Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Structured Prediction Theory Based on Factor Graph Complexity
Authors: Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang
NeurIPS 2016 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We also report the results of experiments with VCRF on several datasets to validate our theory. |
| Researcher Affiliation | Collaboration | Corinna Cortes Google Research New York, NY 10011 EMAIL Vitaly Kuznetsov Google Research New York, NY 10011 EMAIL Mehryar Mohrii Courant Institute and Google New York, NY 10012 EMAIL Scott Yang Courant Institute New York, NY 10012 EMAIL |
| Pseudocode | No | The paper describes algorithms (VCRF, VStruct Boost) and refers to appendices for details, but it does not include any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not contain any statement about making its source code publicly available, nor does it provide a link to a code repository. |
| Open Datasets | Yes | We conducted experiments on several part-of-speech (POS) datasets: Penn Treebank (PTB), CONLL-2000, CONLL-2003, and Ontonotes. |
| Dataset Splits | Yes | We used the standard splits for PTB (sections 0-18 for training, 19-21 for validation, 22-24 for test), for CONLL-2000 (train and test), for CONLL-2003 (train, validation, and test), and for Ontonotes (train, validation, and test). |
| Hardware Specification | No | The paper does not specify any hardware details such as CPU, GPU models, or memory used for running the experiments. |
| Software Dependencies | No | The paper mentions the use of algorithms (e.g., VCRF, CRF) but does not list specific software dependencies with version numbers. |
| Experiment Setup | Yes | For VCRF, we used a fixed learning rate of 0.001. |