Towards Understanding Natural Language: Semantic Parsing, Commonsense Knowledge Acquisition and Applications
Authors: Arpit Sharma
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the steps we took towards the goal and the tools/techniques we developed, such as a semantic parser and a novel algorithm to automatically acquire commonsense knowledge from text. We also show the usefulness of the developed tools by applying them to solve tasks such as hard coreference resolution. |
| Researcher Affiliation | Academia | Arpit Sharma Arizona State University asharm73@asu.edu |
| Pseudocode | No | The paper describes algorithms and implementations but does not include any explicit pseudocode blocks or formally labeled algorithm sections. |
| Open Source Code | No | The paper provides links to an online GUI for the parser (www.kparser.org) and a demo of extracted knowledge (http://bioai8core.fulton.asu.edu/knet), which are demonstrations or online interfaces, not direct links to the source code of the described methodology. |
| Open Datasets | Yes | This type of knowledge is proved helpful in solving a subset of the Winograd Schema Challenge (WSC) [Sharma et al., 2015a], which is a hard co-reference resolution challenge. |
| Dataset Splits | No | The paper mentions using the Winograd Schema Challenge (WSC) and extracting knowledge from a large text repository, but it does not specify any dataset splits for training, validation, or testing (e.g., percentages or sample counts). |
| Hardware Specification | No | The paper does not provide any specific details regarding the hardware used for running the experiments (e.g., CPU, GPU models, or memory specifications). |
| Software Dependencies | No | The paper mentions using 'logic programming (Answer Set Programming1) based reasoning agent', and provides a footnote link to 'http://potassco.sourceforge.net/teaching.html' which is a teaching resource. However, it does not specify version numbers for any software components, libraries, or solvers used in the experiments. |
| Experiment Setup | No | The paper does not provide specific details about the experimental setup, such as hyperparameter values, learning rates, batch sizes, or optimizer settings used during training or evaluation. |