wiki:private/NlpInPracticeCourse/AnaphoraResolution

Anaphora resolution

IA161 NLP in Practice Course, Course Guarantee: Aleš Horák

Prepared by: Marek Medveď

State of the Art

Anaphora resolution (or pronoun resolution) is the problem of resolving references to earlier or later items in the discourse.
Main approaches:

  1. Knowledge-rich approaches:
    1. Syntax-based approaches
    2. Discourse-Based Approaches
    3. Hybrid Approaches
    4. Corpus based Approaches
  2. Knowledge-poor Approaches:
    1. Machine learning techniques

References

  1. Anaphora Resolution, Studies in Language and Linguistics by Mitkov, R., 2014, Taylor & Francis
  2. Caw-coref: Conjunction-aware word-level coreference resolution. D’Oosterlinc at all. (2023)
  3. F-coref: Fast, accurate and easy to use coreference resolution. Otmazgin, S., Cattan, A., and Goldberg, Y. (2022)
  4. Efficient and interpretable neural models for entity tracking. Toshniwal, S. (2022)
  5. Coreference resolution through a seq2seq transition-based system. Bohnet, B., Alberti, C., and Collins, M. (2022)

Practical Session

Student has to understand Hobbs' definition of anaphora resolution and according to it implement the main function of Hobbs' algorithm in the proposed python script that contains all necessary functions. According to real data (syntactic trees) students test their adjusted program and evaluate it. At the end of the session students hand in the results to prove completing the task. An additional task is to find sentence structures that are not covered by Hobbs' algorithm.

The task:

  1. download the script with data from here ->> correct solution here
  2. NLTK package is required for hobbs.py. When running at your computer, paste
    pip3 install nltk --user
    
    in the terminal to install NLTK package. Faculty machines should have nltk already installed.
  3. understand Hobbs' definition of anaphora resolution and replace XXX function calls with correct ones
  4. find 20 nontrivial sentences with anaphora: 10 that Hobbs algorithm can recognize and 10 sentences it dos not. You can use the Stanford parser to test new sentences - copy the tree into file formated into one line.
  5. submit your hobbs.py script with 10 examples that are correctly recognized with hobbs.py and 10 examples that are not correctly recognized by hobbs.py in the homework vault. For each unrecognized example write an explanation into one separate file unrecognized_notes.txt (first column: example id, second column: explanation).

Commands:

  1. execute Hobbs script:
    python3 ./hobbs.py demosents.txt He
    
Last modified 4 months ago Last modified on Dec 5, 2023, 11:00:36 AM

Attachments (3)

Download all attachments as: .zip