1 / 22

Automatic summarization

Automatic summarization. Dragomir R. Radev University of Michigan radev@umich.edu. Outline. What is summarization Genres of summarization (Single-doc, Multi-doc, Query-based, etc.) Extractive vs. non-extractive summarization Evaluation metrics Current systems Marcu/Knight MEAD/Lemur

salena
Télécharger la présentation

Automatic summarization

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Automatic summarization Dragomir R. Radev University of Michigan radev@umich.edu

  2. Outline • What is summarization • Genres of summarization (Single-doc, Multi-doc, Query-based, etc.) • Extractive vs. non-extractive summarization • Evaluation metrics • Current systems • Marcu/Knight • MEAD/Lemur • NewsInEssence/NewsBlaster • What is possible and what is not

  3. Goal of summarization • Preserve the “most important information” in a document. • Make use of redundancy in text • Maximize information density |S| Compression Ratio = |D| i (S) Retention Ratio = i (D) i (S) |S| Goal: > i (D) |D|

  4. Sentence-extraction based (SE) summarization • Classification problem • Approximation

  5. Typical approaches to SE summarization • Manually-selected features: position, overlap with query, cue words, structure information, overlap with centroid • Reranking: maximal marginal relevance [Carbonell/Goldstein98]

  6. Non-SE summarization • Discourse-based [Marcu97] • Lexical chains [Barzilay&Elhadad97] • Template-based [Radev&McKeown98]

  7. Evaluation metrics • Intrinsic measures • Precision, recall • Kappa • Relative utility [Radev&al.00] • Similarity measures (cosine, overlap, BLEU) • Extrinsic measures • Classification accuracy • Informativeness for question answering • Relevance correlation

  8. Relevance correlation (RC)

  9. Web resources http://www.summarization.com http://duc.nist.gov http://www.newsinessence.com http://www.clsp.jhu.edu/ws2001/groups/asmd/ http://www.cs.columbia.edu/~jing/summarization.html http://www.dcs.shef.ac.uk/~gael/alphalist.html http://www.csi.uottawa.ca/tanka/ts.html http://www.ics.mq.edu.au/~swan/summarization/

  10. Generative probabilistic models for summarization Wessel Kraaij TNO TPD

  11. complexity Summarization architecture • What do human summarizers do? • A: Start from scratch: analyze, transform, synthesize (top down) • B: Select material and revise: “cut and paste summarization” (Jing & McKeown-1999) • Automatic systems: • Extraction: selection of material • Revision: reduction, combination, syntactic transformation, paraphrasing, generalization, sentence reordering Extracts Abstracts

  12. Required knowledge

  13. Examples of generative models in summarization systems • Sentence selection • Sentence / document reduction • Headline generation

  14. Ex. 1: Sentence selection • Conroy et al (DUC 2001): • HMM on sentence level, each state has an associated feature vector (pos,len, #content terms) • Compute probability of being a summary sentence • Kraaij et al (DUC 2001) • Rank sentences according to posterior probability given a mixture model • Grammaticality is OK • Lacks aggregation, generalization, MDS

  15. Ex. 2: Sentence reduction

  16. Knight & Marcu (AAAI2000) • Compression: delete substrings in an informed way (based on parse tree) • Required: PCFG parser, tree aligned training corpus • Channel model: probabilistic model for expansion of a parse tree • Results: much better than NP baseline • Tight control on grammaticality • Mimics revision operations by humans

  17. Daumé & Marcu (ACL2002) • Document compression, noisy channel • Based on syntactic structure and discourse structure (extension of Knight & Marcu model) • Required: Discourse & syntactic parsers • Training corpus where EDU’s in summaries are aligned with the documents • Cannot handle interesting document lengths (due to complexity)

  18. Ex. 3: Headline generation

  19. Berger & Mittal (sigir2000) • Input: web pages (often not running text) • Trigram language model • IBM model 1 like channel model: • Choose length, draw word from source model and replace with similar word, independence assumption • Trained on Open Directory • Non-extractive • Grammaticality and coherence are disappointing: indicative

  20. Zajic, Dorr & Schwartz (duc2002) • Headline generation from a full story: P(S|H)P(H) • Channel model based on HMM consisting of a bigram model of headline words and a unigram model of story words, bigram language model • Decoding parameters are crucial to produce good results (length, position, strings) • Good results in fluency and accuracy

  21. Conclusions • Fluent headlines within reach of simple generative models • High quality summaries (coverage, grammaticality, coherence) require higher level symbolic representations • Cut & paste metaphor divides the work into manageable sub-problems • Noisy channel method effective, but not always efficient

  22. Open issues • Audience (user model) • Types of source documents • Dealing with redundancy • Information ordering (e.g., temporal) • Coherent text • Cross-lingual summarization (Norbert Fuhr) • Use summaries to improve IR (or CLIR) - relevance correlation • LM for text generation • Possibly not well-defined problem (low interjudge agreement) • Develop models with more linguistic structure • Develop integrated models, e.g. by using priors (Rosenfeld) • Build efficient implementations • Evaluation: Define a manageable task

More Related