Ling 3798: Introduction to Computational Linguistics
Contents
1. Un supervised word sense disambiguation Classifiers Vector space semantics Thanksgiving break TBA Finals week Our slot Wed Dec 11 8 10am http homepages uconn edu stk12004 Classes UConn 3798 schedule htm1 Last updated August 30 2013 12 6 2013 3 55 PM Ling 3798 Introduction to Computational Linguistics http homepages uconn edu stk12004 Classes UConn 3798 references Home Course Info Schedule References FAQ Misc HuskyCT Ling 3798 Introduction to Computational Linguistics Readings e Bird S E Klein and E Loper 2009 Natural Language Processing with Python O Reilly e Dickinson M C Brew and D Meurers 2012 Language and Computers Wiley Blackwell e Johnson K 2008 Quantitative Methods in Linguistics Blackwell Publishing e Jurafsky D and J H Martin 2009 Speech and Language Processing 2nd edition Prentice Hall e Lutz M and D Ascher 2004 Learning Python 2nd edition O Reilly Links Python e Python Standard Library e Try Python Simulator e Visual Python Tutor NLTK e NLTK Home e NLTK Book Regular expressions e Grant Skinner s RegExr testing tool Steven Livithan s RegexPal testing tool Python Regular Expressio HOWTO Python Regular Expression Syntax The Odds amp Ends of Regular Expressions Python Central Finite state machines e OpenFst Library e Stuttgart Finite State Transducer e J Novak s slides on opera2. Wilbur Cross Building Room 224 Additionally I am available to discuss disability related needs during my office hours or by appointment Last updated August 30 2013 lof 1 12 6 2013 3 54 PM Ling 3798 Introduction to Computational Linguistics 1 of 3 http homepages uconn edu stk 12004 Classes UConn 3798 schedule html Home Course Info Schedule References FAQ Misc HuskyCT Ling 3798 Introduction to Computational Linguistics Schedule Note This schedule is subject to change but not without notice Any changes will be announced in class and reflected on these pages Be sure to check regularly Dates Aug 26 Mo Aug 28 30 We Fr Sep 2 Mo Sep 4 6 We Fr Sep 9 13 Mo Fr Sep 16 20 Mo Fr Sep 23 27 Topics Methods Readings Introduction Some programming Jurafsky amp Martin Ch 1 Computers in linguistics and basics Natural Language Processing The nature and use of text corpora Regular expressions File handling J amp M Ch 2 1 Pattern matching control structures Corpus search and counting No class Labor Day Regular languages Set theory J amp M Ch 2 2 Finite state automata Operations and closure properties Pumping Lemma Finite state linguistics NLTK J amp M Ch 3 Transducers Morphological analysis N grams Probability theory J amp M Ch 4 Language modeling NLTK Smoothing Evaluation Part of Speech Tagging NLTK J amp M Ch 5 12 6 2013 3 55
3. Ling 3798 Introduction to Computational Linguistics http homepages uconn edu stk 12004 Classes UConn 3798 Home Course Info Schedule References FAQ Misc HuskyCT Ling 3798 Introduction to Computational Linguistics Fall 2013 Oak Hall 308 MWF 9 05 9 55 AM Instructor Stefan Kaufmann Email stefan kaufmann uconn edu Office Oak Hall Rm 364 Phone 860 486 8123 Office Hours Wed 10 30 12 00 and by appointment Last updated October 07 2013 1 of 1 12 6 2013 3 53 PM Ling 3798 Introduction to Computational Linguistics http homepages uconn edu stk 12004 Classes UConn 3798 info html Home Course Info Schedule References FAQ Misc HuskyCT Ling 3798 Introduction to Computational Linguistics General Information Course Description This course is an introduction to computational methods in empirical linguistic analysis and natural language processing Topics include the use of text corpora and other sources of linguistic data morphological analysis parsing and language modeling applications in areas such as information retrieval and machine translation The main objective is to familiarize students with core questions and approaches in the field Theoretical material on such topics as formal languages automata and complexity finite state and context free methods n grams etc will be supplemented with practical exercises and mini projects to give students some hands on experience in the use of
