Changes between Initial Version and Version 1 of en/AdvancedNlpCourse2020/AnaphoraResolution

Aug 31, 2021, 2:12:54 PM (13 months ago)
Ales Horak

copied from private/AdvancedNlpCourse/AnaphoraResolution


  • en/AdvancedNlpCourse2020/AnaphoraResolution

    v1 v1  
     1= Anaphora resolution =
     3[[|IA161]] [[en/AdvancedNlpCourse|Advanced NLP Course]], Course Guarantee: Aleš Horák
     5Prepared by: Marek Medveď
     7== State of the Art ==
     9Anaphora resolution (or pronoun resolution) is the problem of resolving references to earlier or later items in the discourse. [[BR]]
     10Main approaches:
     111. Knowledge-rich approaches:
     12     1. Syntax-based approaches
     13     2. Discourse-Based Approaches
     14     3. Hybrid Approaches
     15     4. Corpus based Approaches
     161. Knowledge-poor Approaches:
     17     1. Machine learning techniques
     18=== References ===
     20 1. Anaphora Resolution, Studies in Language and Linguistics by Mitkov, R., 2014, Taylor & Francis, ISBN 9781317881810
     21 1. Anaphora resolution: the state of the art, Ruslan Mitkov,1999, Citeseer
     22 1. Strategies of anaphora resolution, Tanya Reinhart, 2006, North Holland, [[|Source]]
     23 1. Discriminative Approach to Predicate-argument Structure Analysis with Zero-anaphora Resolution, Kenji Imamura and Kuniko Saito  and Tomoko Izumi, 2009, Association for Computational Linguistics, ACMID 1667611, [[| Source]]
     24 1. The Influence of Minimum Edit Distance on Reference Resolution, Michael Strube and Stefan Rapp and Christoph Muller, EMNLP 2002, Association for Computational Linguistics, ACMID 1118733, [[|Source]]
     25 1. Combining Sample Selection and Error-driven Pruning for Machine Learning of Coreference Rules, Vincent Ng and Claire Cardie, EMNLP 2002, Association for Computational Linguistics, ACMID 1118701, [[|Source]]
     27== Practical Session ==
     29Student has to understand Hobbs' definition of anaphora resolution and according to it implement the main function of Hobbs' algorithm in proposed python script that contains all necessary functions. According to real data (syntactic trees) student tests his program and evaluate it. At the and of the session student has to hand the results to prove completing the task. If the student finishes early the additional task is to find sentence structures that are not covered by Hobbs' algorithm.
     31The task:
     32 1. download script with data is available [[|here]]
     33 1. NLTk package is required for Paste 'pip3 install nltk --user' to terminal to install NLTK package.
     34 1. understand Hobbs' definition of anaphora resolution and replace 'XXX' function call with correct one
     35 1. find 20 nontrivial sentences wit anaphora: 10 that Hobbs algorithm can recognize and 10 sentences it dos not. You
     36 can use [ the Stanford parser]
     37 to test new sentences - copy the tree to one line and remove the ROOT tag.
     38 1. submit script with 10 examples that are correctly recognized with and 10 examples that are not correctly recognized by 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).
     41 1. execute Hobbs script: python ./ demosents.txt He