Modeling Evolving Relationships Between Characters in Literary Novels

Authors: Snigdha Chaturvedi, Shashank Srivastava, Hal Daume III, Chris Dyer

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

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically demonstrate that such a framework outperforms competitive baselines. Section 4. Empirical Evaluation includes subsections like 'Databases', 'Baselines and Evaluation Measures', 'Evaluation on the Spark Notes dataset', 'Evaluation on the AMT dataset', and 'Ablation Study' presenting performance tables and cross-validation results.
Researcher Affiliation Academia 1University of Maryland, College Park 2Carnegie Mellon University
Pseudocode Yes Algorithm 1 Training the semi-supervised framework
Open Source Code No The dataset is available at the first author s webpage 3 (https://sites.google.com/site/snigdhac/academics). The paper does not explicitly state that the source code for the described methodology is available.
Open Datasets Yes Spark Notes: This dataset consists of a collection of summaries ( Plot Overviews ) of 300 English novels extracted from the Literature Study Guides section of Spark Notes 2. (The dataset is available at the first author s webpage 3.)
Dataset Splits Yes Table 2 compares 10-fold cross validation performances of our second order Semi-supervised Framework (Order 2 Model)...
Hardware Specification No The paper does not specify any hardware details used for running the experiments.
Software Dependencies No The paper mentions using specific tools like 'Booknlp pipeline', 'Stanford Core NLP system', and 'Semafor', but does not provide specific version numbers for these software dependencies.
Experiment Setup No The paper states the model is trained 'using an averaged structured perceptron (Collins 2002)' but does not provide specific experimental setup details such as learning rates, batch sizes, number of epochs, or other hyperparameters.