Difference between revisions of "Structured Prediction 10-710 in Fall 2011"

From Cohen Courses
Jump to navigationJump to search
 
(44 intermediate revisions by 18 users not shown)
Line 37: Line 37:
 
* The class project
 
* The class project
 
** Choose teams and a general project topic.  (This can change in the coming weeks/month.)  Create a team wiki page, add its members and the project topic.  Every team member then should link to it from their own user homepage.
 
** Choose teams and a general project topic.  (This can change in the coming weeks/month.)  Create a team wiki page, add its members and the project topic.  Every team member then should link to it from their own user homepage.
 +
** Final reports should be in the [http://www.icml-2011.org/format.php ICML 2011 format].  Aim for 6-10 pages including citations.  Please be concise; we do not encourage you to write a report that is longer than necessary.
 
* [[Wiki writeup assignments for 10-710 in Fall 2011|Wiki writeup assignments]]
 
* [[Wiki writeup assignments for 10-710 in Fall 2011|Wiki writeup assignments]]
 
* Class participation
 
* Class participation
  
 
== Attendees ==
 
== Attendees ==
 
'''Assignment for 9/6: Everyone must make a user home page, as User:USERNAME'''
 
  
 
People taking this class in Fall 2011 include:
 
People taking this class in Fall 2011 include:
* [[User:Ajuarez|Antonio Juárez López]]
 
 
* [[User:Dmovshov|Dana Movshovitz-Attias]]
 
* [[User:Dmovshov|Dana Movshovitz-Attias]]
 
* [[User:Ysim|Yanchuan Sim (yc)]]
 
* [[User:Ysim|Yanchuan Sim (yc)]]
* [[User:Yww|William Yang Wang]]
 
* [[User:Akoul|Anirudh Koul]]
 
 
* [[User:Asaluja|Avneesh Saluja]]
 
* [[User:Asaluja|Avneesh Saluja]]
 
* [[User:Junyangn|Junyang Ng]]
 
* [[User:Junyangn|Junyang Ng]]
Line 59: Line 55:
 
* [[User:cheuktol|Cheuk To Law (Kelvin)]]
 
* [[User:cheuktol|Cheuk To Law (Kelvin)]]
 
* [[User:manajs|Manaj Srivastava]]
 
* [[User:manajs|Manaj Srivastava]]
* [[User:Avinava.dubey| Avinava Dubey]]
 
 
* [[User:Fkeith|Francis Keith]]
 
* [[User:Fkeith|Francis Keith]]
 
* [[User:Dkulkarn|Dhananjay Kulkarni]]
 
* [[User:Dkulkarn|Dhananjay Kulkarni]]
 +
* [[User:Yww|William Yang Wang]]
 
* [[User:Emayfiel|Elijah Mayfield]]
 
* [[User:Emayfiel|Elijah Mayfield]]
 
* [[User:Taruns|Tarun Sharma]]
 
* [[User:Taruns|Tarun Sharma]]
Line 71: Line 67:
 
* [[User:Howarth| Dan Howarth]]
 
* [[User:Howarth| Dan Howarth]]
 
* [[User:Dwijaya| Derry Wijaya]]
 
* [[User:Dwijaya| Derry Wijaya]]
 +
* [[User:Jmflanig| Jeff Flanigan]]
 +
* [[User:Tkumar| Tarun Kumar]]
 +
 
* [[User:akgoyal| Anuj Goyal]]
 
* [[User:akgoyal| Anuj Goyal]]
 +
* [[User:Avinava.dubey| Avinava Dubey]]
 +
* [[User:Dyogatam| Dani Yogatama]]
  
 
Here are sample pages for [[User:Wcohen|William]], [[User:Nasmith|Noah]], and [[User:Brendan|Brendan]].
 
Here are sample pages for [[User:Wcohen|William]], [[User:Nasmith|Noah]], and [[User:Brendan|Brendan]].
  
== Possible Projects ==
+
== Projects ==
  
If you have an idea for a possible project, list it here, as William has done in the example.  This is for coordination and brainstorming at this point. You probably want to include your name and the names of your team-mates in the project description.
+
== Final presentation dates ==
  
