Analogical Generalization of Linguistic Constructions

Authors: Clifton McFate

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

Reproducibility Variable Result LLM Response
Research Type Experimental In pursuing the first goal, I plan to model several existing human studies. Casenhiser & Goldberg (2005) presented children with nonce verbs in a novel construction (S-O-V) which described videos of appearance scenarios. They found that children quickly applied the novel construction to new appearance scenarios and that this was facilitated when examples frequently shared a verb. ... I aim to replicate these studies with my model. ... To assess performance, I plan to use Kaschak & Glenberg s (2000) denominal verb stimuli.
Researcher Affiliation Academia Clifton Mc Fate Qualitative Reasoning Group, Northwestern University c-mcfate@northwestern.edu
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper mentions existing tools like Cog Sketch, SAGE, and EA NLU and cites Research Cyc, but it does not state that the code for the author's specific methodology or implementation described in this paper is publicly available.
Open Datasets Yes I will use SAGE to generalize semantic annotations from Fillmore et al s (2001) Frame Net. ... To assess performance, I plan to use Kaschak & Glenberg s (2000) denominal verb stimuli.
Dataset Splits No The paper mentions using specific stimuli for performance assessment and generalizing from Frame Net, but it does not provide specific details on dataset splits (e.g., percentages, counts, or explicit splitting methodology) for training, validation, or testing.
Hardware Specification No The paper does not provide any specific details regarding the hardware (e.g., GPU models, CPU types, memory) used or to be used for the experiments.
Software Dependencies No The paper mentions software like Cog Sketch, SAGE, EA NLU, Frame Net, and Research Cyc, but it does not provide specific version numbers for any of these dependencies.
Experiment Setup No The paper describes high-level plans for replicating studies and generalizing data but does not provide specific experimental setup details such as hyperparameter values, optimization settings, or training configurations.