Semantical Clustering of Morphologically Related Chinese Words

Authors: Chia-Ling Lee, Ya-Ning Chang, Chao-Lin Liu, Chia-Ying Lee, Jane Yung-jen Hsu

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

Reproducibility Variable Result LLM Response
Research Type Experimental In Experiment 1, we employed linguistic features at the word, syntactic, semantic, and contextual levels in aggregated computational linguistics methods to handle the clustering task. In Experiment 2, we recruited adults and children to perform the clustering task. Experimental results indicate that our computational model achieved a similar level of performance as children.
Researcher Affiliation Academia Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan1 Institute of Linguistics, Academia Sinica, Taipei, Taiwan2 Department of Computer Science, National Chengchi University, Taipei, Taiwan3
Pseudocode No The paper describes methods in text but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper provides a personal/project URL (http://www.csie.ntu.edu.tw/~r00922072/aaai14stu.html) but does not explicitly state that source code for the methodology is available there, nor is it a direct link to a code repository.
Open Datasets Yes We used the Academia Sinica Balanced Corpus3 as the reference corpus. 3http://rocling.iis.sinica.edu.tw/CKIP/engversion/20corpus.htm
Dataset Splits No The paper refers to 'Our test data and ground truth' and '11 morphological families, including 285 target words' but does not specify explicit training, validation, or test dataset splits in terms of percentages, counts, or a standard split reference.
Hardware Specification No The paper does not provide any specific details about the hardware used for running experiments.
Software Dependencies No The paper mentions using 'Stanford Parser' and 'Word Net' but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup Yes Based on heuristic, the weight of each method were determined based on its rank of individual performance (e.g., 1.0, 1.2, 1.3, 1.4)... To compute the similarity between two clusters, the average link method was adopted... F-NMI is defined as α F1+(1 α) NMI where α is set to 0.5 in the current experiments.