PPT-LING 581: Advanced Computational Linguistics

Lecture Notes April 27th TCE 2 nd last class today WordNet Homework If you havent already you should have emailed me this report QA Homework Idea evaluate the feasibility of QA on the web. 2012 Association for Computational Linguistics You Had Me at Hello How Phrasing Affects Memorability Cristian DanescuNiculescuMizil Justin Cheng Jon Kleinberg Lillian Lee Department of Computer Science Cornell University cristiancscornelledu jc882co 2014 Association for Computational Linguistics Fast and Robust Neural Network Joint Models for Statistical Machine Translation Jacob Devlin Rabih Zbib Zhongqiang Huang Thomas Lamar Richard Schwartz and John Makhoul Raytheon BBN Technologies 10 Moult guse Abstract This paper deals with the problem of recognizing and extracting acronym de64257nition pairs in Swedish medical texts This project applies a rulebased method to solve the acronym recognition task and compares and evaluates the results of Today
What is Linguistics?
Descriptive vs. Prescriptive rules/grammars
Linguistic competence vs. performanceReadings: 1.2-1.3 LING 200 --McGarrity What is Linguistics?The scientific study and an Lecture Notes. March 26th. Catching up…. WordNet. Did everyone manage to install?. WordNet. 3.0 package. wnb. (. WordNet. browser). shell:. export . PATH=/. usr. /local/WordNet-3.0/bin:$. PATH. WordNet. Lecture Notes. February . 19th. Bikel. Collins and EVALB. How did you guys do with . Bikel. -. Collins on section 23?. Steps. Running . evalb. Need: . parameter file: . COLLINS.prm. Parser output: .
        
               
       Longman Lancaster corpus: 30 million words. ____________________________ Reference corpora have a fixed size (e.g., the British National Corpus Monitor corpora are expandable (e.g., the Bank of Engli L a w l e r & Br eck Embo dy ing Arithmetic La ng u agi ng 1 9 98 “We claim that mathematics is no more part of the external, mind-free world than color is. Both are aspects — very dif Lecture Notes. April 2nd. Word Smart for the GRE. Non-programmers can take more time on this assignment…. y. ou can combine my sample breadth. -first search . Perl code, e.g. bfs3.perl, and try to compute connections between words and meanings and store them into a table. Then you want to pair them up according to some objective function. Lecture Notes. March 29th. Today's Topics. Some possible test cases for WordNet. Word Smart for the GRE. Example: using bfs2.perl. Word:. cadge. brook. cacophony. Definition:. mooch. tolerate. discordant sound. Lecture Notes. April 17th. Two Topics. Homework 9. Grammar and Logic. Homework 9. Use . cosines.py. . or . bfs4.perl . (or some . nltk. similarity measure mentioned in a previous lecture) or a mix of the two to come up with a method of matching words to (simple) definitions for quizzes A and B (shown on the next slides). Lecture 14. Feb 26. th. . Administrivia. Hope you sent feedback on the last lecture on Text Classification by Marcos . Zampieri. . . This Thursday (Feb 21. st. ), we have another guest lecture from faculty candidate Adriana . LING/C SC 581: Advanced Computational Linguistics Lecture 2 Jan 15 th From last time Did everyone install Python 3 and nltk / nltk_data ? We'll do a Homework 2 on this today … Importing your own corpus