Course: Semantic Analysis in Language Technology

Uppsala University, Sweden

Uppsala University, Sweden

Uppsala University: Department of Linguistics and Philology

Semantic Analysis in Language Technology (2013)

 

 

 

 

Credits: 7,5 hp
Syllabus: 5LN456
Teacher: Marina Santini

The course website will be update regularly during the teaching session with additional material.

Last Updated: 23 October 2013

Course website: http://stp.lingfil.uu.se/~santinim/sais/sais_fall2013.htm

Nov, 12
(Tue)
10‑12 9-2042
(Turing)
Course introduction [OH]. J&M 17–18
Nov, 14
(Thu)
10-12 9-2042
(Turing)
Introduction to essay assignment (EA) [OH].
Nov, 19
(Tue)
10-12 9-2042
(Turing)
IE/PAS, PAS assignment [OH] Johansson and Nugues 2008, J&M 20.9
Nov, 21
(Thu)
10-12 9-2042
(Turing)
EA and PAS supervision
Nov, 26
(Tue)
10-12 9-2042
(Turing)
Sentiment analysis BL 1–4
Nov, 28
(Thu)
10-12 9-2042
(Turing)
Sentiment analysis BL 5–7
Dec, 03
(Tue)
10-12 9-2042
(Turing)
Supervision
Dec, 06
(Thu)
Deadline EA, step 1
Dec, 10
(Tue)
10-12 9-2042
(Turing)
EA presentations
Dec, 12
(Thu)
10-12 9-2042
(Turing)
WSD [OH] J&M 19–20.
Dec, 17
(Tue)
10-12 9-2042
(Turing)
WSD. Deadline EA, feedback to another
group
(link to submitted essays below)
Jan, 20
(Mon)
2014-01-20: Deadline, all assignments

Intended learning outcomes

In order to pass the course, a student must be able to:

describe systems that perform the following tasks,
apply them to authentic linguistic data, and evaluate the results:

  • disambiguate instances of polysemous lemmas [word sense
    disambiguation, WSD];
  • use semantic analysis in the context of information extraction [IE];
  • use robust methods to extract the predicate-argument structure [PAS];
  • detect and extract attitudes and opinions from text [“sentiment analysis”].

Assignments and examination

  • Essay assignment: This will involve a more independent
    study of a system, an approach, or a field within semantics-oriented
    language technology. The study will be presented both as a written
    essay and an oral presentation. The essay work will also include a
    feedback step where the work of another group is reviewed. (This is
    intended to provide training useful for later larger essay projects.)
    Read more in the OH-pictures.
    Submitted essays.
  • Assignment on PAS.
  • Assignment on sentiment analysis.
  • Assignment on WSD.

Grade G will be given to students who pass each assignment. Grade
VG to those who pass the essay assignment and at least one of the other ones
with distinction.

Reading list

Additional material will be used, in particular for the essay assignment.

Bing Liu (2012) Sentiment Analysis and Opinion Mining, Morgan & Claypool. Pdf for UU students at the publishers websiteThe author’s slides.

Richard Johansson and Pierre Nugues. 2008. Dependency-based Syntactic–Semantic Analysis with PropBank and NomBankCoNLL 2008: Proceedings of the 12th Conference on Computational Natural Language Learning.

Daniel Jurafsky and James H. Martin (2009), Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Second Edition, Pearson Education.

Daniel Gildea and Daniel Jurafsky. 2002. Automatic Labeling of Semantic RolesComputational Linguistics 28:3, 245-288.

M Palmer, D Gildea, P Kingsbury. 2005. The proposition bank: An annotated corpus of semantic rolesComputational Linguistics 31 (1), 71-106.

Demos, etc.

Semantic role labeling/predicate argument structure analysis

Enju – Predicate argument structure analysis, University of Tokyo. Online demo. (Also installed at our Linux network.)

Semantic role labeller (Richard Johansson, Lunds universitet). Online demo.

Semantic Role Labeling: Online demo, University of Illinois at Urbana-Champaign.

LinGO English Resource Grammar Online demo.

FrameNet.dk.

Proposition Bank.

Olga Babko-Malaya 2005. PropBank Annotation Guidelines.

Unified Verb Index (find PropBank analyses of verbs).

Information extraction

ANNIE – Information extraction system, University of Sheffield.

Open Information Extraction, University of Washington.

START,a Web-based question answering system, MIT.

Sentiment analysis – document level

Sentiment Analysis Online demo. Python NLTK Text Classification.

Lexalytics, sentiment analysis.

TrustYou Labs, statistical sentiment analysis.

Sentiment analysis – Twitter data

Sentiment140 – A Twitter Sentiment Analysis Tool. Search by product or brand. Discover the Twitter sentiment.

Tweetfeel.

Tweettone.

Sentiment analysis – more

Sentiment Tutorial. LingPipe – tool kit for processing text using computational linguistics (written in Java).

Leave a Reply

Your email address will not be published. Required fields are marked *

*