 +
Tues 12/6
 +
* 3:05 Word Alignments using an HMM-based model - Wang Ling and Rui Correia
 +
* 3:17 Training SMT Systems with the Latent Structured SVM - Avneesh Saluja and Jeff Flanigan
 +
* 3:29 Semi-supervised Generation of Wikipedia Infoboxes - Wangshu Pang, Yun Wang and Matt Gardner
 +
* 3:41 Relevant Information Extraction from Court-room Hearings To Predict Judgement - Manaj Srivastava, Mridul Gupta
 +
* 3:53 Stylistic Structure Extraction from Early United States Slave-related Legal Opinions William Y. Wang and Elijah Mayfield
 +
* 4:05 Restaurant Recommendations Based On Review Content (updated!) - Junyang Ng, Yan Chuan Sim, Kelvin Law
 +
 +
Thurs 12/8
 +
* 3:05 Automated Template Extraction - Francis Keith, Andrew Rodriguez
 +
* 3:17 Learning Indian Classical Music Using Sequential Models - Dhananjay Kulkarni, Tarun Kumar
 +
* 3:29 Finding out who you are from where, when, what and with whom you tweet - Derry Wijaya, Tarun Sharma
 +
* 3:41 Wikipedia Infobox Generator Using Cross Lingual Unstructured Text - Daegun Won and Tony Navas
 +
* 3:53 Identifying Abbreviations in Biomedical Text - Dana Movshovitz-Attias
 +
 +
 +
== Project list ==
 +
 +
(should get comments from Brendan:)
 +
* [[Automated Template Extraction]] - [[User:Fkeith|Francis Keith]], [[User:amr1|Andrew Rodriguez]]
 +
* [[Project:Tweet | Finding out who you are from where, when, what and with whom you tweet]] - [[User:Dwijaya|Derry Wijaya]], [[User:taruns|Tarun Sharma]]
 +
* [[Information_Extraction_to_Predict_Judgement|Relevant Information Extraction from Court-room Hearings To Predict Judgement]] - [[User:manajs|Manaj Srivastava]], [[User:mridulg|Mridul Gupta]]
 +
 +
(should get comments from Noah:)
 +
* [[Stylistic Structure in Historic Legal Text|Stylistic Structure Extraction from Early United States Slave-related Legal Opinions]] [[User:Yww|William Y. Wang]] and [[User:Emayfiel|Elijah Mayfield]]
 +
* [[Word Alignments using an HMM-based model]] - [[User:Lingwang|Wang Ling]] and [[User:Ruipedrocorreia|Rui Correia]]
 +
* [[Training SMT Systems with the Latent Structured SVM]] - [[User:Asaluja|Avneesh Saluja]] and [[User:Jmflanig| Jeff Flanigan]]
 +
* [[Wikipedia Infobox Generator Using Cross Lingual Unstructured Text]] - [[User:Daegunw|Daegun Won]] and [[User:Aanavas|Tony Navas]]
 +
 +
(should get comments from William:)
 +
* [[Semi-supervised Generation of Wikipedia Infoboxes]] - [[User:wpang|Wangshu Pang]], [[User:Yunwang|Yun Wang]] and [[User:Mg1|Matt Gardner]]
 +
* [[Restaurant Recommendations Based On Review Content]]  (updated!) - [[User:Junyangn|Junyang Ng]], [[User:Ysim| Yan Chuan Sim]], [[User:Cheuktol|Kelvin Law]]
 +
* [[Project:Dmovshov_abbreviations | Identifying Abbreviations in Biomedical Text]] - [[User:Dmovshov|Dana Movshovitz-Attias]]
 +
* [[Project:Learning_Indian_Classical_Using_Sequential_Models| Learning Indian Classical Music Using Sequential Models]] - [[User:dkulkarn|Dhananjay Kulkarni]], [[User:tkumar|Tarun Kumar]]
 +
 +
(older ideas:)
 +
* [[Improving SMT word alignment with binary feedback]] - [[User:Asaluja|Avneesh Saluja]] and [[User:Jmflanig| Jeff Flanigan]]
 +
* [[Linearizing Dependency Trees]] - [[User:Jmflanig| Jeff Flanigan]]
 
* [[Mapping entity names in a document to places on a map]].
 
* [[Mapping entity names in a document to places on a map]].
* [[Wikipedia Infobox Generator Using Cross Lingual Unstructured Text]] - [[User:Akoul|Anirudh Koul]], [[User:Daegunw|Daegun Won]] and [[User:Aanavas|Tony Navas]]
 
* Automatic extraction of answering patterns for Question Answering -  [[User:Akoul|Anirudh Koul]]
 
* Including a knowledge base into Haghighi & Klein's coreference resolution system - [[User:Mg1|Matt Gardner]], [[User:Avinava.dubey|Avinava Dubey]]
 
* [[Stylistic Structure in Historic Legal Text|Stylistic Structure Extraction from Early United States Slave-related Legal Opinions]] [[User:Yww|William Y. Wang]] and [[User:Emayfiel|Elijah Mayfield]]
 
 
* Automatically generating headings for sections (group of contiguous paragraph) in unstructured text  
 
* Automatically generating headings for sections (group of contiguous paragraph) in unstructured text  
* Extract structured information from Wikipedia - [[User:wpang|Wangshu Pang]] and [[User:Yunwang|Yun Wang]]
 
* [[Word Alignments using an HMM-based model]] - [[User:Lingwang|Wang Ling]] and [[User:Ruipedrocorreia|Rui Correia]]
 
