SIL UND 2010 LING 507: Computational Syntax and Morphology Calendar

NB: All materials in the links of the table below are listed in their LING 507 Computational Syntax and Morphology folders on the SIL-UND fileserver and therefore are not currently working. Sample lectures and quizzes are provided.

#	Date	Topic	Assignment	Quiz
1	06/08/10	Introduction to Computational Linguistics Readings Parsing vs. Text Processing in dictionary construction (Ahlswede & Evens 1988) What is computational linguistics (Hans Uszkoreit, 2000, http://www.coli.uni-saarland.de/~hansu/what_is_cl.html) What do computational linguists needs to know about linguistics (Moore 2009) Topics covered What is Computational Linguistics Introduction to Computational Syntax FSMs Chomsky hierarchy Syntactic parsing with CFGs Parsing vs. text processing Material presented Lecture: Introduction to Computational Syntax (presentation, pdf)	Assignment_June10.pdf Writing assignments: Summaries of the articles in the readings list	Quiz_Fri_June_11
2	06/14/10	Unix text processing and regular expressions Readings Using Natural Language to Access Databases on the Web (Hongchi et al 2001) Text Mining with Information Extraction (Nahm and Mooney 2002) Data-driven Dependency Parsing across Languages and Domains: Perspectives from the CoNLL 2007 Shared Task (Nivre 2007) Extracting a verb lexicon for deep parsing from FrameNet (McConville and Dzikovska 2005) Topics covered Unix file management commands Unix text processing techniques Finite State morphology: FSAs and RegEx's Material presented Lecture: FSAs and Regexs (presentation, pdf) Lecture: Regexs & FSAs part 2 (presentation, pdf) Unix file management: Handout_1.pdf Unix file management and text processing: Handout_2.pdf Unix file management and text processing: Handout_3.pdf	Unix_Assignment_1.pdf Unix_Assignment_2.pdf Unix_Assignment_3.pdf Writing assignments: Summaries of the articles in the readings list	Quiz_Fri_June_18
3	06/21/10	Information Extraction and text processing Readings ExPRESS – Extraction Pattern Recognition Engine and Specification Suite (Piskorski 2007) Information Extraction (McCallum 2005) TextAnalysisInternational-IDE-VisualText (Text Analysis International Inc, 2001) Hierarchical Hidden Markov Models for Information Extraction (Skounakis, Craven and Ray 2003) Topics covered Information Extraction (IE): – What is Information Extraction (IE)? – What types of terms are usually extracted? – What are two approaches to building extraction systems? – How is the output usually evaluated? – List some applications of IE Regex metacharacters More on grep processing Relevance, Recall and Precision metrics The concept of greediness in pattern matching Material presented Lecture: Introduction to IE (presentation, pdf) Lecture: IE challenges (presentation, pdf) Handout: Relevance, P, R.pdf Handout: Regex metacharacters.pdf Handout: Dots, greediness and white spaces.pdf Unix Handout 5.pdf Unix Handout 6.pdf Project proposals due: drafts by end of wk3	Unix_Assignment_5.pdf Unix_Assignment_6.pdf Writing assignments: Summaries of the articles in the readings list	Quiz_Fri_June_25
4	06/28/10	Advanced text processing techniques (sed, regex's and automatic entity annotation and extraction) Readings Campbell et al. 2009. Practical Programming: An Introduction to Computer Science using Python.[ch1&2] Automatic Alignment In ParallelCorpora (Papageorgiou, Cranias, Piperidis 1994) Topics covered Unix text processing commands: – Removing dup's – Translating txt – Word freq's: uniq -c – A few more sed commands VisualText: – entity types vs. entity terms – entity relationships Open_CALAIS: demo Notepadd++: regex's and proper name entity recognition and extraction Material presented Unix_Handout_7.pdf Notepad++ Regex Exercise.pdf Handout_6302010_advanced_text_processing.pdf Handout: Points to remember_Append_Uniq.pdf Project proposals due: drafts by end of wk4	Assignment_7.pdf Assignment_8.pdf Assignment_9.pdf Writing assignments: Summaries of the articles in the readings list	Quiz_Fri_July_2
5	07/06/10	VisualText: natural language processing and hands-on rule writing for the automatic recognition, annotation and extraction of named entities in text Readings Brian Roark and Richard Sproat. 