Explaining Watson: Polymath Style
Authors: Wlodek Zadrozny, Valeria de Paiva, Lawrence Moss
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our paper is actually two contributions in one. First, we argue that IBM s Jeopardy! playing machine needs a formal semantics. We present several arguments as we discuss the system. We also situate the work in the broader context of contemporary AI. Our second point is that the work in this area might well be done as a broad collaborative project. Hence our Blue Sky contribution is a proposal to organize a polymath-style effort aimed at developing formal tools for the study of state of the art question-answer systems, and other large scale NLP efforts whose architectures and algorithms lack a theoretical foundation. |
| Researcher Affiliation | Collaboration | Wlodek Zadrozny UNC Charlotte wzadrozn@uncc.edu; Valeria de Paiva Nuance valeria.depaiva@nuance.com; Lawrence S. Moss Indiana University lmoss@indiana.edu |
| Pseudocode | No | The paper is a conceptual and theoretical discussion proposing future work; it does not present any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper discusses the use of 'open source NLP resources' and IBM's 'Watson APIs' as tools that could be utilized in the proposed polymath project, but it does not provide or explicitly state the release of its own source code for the concepts or proposals described. |
| Open Datasets | No | The paper is a theoretical work proposing future research and does not perform experiments. It references Watson's training data ('200K available questions...50K of them used for training and testing') but does not use or provide access information for a dataset for its own work. |
| Dataset Splits | No | The paper is a theoretical work proposing future research and does not perform experiments, thus it does not describe validation dataset splits. |
| Hardware Specification | No | The paper is a theoretical work proposing future research and does not describe experiments performed by the authors. It mentions Watson's 'highly parallel aspect of its scoring system' but provides no specific hardware details for any experimental setup of its own. |
| Software Dependencies | No | The paper is a theoretical work proposing future research and does not describe experiments performed by the authors. It mentions 'open source NLP resources' and 'Watson APIs' as tools that could be used in future work, but does not specify software dependencies with version numbers for its own research. |
| Experiment Setup | No | The paper is a theoretical work proposing future research; it does not describe experiments performed by the authors and therefore provides no details on experimental setup or hyperparameters. |