Online Papers

Categorised References

(This list is no longer maintained)

Extraction type	Generation type	Title	Authors	Date	Institution	Corpus	Evaluation Metric
Machine Learning features cue phrase location sentence length thematic word title	null	Sentence extraction as a classification task	Teufel Moens	1997	Edinburgh	Self-collected computational linguistics papers	precision recall
		Sentence extraction and rhetorical classification for flexible abstracts	Teufel Moens	1998	Edinburgh
Stats-TFLF with POS in aligning text spans	null	Generating Extraction-Based Summaries from Hand-Written Summaries by Aligning Text Spans	Banko Mittal Kantrowitz Goldstein	1999	Just Research CMU	Self Collected news from Reuters and LA Times	null
		Summarizing Text Documents: Sentence Selection and Evaluation Metrics	Goldstein Kantrowitz Mittal Carbonell	1999	Just Research CMU
Statistical Models	null	Ultra-Summarization: A Statistical Approach to Generating Highly Condensed Non-extractive Summaries	Witbrock Mittal	1999	Lycos Just Research	Reuters news-wire articles and Associated Press (in LDC)
Statistical Models noisy channel Probabilistic Context-free Grammar score Decision-based model (Shift-Reduce-drop)	null	Statistics-Based Summarization -- Step One: Sentence Compression	Knight Marcu	2000	USC: ISI	Ziff-Davis corpus	T-test
		Robust Automated Topic Identification, PhD Thesis	Lin	1997	USC: ISI
		Automated Text Summarization in SUMMARIST	Hovy Lin	1997	USC: ISI
		Identifying Topics by Position	Lin	1997	USC: ISI
		An Architecture for Aggregation in Text Generation	Shaw McKeown	1997	Columbia Univ.
Hidden Markov Model Viterbi Algorithm		The Decomposition of Human-Written Summary Sentences	Jing McKeown	1999	Columbia Univ.	Ziff-Davis	Precision-recall
Identifying Themes: Features: word co-occurence matching NP WordNet synonyms common verb semantic classes Cohen's Machine Learning Alg for classifierdecision	Content choosing: Collins parser on themes Dependency Grammar Representation Generation: FUF-SURGE	Towards Multidocument Summarization by Reformulation: Progress and Prospects	McKeown Klavans Hatzivassiloglou Barzilay Eskin	1999	Columbia Univ Ben Gurion Univ	Topic Detection and Tracking (TDT)	not available
		Information Fusion in the Context of Multi-Document Summarization	Barzilay McKeown Elhadad	1999	Columbia Univ Ben Gurion Univ.
		Resources for the Evaluation of Summarization Techniques	Klavans McKeown Kan Lee	1998	Columbia Univ.
		Information Extraction and Summarization: Domain Independence through Focus Types	Kan McKeown	????	Columbia Univ.
n/a	n/a	Summarization Evaluation Methods: Experiments and Analysis	Jing Barzilay Mckeown Elhadad	1998	Columbia Univ. Ben Gurion Univ.	TREC collection computer terrorism hypnosis nuclear treaties	precision-recall
Lexical Chains WordNet		Using Lexical Chains for Text Summarization	Barzilay Elhadad	1997	Ben Hurion University, Israel	self-collected 30 random popular magazine aticles	Cochrans test
		Summarization of Multiple Documents Clustering Sentence Extraction and Evaluation	Radev Jing Budzikowska	2000	Columbia Univ.
		Language Reuse and Regeneration: Generating Natural Language Summaries from Multiple On-Line Sources, PhD thesis	Radev	1999	Columbia Univ.
		Generating Summaries of Multiple News Articles	Radev McKeown	1998	Columbia Univ.
MUC templates	Schemas	Generating Natural Language Summaries from Multiple On-Line Sources	Radev McKeown	1998	Columbia Univ.	DARPA MUC	SUMMONS
		An Architecture for distributed Natural Language Summarization	Radev	1996	Columbia Univ.
		A Trainable Document Summarizer	Kupiec Pedersen Chen	1995	Xerox Parc
Genetic Algorithms C4.5	null	Learning Algorithms	Turney	2000	Tetranet
n/a	n/a	SUMMAC TIPSTER final report	Inderjeet Mani David House Gary Klein Lynette Hirschman Leo Orbrst Therese Firmin Michael Chrzanowski Beth Sunheim	1998	NIST

Other (as yet uncategorised) online references

Byron Georgantopoulos' MSc dissertation: Automatic summarising based on sentence extraction: A statistical approach
Klaus Zechner: (CMU LTI)
W.J. Black: "Parsing, Linguistic Resources and Semantic Analysis for Abstracting and Categorization"
Karen Sparck Jones: Automatic summarising: factors and directions
Hyuk R. Park (Chonnam National University), Young S. Han (Suwon University), Tae H. Kim (Korea R&D Information Center)
Heuristic algorithms for automatic summarization of Korean texts
M. Aretoulaki, COSY-MATS: A Hybrid Connectionist-Symbolic Approach To The Pragmatic Analysis of Texts For Their Automatic Summarisation , Ph.D. Thesis, Dept. of Language Engineering, U.M.I.S.T., Manchester, U.K., March 1996.
M. Aretoulaki, "Chapter 4: Towards a Hybrid Abstract Generation System" . In D. Jones & H. Somers (Eds.), New Methods in Language Processing , UCL Press, London, U.K. June 1997.
M. Aretoulaki, COSY-MATS: An Intelligent and Scalable Summarisation Shell . In Proceedings of the ACL'97/EACL'97 Workshop on Intelligent Scalable Text Summarization (ISTS'97) , Madrid, Spain, July 11, 1997.
M. Aretoulaki, G. Scheler, & W. Brauer, Connectionist Modeling of Human Event Memorization Processes with Application to Automatic Text Summarization . In Proceedings of AAAI 1998 Spring Symposium on Intelligent Text Summarization , Stanford University, California, March 23--25, 1998.
Automatic Text Summarization by Paragraph Extraction. Mandar Mitra, Amit Singhal, Chris Buckley. Proceedings of the ACL Workshop on Intelligent and Scalable Text Summarization, 39-46, 1997.
Automatic Text Decomposition Using Text Segments and Text Themes. Gerard Salton, Amit Singhal, Chris Buckley, Mandar Mitra, Hypertext '96, 53-65, 1996.