2007. Computational Approaches to Morphology and Syntax. Oxford University Press [pp.1-19 and pp.62-66] Computing with Realizational Morphology (Karttunen 2003) The Corpus-based Approach: A New Paradigm in Translation Studies (Laviosa 1998) Automatic Construction of English/Chinese Parallel Corpora (Yang & Wing Li 2003) Topics covered VisualText: – How to create a new analyzer – How to select an initial template – How to reload your new analyzer – How to create an input file – How to run the analyzer and view the parse tree – How to generate built-in rules from sample data – How to create a stub for the passes and pass files – How to create concepts and concept folders for the generated rules – How to populate the concepts with sample data – How to generate built-in rules from the sample data Extra Lab Visual Text rule-writing: – How to write your own rules for finding NPs, VPs, PPs and Possessive Phrases – How to use simple NLP++ syntax for rule-writing Realizational morphology Material presented Lecture: Introduction to Computational Morphology (presentation, pdf) Visual Text Tutorials: based on VisualText Help (part of the VisualText IDE) Informal mid-term course evaluation (template)	Assignment_07072010.pdf Assignment_VisualText_POS_tagging.pdf* Writing assignments: Summaries of the articles in the readings list *See class overview: week 5 class 2 Wed 07072010.pdf	Quiz_Fri_July_9
6	07/12/10	Corpus linguistics tools and techniques Readings English Corpus Introduction: An introduction (Meyer 2002, pp. 1-19) A Computer-assisted Approach to the Analysis of Translation Shifts (Munday 1998) Web As Parallel Corpus (Resnik and Smith 2003) Corpus Analysis For Indexing (Oliveira et all 2005) Exploiting Parallel Texts for WSD (Ng et al 2003) Translation Prediction using Word Coocurrence graphs (Apidianaki 2005) Topics covered Unix file and dir permissions More advanced sed commands Corpus linguistics: – techniques, principles and best practices – concordancing and concordancers – lexical priming and semantic prosody – denotation vs. collocations and colligations and semantic associations – techniques for mining corpora (KWIC, comparison across different corpora, freq's, etc.) Tool: Wordsmith How To Material presented Lecture: Introduction to Corpus Lx part1.pdf Unix_Handout_7122010.pdf Unix_Handout_7132010.pdf Handout: CorpusBased Translation using WordSmith.pdf [includes corpora mining exercises on WordSmith]	Assignment_07122010.pdf Assignment_07132010.pdf Corpora hands on #1.pdf Writing assignments: Summaries of the articles in the readings list	Quiz_Fri_July_16
7	07/19/10	Python Regex module, advanced string manipulation, morphological parsing using FLEx, interlinear texts Readings: Campbell et al. 2009. Practical Programming: An Introduction to Computer Science using Python. [pp. 29-39 and 153-176] A Formal Framework For Interlinear Text (Maeda and Bird 2000) The SIL FieldWorks Language Explorer Approach to Morphological Parsing (Black and Simons, 2006) Topics covered Complex Unix strings and string manipulation Toolbox: demo FLEx: demo Python IDLE and shell Python: RE module Python: string manipulation and regex's Morphological parsing, interlinear text Material presented Handout: Anagram_Eric_Clapton.pdf Handout_7192010.pdf: string manipulation Handout_7202010_part2.pdf: string manipulation Handout_7202010_part3.pdf: string manipulation Python_IDLE_intro_part_1.pdf Python_IDLE_intro_part_2_REs_string_man.pdf Python_IDLE_intro_part_3_more_REs&strings.pdf	Assignment_07192010.pdf Assignment_07202010.pdf Assignment_07212010.pdf Assignment_2_07212010.pdf Assignment_07222010.pdf Writing assignments: Summaries of the articles in the readings list	Quiz_Fri_July_23
8	07/26/10	Machine Translation: shallow transfer for closely-related languages (and Python cont.) Readings Campbell et al. 2009. Practical Programming: An Introduction to Computer Science using Python.[ch.3,4,8] Shallow-transfer rule-based machine translation for Swedish to Danish (Tyers and Nordfalk 2009) Shallow Parsing for Portuguese–Spanish Machine Translation (Garrido-Alenda et al 2004) Topics covered Machine translation: – models, approaches, evaluation metrics and challenges – shallow transfer of closely-related languages Parsing street addresses using Python Parsing phone numbers using Python Parsing NL input, extracting and tagging NL elements using Python How to write to files in Python Material presented Lecture: Overview of MT models, approaches, challenges.pdf Handout: Python_RE_case_study_1.pdf Handout: Python_RE_case_study_2.pdf Handout: Python_RE_case_study_3_ExtractingFromSs.pdf Handout: Python_RE_case_study_4.pdf Handout: Python_NLTK.pdf Machine translation freeware tools: demo Dissemination of final project template: Monday 7/26 Students' final project write-up's due: Friday 7/30 by 4pm	Python_RE_case_study_1.pdf Python_RE_case_study_2.pdf Python_RE_case_study_3_ExtractingFromSs.pdf Python_RE_case_study_4.pdf Writing assignments: Summaries of the articles in the readings list	final quiz 7/30
9	08/02/10	Student in-class presentations and project evaluations -handouts -I/O sample -demo of proposed implementation Final course evaluations		No quiz

Copyright © Eleni Koutsomitopoulou 2010 All Rights Reserved. No part of this document may be reproduced or otherwise used without the written consent of the author.