Detecting anaphoricity and antecedenthood for coreference resolution
Download
1 / 21

Detecting Anaphoricity and Antecedenthood for Coreference Resolution - PowerPoint PPT Presentation


  • 121 Views
  • Uploaded on

Detecting Anaphoricity and Antecedenthood for Coreference Resolution. Olga Uryupina ( uryupina @ gmail . com ) Institute of Linguistics, RAS 13.11.08. Overview. Anaphoricity and Antecedenthood Experiments Incorporating A&A detectors into a CR system Conclusion. A&A: example.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' Detecting Anaphoricity and Antecedenthood for Coreference Resolution ' - geona


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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Detecting anaphoricity and antecedenthood for coreference resolution

Detecting Anaphoricity and Antecedenthood for Coreference Resolution

Olga Uryupina ([email protected])

Institute of Linguistics, RAS

13.11.08


Overview
Overview Resolution

  • Anaphoricity and Antecedenthood

  • Experiments

  • Incorporating A&A detectors into a CR system

  • Conclusion


A a example
A&A: example Resolution

Shares in Loral Space will be distributed to Loral shareholders. The new company will start life with no debt and $700 million in cash. Globalstar still needs to raise $600 million, and Schwartz said that the company would try to raise the money in the debt market.


A a example1
A&A: example Resolution

Shares in Loral Space will be distributed to Loral shareholders. The new company will start life with no debt and $700 million in cash. Globalstar still needs to raise $600 million, and Schwartz said that the company would try to raise the money in the debt market.


Anaphoricity
Anaphoricity Resolution

Likely anaphors:

- pronouns, definite descriptions

Unlikely anaphors:

- indefinites

Unknown:

- proper names

Poesio&Vieira: more than 50% of definite descriptions in a newswire text are not anaphoric!


A a example2
A&A: example Resolution

Shares in Loral Space will be distributed to Loral shareholders. The new company will start life with no debt and $700 million in cash. Globalstar still needs to raise $600 million, and Schwartz said that the company would try to raise the money in the debt market.


A a example3
A&A: example Resolution

Shares in Loral Space will be distributed to Loral shareholders. The new company will start life with no debt and $700 million in cash. Globalstar still needs to raise $600 million, and Schwartz said that the company would try to raise the money in the debt market.


Antecedenthood
Antecedenthood Resolution

Related to referentiality (Karttunen, 1976):

„no debt“ etc

Antecedenthood vs. Referentiality: corpus-based decision


Experiments
Experiments Resolution

  • Can we learn anaphoricity/antecedenthood classifiers?

  • Do they help for coreference resolution?


Methodology
Methodology Resolution

  • MUC-7 dataset

  • Anaphoricity/antecedenthood induced from the MUC annotations

  • Ripper, SVM


Features
Features Resolution

  • Surface form (12)

  • Syntax (20)

  • Semantics (3)

  • Salience (10)

  • „same-head“ (2)

  • From Karttunen, 1976 (7)

    49 features – 123 boolean/continuous




Integrating a a into a cr system
Integrating A&A into a CR system Resolution

Apply an A&A prefiltering before CR starts:

  • Saves time

  • Improves precision

    Problem: we can filter out good candidates..:

    - Will loose some recall


Oracle based a a prefiltering
Oracle-based A&A prefiltering Resolution

Take MUC-based A&A classifier („gold standard“

CR system: Soon et al. (2001) with SVMs

MUC-7 validation set (3 „training“ documents)



Automatically induced classifiers
Automatically induced classifiers Resolution

Precision more crucial than Recall

Learn Ripper classifiers with different Ls (Loss Ratio)




Conclusion
Conclusion Resolution

Automatically induced detectors:

  • Reliable for anaphoricity

  • Much less reliable for antecedenthood

    (a corpus, explicitly annotated for referentiality could help)

    A&A prefiltering:

  • Ideally, should help

  • In practice – substantial optimization required


Thank you

Thank You Resolution !


ad