4. PM Ling 3798 Introduction to Computational Linguistics 2 of 3 Mo Fr Sep 30 Oct 4 Mo Fr Oct 7 11 Mo Fr Oct 14 21 Mo Mo Oct 23 25 We Fr Oct 28 Nov 1 Mo Fr Nov 4 6 Mo We Nov 8 Fr Nov 11 15 Mo Fr Nov 18 22 Word classes and tagsets Rule based and stochastic POS tagging Hidden Markov Models Evaluation Further topics in sequence linguistics Maximum entropy models Context free languages Syntactic ambiguity Context free grammars Push down automata Pumping lemmas Chomsky Hierarchy Parsing Search and dynamic programming Chart parsing CKY Earley Chunking Evaluation No class Further topics in tree linguistics Probabilistic context free grammars Statistical parsing Meaning Some approaches and desiderata Syntax semantics interface Compositionality No class Word meaning Semantic ambiguity Semantic relations Semantic roles Computational lexical semantics http homepages uconn edu stk 12004 Classes UConn 3798 schedule html Information theory Programming exercises NLTK Treebanks tgrep Logic WordNet FrameNet NLTK NLTK in fomap J amp M Ch 6 J amp M Ch 12 16 J amp M Ch 13 J amp M Ch 14 Tgrep User Manual J amp M Ch 17 J amp M Ch 19 J amp M Ch 20 12 6 2013 3 55 PM Ling 3798 Introduction to Computational Linguistics 3 of 3 Mo Fr Nov 25 29 Mo Fr Dec 2 6 Mo Fr Dec 9 13 Mo Fr
5. corpora and the implementation of algorithms Programming skills are not required but are a plus Students projects may be scaled to their level of expertise Some background in linguistics is definitely an advantage Registration Students should register for LING 3798 listed with the title Variable Topics The course is a new addition to the Linguistics offerings and does not yet have its own course number Prerequisites At least one course in Linguistics or permission of the instructor Teaching method Lectures discussions in class exercises homeworks programming projects Evaluation Six take home assignments 60 final exam 30 participation 10 Substitution of individual programming project s for some of the homeworks can be negotiated The format of the final exam will be announced later in the semester Readings Jurafsky D and J H Martin 2009 Speech and Language Processing 2nd edition Prentice Hall This is a good book to own but students are not required to buy it since we will only use excerpts from it and supplement them with other readings where appropriate Notice to students with disabilities In compliance with Section 504 of the 1973 Rehabilitation Act and the Americans with Disabilities Act UConn is committed to providing equal access to all programming Students with disabilities seeking accommodations are encouraged to contact the Center for Students with Disabilities CSD CSD is located in
6. tions on weighted FSTs POS Taggers e Xerox FST POS tagger online demo Last updated October 07 2013 1 of 1 12 6 2013 3 55 PM Ling 3798 Introduction to Computational Linguistics http homepages uconn edu stk 12004 Classes UConn 3798 faq html 1 of 2 Home Course Info Schedule References FAQ Misc HuskyCT e How do I tell IDLE where to find my files e How do I scroll through the command history in IDLE How do I make IDLE find my files You need to keep your files e g data and Python scripts in directory in which you can permanently store things The P drive is a good option it s automatically mounted when you log in with your NetID alternatively you could use a USB stick or a cloud based system like Dropbox or Google Drive or the like For instance if I store the file moby txt in my Dropbox directory and start IDLE from the Windows Startup menu I get an error message gt gt gt myfile open moby txt r Traceback most recent call last File line 1 in myfile open moby txt r TOError Errno 2 No such file or directory moby txt gt gt gt Basically there are two options 1 Change the current working directory so Python will keep looking for and writing to files in this directory for the remainder of this session This requires that you import the module os short for operating system gt gt gt import os gt gt gt os getc
7. wd C Python27 gt gt gt os chdir r C Users stk12004 Dropbox Classes UConn 3798 Materials gt gt gt myfile open moby txt r SS 2 OR you can refer to the file with its full path In this case the current working directory remains as before so you ll have to give full paths throughout the session gt gt gt myfile open r C Users stk12004 Dropbox Classes UConn 3798 Materials moby txt r gt gt gt ft top of this page How do I scroll through the command history in IDLE One convenient feature of the IDLE environment is that it lets you scroll through your command history By default you do that with alt p and Alt n for the next and previous command respectively Some people prefer to use the Up and Down arrows instead To set this up do the following in the IDLE window Options gt Configure IDLE gt Keys select history next in the Costum Key Bindings menu click Get New Keys for Selection select Down Arrow elick OK 12 6 2013 3 56 PM Ling 3798 Introduction to Computational Linguistics http homepages uconn edu stk 12004 Classes UConn 3798 faq html You will be prompted just the first time to give a name to the key setting Give it one Then do the analogous thing for history previous and the up arrow Adjust any other settings to your liking ft top of this page Last updated August 30 2013 2 of 2 12 6 2013 3 56 PM
Download Pdf Manuals
Related Search