of language usage, web generated corpora are fairly similar to more carefully built corpora, like the BNC, indicating that the lack of control and balance of these corpora are probably compensated by their size. I also show a qualitative evaluation of the results of automatically adding extracted MWEs to existing linguistic resources. I argue that the process of the automatic addition of extracted MWEs to existing linguistic resources improves qualitatively, if a more compositional approach to the grammar/lexicon automated extension is adopted. Finally, I conclude the talk with a brief presentation of an innovative chart mining technique which enhances even more the performance of the grammar by supporting a lexical acquisition model developed for a very challenging type of MWEs, namely, English verb particle constructions. The chart mining technique operates over unlexicalised features mined from a partial parsing chart. The proposed technique is shown to outperform a state-of-the-art parser over the target task, despite being based on relatively simplistic features.
|
Featured News
- Congratulations to PhD student Panagiotis Georgiades
- 24-month postdoctoral research position in Athens, Greece
- PhD opportunity in collaboration with Athens Univ. of Economics and Business
- iCASE EPSRC funded PhD- multimodal NLP - UoM & BAE - Application deadline 30th April 2024
- CFP: BIONLP 2024 and Shared Tasks @ ACL 2024
- Advances in Data Science and Artificial Intelligence Conference 2024
Other News & Events
- Invited talk at the 8th Annual Women in Data Science Event at the American University of Beirut
- Invited talk at the 2nd Symposium on NLP for Social Good (NSG), University of Liverpool
- Invited talk at Annual Meeting of the Danish Society of Occupational and Environmental Medicine
- New review article on emotion detection for misinformation
- BioNLP 2024 accepted as workshop at ACL 2024