Ask, and Shall You Receive? Understanding Desire Fulfillment in Natural Language Text

Authors: Snigdha Chaturvedi, Dan Goldwasser, Hal Daume III

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments with two different datasets demonstrate the importance of understanding the narrative and discourse structure to address this task. Table 4 compares the test set performances using F1 score of the positive (desire fulfilled) class for various models.
Researcher Affiliation Academia 1University of Maryland, College Park 2Purdue University
Pseudocode Yes Algorithm 1 Training algorithm for LSNM
Open Source Code No No explicit statement about releasing the source code for their proposed methodology was found. The paper mentions "BIUTEE: A modular open-source system for recognizing textual entailment" which is a third-party tool they used, not their own code.
Open Datasets Yes We have used two manually annotated datasets for our experiments: MCTest and Simple Wiki. Both the datasets are available on the first author s webpage.
Dataset Splits Yes Also, the number of latent states, H, was set to be 2 and 15 for the MCTest and Simple Wiki datasets respectively using cross-validation.
Hardware Specification No No specific hardware details (such as GPU/CPU models, memory, or cloud instance types) used for running experiments are provided in the paper.
Software Dependencies No No specific software dependencies with version numbers are provided. The paper mentions tools like "Stanford Core NLP coreference resolution system" and "BIUTEE" (Stern and Dagan 2012; Magnini et al. 2014) but without version details.
Experiment Setup No No specific experimental setup details such as hyperparameters (e.g., learning rate, batch size, number of epochs) or optimizer settings are provided in the main text.