* [[Improving SMT word alignment with binary feedback]] - [[User:Asaluja|Avneesh Saluja]]
 
* [[Building domain specific NERs by using information from domain-general annotations]] - [[User:Junyangn|Junyang Ng]], [[User:Ysim| Yan Chuan Sim]], [[User:Cheuktol|Kelvin Law]]
 
* [[Information_Extraction_to_Predict_Judgement|Relevant Information Extraction from Court-room Hearings To Predict Judgement]] - [[User:manajs|Manaj Srivastava]], [[User:mridulg|Mridul Gupta]]
 
* [[Identifying Abbreviations in Biomedical Text]] - [[User:Dmovshov|Dana Movshovitz-Attias]]
 
  
 
In general, a nice way to find already-made datasets is to read papers in the literature and see what they use and reference.  A few data ideas: [[Project Brainstorming for 10-710 in Fall 2011/Some data ideas]]
 
In general, a nice way to find already-made datasets is to read papers in the literature and see what they use and reference.  A few data ideas: [[Project Brainstorming for 10-710 in Fall 2011/Some data ideas]]

Latest revision as of 14:11, 30 November 2011

Instructor and Venue

  • Instructors: William Cohen and Noah Smith, Machine Learning Dept and LTI
  • Course secretary: Sharon Cavlovich, sharonw+@cs.cmu.edu, 412-268-5196
  • When/where: Tues-Thursday 3:00-4:20 in Gates-Hillman 4211
  • Course Number: ML 10-710 and LTI 11-763
  • Prerequisites: a machine learning course (e.g., 10-701 or 10-601) or consent of the instructor.
  • TA: Brendan O'Connor
  • Syllabus: Syllabus for Structured Prediction 10-710 in Fall 2011
  • Office hours:
    • Noah, GHC 5723, Thursdays 4:30-5:30 (starting 9/8)
    • Brendan, GHC 8005, Tuesdays 4:30-5:30
    • William, GHC 8217, Fridays 11:00-12:00 (starting 9/16)

Description

This course seeks to cover statistical modeling techniques for discrete, structured data such as text. It brings together content previously covered in Language and Statistics 2 (11-762) and Information Extraction (10-707 and 11-748), and aims to define a canonical set of models and techniques applicable to problems in natural language processing, information extraction, and other application areas. Upon completion, students will have a broad understanding of machine learning techniques for structured outputs, will be able to develop appropriate algorithms for use in new research, and will be able to critically read related literature. The course is organized around methods, with example tasks introduced throughout.

The prerequisite is Machine Learning (10-601 or 10-701), or permission of the instructors.

Syllabus

Older syllabi:

Readings

Unless there's announcement to the contrary, required readings should be done before the class.

Grading

Grades are based on

  • The class project
    • Choose teams and a general project topic. (This can change in the coming weeks/month.) Create a team wiki page, add its members and the project topic. Every team member then should link to it from their own user homepage.
    • Final reports should be in the ICML 2011 format. Aim for 6-10 pages including citations. Please be concise; we do not encourage you to write a report that is longer than necessary.
  • Wiki writeup assignments
  • Class participation

Attendees

People taking this class in Fall 2011 include:

Here are sample pages for William, Noah, and Brendan.

Projects

Final presentation dates

Tues 12/6

  • 3:05 Word Alignments using an HMM-based model - Wang Ling and Rui Correia
  • 3:17 Training SMT Systems with the Latent Structured SVM - Avneesh Saluja and Jeff Flanigan
  • 3:29 Semi-supervised Generation of Wikipedia Infoboxes - Wangshu Pang, Yun Wang and Matt Gardner
  • 3:41 Relevant Information Extraction from Court-room Hearings To Predict Judgement - Manaj Srivastava, Mridul Gupta
  • 3:53 Stylistic Structure Extraction from Early United States Slave-related Legal Opinions William Y. Wang and Elijah Mayfield
  • 4:05 Restaurant Recommendations Based On Review Content (updated!) - Junyang Ng, Yan Chuan Sim, Kelvin Law

Thurs 12/8

  • 3:05 Automated Template Extraction - Francis Keith, Andrew Rodriguez
  • 3:17 Learning Indian Classical Music Using Sequential Models - Dhananjay Kulkarni, Tarun Kumar
  • 3:29 Finding out who you are from where, when, what and with whom you tweet - Derry Wijaya, Tarun Sharma
  • 3:41 Wikipedia Infobox Generator Using Cross Lingual Unstructured Text - Daegun Won and Tony Navas
  • 3:53 Identifying Abbreviations in Biomedical Text - Dana Movshovitz-Attias


Project list

(should get comments from Brendan:)

(should get comments from Noah:)

(should get comments from William:)

(older ideas:)

In general, a nice way to find already-made datasets is to read papers in the literature and see what they use and reference. A few data ideas: Project Brainstorming for 10-710 in Fall 2011/Some data ideas