Ruprecht-Karls-Universität Heidelberg
Institut für Computerlinguistik

Bilder vom Neuenheimer Feld, Heidelberg und der Universität Heidelberg

Automatic Text Summarization

Kursbeschreibung

Studiengang Modulkürzel Leistungs-
bewertung
BA-2010[100%|75%] CS-CL 6 LP
BA-2010[50%] BS-CL 6 LP
BA-2010[25%] BS-AC, BS-FL 4 LP
NBA[100%|75%] CS-CL 6 LP
NBA[50%|25%] BS-CL, BS-AC 4 LP
Magister - -
Dozenten/-innen Tri Duc Nghiem
email: my_last_name@cl_domain
Veranstaltungsart Proseminar
Erster Termin 22.10.2014
Zeit und Ort Mi, 14:1515:45, INF 325 / SR 24 (SR)
Commitment-Frist 18.01.2015

Teilnahmevoraussetzungen

To register, please send an e-mail to the lecturer (better in English), Subject starts with [Reg-SummarizationWS14]

Leistungsnachweis

Inhalt

Text summarization is the process of reducing a text document in order to create a summary that retains the most important information of the original document. As the problem of information overload has grown, and as the quantity of data has increased, so has interest in automatic summarization. Techniques for producing coherent summary/ies take into account variables such as length, writing style and syntax.

The goal of the seminar is to introduce basic methods for text summarization with an overview of current approaches along with some practical exercises. In particular, we will look at single and multi-document summarization approaches, as well as specialized forms, such as update summarization, aspect-based and query-based summarization.

Kursübersicht

Seminarplan

Datum Sitzung Materialien
22.10.2014 Introduction Introduction
List of Papers
27.10.2014 Rada Mihalcea (2004) Graph-based ranking algorithms for sentence extraction, applied to text summarization
Clarke, James & Mirella Lapata (2007). Modelling compression with discourse constraints. (Xenia Kuehling)
Hanah Becker , Xenia Kuehling
05.11.2014 Lin (2004). Rouge: A package for automatic evaluation of summaries(Atilla Azgin)
, Harnly et al. (2005). Automation of summary evaluation by the pyramid method (Bettina Emmerich)
Atilla Azgin , Bettina Emmerich
12.11.2014 Banko et al. (2000). Headline generation based on statistical translation (Jasper Bischofberger)
Zhou and Hovy (2004). Template-filtered headline summarization (Duc)
Jasper Bischofberger,
Duc
19.11.2014 Dorr et al. (2003) Hedge trimmer: A parse-and-trim approache to headline generation (Kai-Fabian Rudolf)
Xu et al. (2010) Keyword extraction and headline generation using novel word features. (Max Bacher)
Kai-Fabian,
Max Bacher
26.11.2014 Branavan et al (2007) Generating table-of-contents
, Moens (2008). Using patterns of thematic progression for bulding a table of contents of a text. (Carolin Guenzel; Tobian Goebel; Darmin Spahic)
Guenzel ,
Goebel_Spahic
03.12.2014 Erkan and Radev (2004). Lexrank: Graph-based lexical centrality as salience in text summarization. (Hanna Hees; Miriam Klowersa) Hees_Klowersa
10.12.2014 Barzilay and Elhadad (1999) Using lexical chains for text summarization (Lukas Muelleder)
Azzam et al. (1999) Using coreference chains for text summarization (Julius Steen)
Lukas Muelleder ,
Julius Steen
17.12.2014 Bergler et al. (2003). Using knowledge-poor coreference resolution for text summarization (Janos Seboek)
07.01.2015 Ganesan et al. (2010). A graph based approach to abstractive summarization of highly redundant opinions (Tamas Janusko)
Pighin et al. (2014). Modelling events through memory-based, open-ie patterns for abstractive summarization (??)
Tamas Janusko
14.01.2015 Mehdad et al. (2014). Abstractive summarization of spoken and written conversations based on phrasal queries. (Fritz Devon)
Zhou and Hovy (2005). Digesting virtual “geek” culture: The summarization of technical internet relay chats. (Raphael Schumann)
Optional: Olariu (2014). Efficient online summarization of microblogging streams.
Schumann
21.01.2015 Radev et al. (2010) Centroid-based summarization of mutliple documents: Sentence extraction, utility-based evaluation, and user studies. (Westphal Robin)
Zhou et al. (2004) Multi-document Biography Summarization (Iryna Foster)
Iryna Forster
28.01.2015 Ng et al. (2014) Exploiting timelines to enhance multi-document summarization. (??)
Christensen et al. (2014) Hierarchical summarization: Scaling up multi-document summarization. (Dorothea Hoff)
Dorothea Hoff
04.02.2015 Baumel et al. (2014) Query-chain focused summarization. (?)

Literatur

Literatur: The main texts and slides in the lecture use materials in

» weitere Kursmaterialien

zum Seitenanfang