Fine-Grained Semantic Conceptualization of FrameNet

Authors: Jin-woo Park, Seung-won Hwang, Haixun Wang

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our extensive analysis with real-life data validates that our approach improves not only the quality of the identified concepts for Frame Net, but also that of applications such as selectional preference.
Researcher Affiliation Collaboration Jin-woo Park POSTECH, Korea, Republic of jwpark85@postech.edu Seung-won Hwang Yonsei University, Korea, Republic of seungwonh@yonsei.ac.kr Haixun Wang Facebook Inc., USA haixun@gamil.com
Pseudocode Yes Algorithm 1: Truss (G )
Open Source Code No The paper states: "The entire results are released at http://karok.postech.ac.kr/FEconceptualization.zip." This link is for results, not source code. No other explicit statement or link for the paper's source code is provided.
Open Datasets Yes Proposed method To overcome concept and instance sparsity of manually-built KB, we utilize on Probase (Wu et al. 2012)2, which contains millions of fine-grained concepts automatically harvested from billions of web documents. Footnote 2: Dataset publicly available at http://probase.msra.cn/dataset.aspx. Frame Net (Fillmore, Johnson, and Petruck 2003)3. Footnote 3: We used the Frame Net 1.5 dataset.
Dataset Splits No The paper describes the Sem Eval 2010 dataset used for pseudo-disambiguation evaluation but does not specify training, validation, or test splits for its model's development and evaluation (e.g., percentages, sample counts, or references to standard splits).
Hardware Specification Yes All experiments were carried out on a machine with a Intel Core i3 CPU processor at 3.07GHz and 4GB of DDR3 memory.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names like PyTorch or TensorFlow with their respective versions).
Experiment Setup No The paper does not provide specific experimental setup details such as hyperparameters (e.g., learning rate, batch size, number of epochs) or specific training configurations.