Embedding Inference for Structured Multilabel Prediction

Authors: Farzaneh Mirzazadeh, Siamak Ravanbakhsh, Nan Ding, Dale Schuurmans

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments demonstrate that the benefits of structured output training can still be realized even after inference has been eliminated.
Researcher Affiliation Collaboration Farzaneh Mirzazadeh Siamak Ravanbakhsh University of Alberta {mirzazad,mravanba}@ualberta.ca Nan Ding Google dingnan@google.com Dale Schuurmans University of Alberta daes@ualberta.ca
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes In particular, we investigated three multilabel text classification data sets, Enron, WIPO and Reuters, obtained from https://sites. google.com/site/hrsvmproject/datasets-hier (see Table 1 for details).
Dataset Splits No The paper does not provide specific details on training, validation, or test dataset splits, beyond referring to a 'test set'.
Hardware Specification No The paper does not provide specific details on the hardware used for running experiments.
Software Dependencies No The paper mentions LBFGS and a bundle method but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes In each case, the regularization parameter was simply set to 1.