Chinese Overt Pronoun Resolution: A Bilingual Approach

Authors: Chen Chen, Vincent Ng

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on the OntoNotes corpus demonstrate that our bilingual approach to Chinese pronoun resolution significantly surpasses the performance of state of the art monolingual approaches.
Researcher Affiliation Academia Chen Chen and Vincent Ng Human Language Technology Research Institute University of Texas at Dallas Richardson TX cchen, vincen@hlt.utdallas.edu
Pseudocode No The paper describes the approach steps in prose but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes The complete list of features can be found in the source code of the resolver. See http://www.ims.uni-stuttgart.de/forschung/ressourcen/werkzeuge/IMSCoref.en.html
Open Datasets Yes We use the OntoNotes corpus that we obtained from the CoNLL shared task organizers for evaluating our bilingual approach to Chinese pronoun resolution.
Dataset Splits Yes We follow the shared task’s train/test partition of the documents performing training and parameter tuning on the training and development documents and reserving the test documents solely for evaluation purposes. Specifically, when Method 4 is employed, which requires parameter tuning, we train the resolvers on the training set and tune the parameters on the development set.
Hardware Specification No No specific hardware details (e.g., GPU models, CPU specifications, or memory) used for running the experiments are mentioned in the paper.
Software Dependencies No No specific version numbers for software dependencies are provided. The paper mentions using the LIBSVM software package and BerkeleyAligner, but without version details.
Experiment Setup No While the paper mentions tunable parameters for Method 4 and a hill climbing local search algorithm for tuning, it does not provide the specific values for these parameters (e.g., learning rate, batch size, number of epochs) or other detailed experimental setup configurations.