1 / 14

Minh-Quoc NGHIEM NaCTeM , The University of Manchester

Introduction. UIMA. OpenMinTeD. Argo. The interoperability of text and data mining: UIMA, Argo, and OpenMinTeD. Minh-Quoc NGHIEM NaCTeM , The University of Manchester. Welcome everyone to the Text Mining and Applications Workshop in Vietnam.

sbrian
Download Presentation

Minh-Quoc NGHIEM NaCTeM , The University of Manchester

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. Introduction UIMA OpenMinTeD Argo The interoperability of text and data mining: UIMA, Argo, and OpenMinTeD Minh-Quoc NGHIEM NaCTeM, The University of Manchester

  2. Welcome everyone to the Text Mining and Applications Workshop in Vietnam. Welcome/VB everyone/NN to/TO the/DT Text/NNP Mining/NNP and/CC Applications/NNP Workshop/NNP in/IN Vietnam/NNP ./. (ROOT (S (VP (VB Welcome) (NP (NN everyone)) (PP (TO to) (NP (NP (DT the) (NNP Text) (NNP Mining) (CC and) (NNP Applications) (NNP Workshop)) (PP (IN in) (NP (NNP Vietnam)))))) (. .)))

  3. Welcome everyone to the Text Mining and Applications Workshop in Vietnam. Standoff annotation  No text modification  Annotations as offsets

  4. 0 1 2 3 4 5 10 15 20 25 Welcome everyone to the Text Mining and Applications Workshop in Vietnam. 30 35 40 45 50 55 60 65 70 Sentence: 0-71 Token: 0-7, 8-16, 17-19, …

  5. Unstructured Information Management Architecture

  6. Identify Semantic Entities Induce Structure People, Places, Org, Events … Times, Topics, Opinions, Relationships …

  7. Pipeline Tokenizer POS Tagger Chunker NER Components

  8. Type System • Sentence • begin, end … • Token • begin, end • POS … • Named-entity • begin, end • Entity type … • Relation • Entity 1, Entity 2 • Relation type

  9. Example CollectionReader reader = UriCollectionReader.getCollectionReaderFromFiles(Arrays.asList(options.getTextFile())); AggregateBuilder aggregate = new AggregateBuilder(); aggregate.add(SentenceBoundaryDetector.getDescription()); aggregate.add(Tokenizer.getDescription()); aggregate.add(POSTagger.getDescription()); aggregate.add(Chunker.getDescription()); aggregate.add(NamedEntityRecognizer.getDescription()); SimplePipeline.runPipeline(reader, aggregate.createAggregateDescription());

  10. Don’t know programming? UIMA Web App Components ARGO Interaction Collaboration

  11. Have data / service to share?

  12. Thank you for listening!

More Related