1 / 22

Named Entity Recognition based on Bilingual Co-training

Named Entity Recognition based on Bilingual Co-training. Li Yegang lyg8256@bit.edu.cn School of Computer, BIT. Outline. Introduction and Related Work Bilingual Co-training Corrective NE Projection Annotation Experiment Result. 1.Introduction. Related work Das et al.,2011

nia
Télécharger la présentation

Named Entity Recognition based on Bilingual Co-training

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. Named Entity Recognition based on Bilingual Co-training Li Yegang lyg8256@bit.edu.cn School of Computer, BIT

  2. Outline • Introduction and Related Work • Bilingual Co-training • Corrective NE Projection Annotation • Experiment Result

  3. 1.Introduction • Related work • Das et al.,2011 • using parallel English-foreign language data, a high-quality NER tagger for English, and projected annotations for the foreign language . • Burkett et al., 2010 • Parallel data has also been used to improve existing monolingual taggers or other analyzers in both languages.

  4. Introduction • Disadvantages • current NE alignment methods are not accurate enough, and many noises could be introduced during the word alignment stage. • manual annotation is usually obtained from a few limited domains, leading to a bad affect on statistical supervised learning methods.

  5. Introduction • Complementarity a) Results from Chinese name tagger: <PER>金庸新</PER >小说 (b) Results from English name tagger: the new novels of <PER>Jin Yong</PER> (c) Name tagging after using bilingual co-training: < PER >金庸</PER >新小说 • “金庸新” and “金庸” in Chinese can be a PER name, while its English translation “Jin Yong” indicates that “金庸” is more likely to be a PER name than “金庸新”.

  6. Introduction • Complementarity (a) Results from English name tagger The captain of a ferry boat who works on 〈PER〉 Lake Constance 〈/PER〉... (b) Results from Chinese name tagger: 在〈LOC〉康斯坦茨湖〈/LOC〉工作的一艘渡船的船长... (c) Name tagging after using bilingual co-training: The captain of a ferry boat who works on 〈LOC〉 LakeConstance 〈/LOC〉…  “Lake” in English can be the suffix word of either a PER or LOC name, while its Chinese translation “康斯坦茨湖” indicates that “Lake Constance” is more likely to be a LOC name.

  7. 2.Bilingual Co-training • Co-training • Starting with a set of labeled data, co-training algorithms attempt to increase the amount of annotated data using large amounts of unlabeled data. The process may continue for several iterations.

  8. Bilingual Co-training • Bilingual Co-training • regarding the parallel Chinese-English sentences as weaker independent views for NE identity

  9. Bilingual Co-training

  10. Algorithm of Bilingual Co-training • Given: • A set Ls of source labeled examples • A set Lt of target labeled examples • A set Us of source unlabeled examples • A set Ut of target unlabeled examples

  11. Algorithm of Bilingual Co-training • 1. Classifiers • Use Ls to train the classifiers Classifier(s) • Use Lt to train the classifiers Classifier(t)

  12. Algorithm of Bilingual Co-training

  13. Algorithm of Bilingual Co-training

  14. Algorithm of Bilingual Co-training

  15. 3.Corrective NE Projection Annotation • Projection NE Candidate • For each word in the source language NE, we find all the possible projection word in target language through the word alignment. Next, we have all the projection words as the “seed” data. With an open-ended window for each seed, all the possible sequences located within the window are considered as possible candidates for NE projection. Their lengths range from 1 to the empirically determined length of the window. During the best candidate projection NE selection, the NE alignment model discussed as follows is applied to search the best projection NE.

  16. 3.Corrective NE Projection Annotation • NE Alignment Model translation feature, the source NE and target NE’s co-occurrence feature, and length of NE pair feature

  17. 3.Corrective NE Projection Annotation • Translation Feature (Brown et al.,1993)

  18. 3.Corrective NE Projection Annotation • Co-occurrence Feature

  19. 3.Corrective NE Projection Annotation • Length Feature (Church,1993)

  20. Experimental Results Baseline F-Measure (%) of NE Tagging

  21. Experimental Results Co-training Model F-Measure (%) of NE Tagging

  22. Thank you!

More Related