Natural Language Parsing -- for what purpose?

Add to your list(s) Download to your calendar using vCal

• Milos Jakubicek
• Friday 02 May 2014, 12:00-13:00
• FW26, Computer Laboratory.

If you have a question about this talk, please contact Tamara Polajnar.

“Parsing is a crucial/necessary/important/useful/nice-to-have part of many NLP applications”—an omnipresent sentence (in variations). But is it really? In the talk I will provide a somewhat provocative and critical review of state-of-the-art in natural language parsing with regards to its exploitation in particular end-user applications. I will try to show an overview of how parsing is actually used now, discuss its present limitations, impeach the usefulness of the dominant evaluation paradigm and shed light on what the alternatives may look like.

So as not to end up with a talk consisting purely of negative results, I will finally present research, linguistic and engineering issues and current results in parsing of large web corpora carried out at Lexical Computing and parsing of morphologically-rich languages conducted at the NLP Centre at Masaryk University.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Big Data
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Chris Davis' list
• Computer Laboratory talks
• FW26, Computer Laboratory
• Graduate-Seminars
• Guy Emerson's list
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• rp587

Note that ex-directory lists are not shown.