Internet-based Information Extraction Technologies

Teacher: Fang Li

Office: SEIEE Building, No.3 Room: 533

Office Time: Tuesday (10~11 AM)

References:

1）Sonit Singh, Natural Language Processing for Information Extraction (2018)

2） Information Extraction: Algorithms and Prospects in a Retrieval Context by Marie-Francine Moens Published by Spinger, (P.O. Box 17, 3300 AA Dordrecht, The Netherlands) . ISBN-13 978-1-4020-4993-4 (e-book)

3）Jerry R.Hobbs, Ellen Riloff, Information Extraction chapter 21 of Handbook of Natural Language Processing (2010).

4）Ralph Grishman. Information Extraction: Capabilities and Challenges (2012)

Introduction:

Internet-based Information extraction (IE) is the method of deriving structured information from unstructured text and semi-structured web pages. More succinctly, information extraction is finding names of the entities, relations and events from the Internet and free text.

The lecture introduces an overview of the history and technologies of information extraction. It presents the state-of-the art research methods and focuses on real world applications.

Readings will be based on the conference articles. Grades will be based on class participation and projects. There is no final examination for this course. Students are encouraged to form a group in order to finish projects and write reports. There are three tasks. Each group can choose two of them and present their project in the class workshop at the end of the semester.

Course Topics and Readings

Weeks	Topics	Slides	Readings & References
1^th	Motivation & Course Introduction	Lecture 1	NELL system
2^th	Basic Knowledge for IE	Lecture 2 WordVectorTutorial	POSforChinese WordVector1 WordVector2
3^th	IE Concepts	Lecture 3 PPT(TA)	Chapter 1 of textbook Chapter 2 of textbook Chapter 8 of textbook
4^th	Holiday
5^th	Named Entity Extraction	Lecture 4-5	Chapter 4 of textbook CRFmodelforORG
6^th	Named Entity Extraction (Discussion & group presentation)	Article Reading and NotesSample	Chapter 5 of textbook Reference1 Reference2 Reference3
7^th	Relation Extraction (pattern-based, supervised, semi-supervised)	Lecture 6	Reference, SVMguide
8^th	Relation Extraction (distant-supervised, deepLearning) & group Discussion	Lecture 7	DistantSupervisionMethod TransE(deepLearning)
9^th	Event extraction	Lecture 8	Chapter9 of textbook Template-based Event extraction without template ALanguage-IndependentNeuralNetworkforEventDetection
10^th	Opinion Mining	Lecture 9	Sentimental Analysis PolarityEmbeddingFusionforRobustSentimentAnalysis SAwithEnsembleofConvolutionalNeuralNetworkswithDistantSupervision
11^th	Opinion Mining	Lecture 10	Turney Algorithm Inducing Domain-specific Sentiment Lexicons from Unlabeled Corpora
12^th	Webpage IE	Lecture 11	surveyofwebIE
13^th	IE system	lecture 12 lecture 13 14	LixTo, Roadrunner Know-it-all, Text runner, OPENIE
14^th	Knowledge Graph (new)
15^th ~16^th	Student Workshop		Each group presents their work which includes: the task, its problems and analysis (2 minutes) Describe your general approach (3 minutes) Your results (3 minutes) Open questions and challenges (2 minutes) , Q&A (5 minutes).

Noted:

The content of each lecture may change every year. The above slides only give you the general information about each lecture. The classroom exercises and discussions are not included in these slides. The new teaching materials are in the Canvas.

Prerequisites

Data Structure, Programming Language, Natural Language Processing

Grading:

1. Attendence & Classroom Discussions (40%)

2. Reading & writing (20%)

3. Algorithm Design (40%)

Project tasks:

1) Specific Relation Extraction. Please see the training data(for employment, chief of, location extraction) , another training data (for four kinds of employment relationship extraction) and student work1 and student work2 presented in the last few years for your references.

2) Positive and negative Sentimental Analysis. Please see the training data for example.

3) Web Page Extraction

About the evaluation:

1) Task1 (employment relation extraction): input file format and output file format.

2) Task2 (positive and negative sentimental analysis) input file format and output file format

3) Specification for evaluation and evaluation tools.