Multitask Spectral Learning of Weighted Automata
Authors: Guillaume Rabusseau, Borja Balle, Joelle Pineau
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The benefits of the proposed multitask approach are theoretically motivated and showcased through experiments on both synthetic and real world datasets. |
| Researcher Affiliation | Collaboration | Guillaume Rabusseau Mc Gill University Borja Balle Amazon Research Cambridge Joelle Pineau Mc Gill University |
| Pseudocode | Yes | Algorithm 1 MT-SL: Spectral Learning of vector-valued WFA for multitask learning |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code for the methodology described, nor does it include links to a code repository. |
| Open Datasets | Yes | We evaluate MT-SL on 33 languages from the Universal Dependencies (UNIDEP) 1.4 treebank [24] |
| Dataset Splits | Yes | For each language, the available data is split between a training, a validation and a test set (80%, 10%, 10%). |
| Hardware Specification | No | The paper does not specify any particular hardware (e.g., CPU, GPU models, or cloud computing instance types) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies, libraries, or programming languages used in the experiments. |
| Experiment Setup | Yes | For both methods the prefix set P (resp. suffix set S) is chosen by taking the 1,000 most frequent prefixes (resp. suffixes) in the training data of the target task, and the values of the ranks are chosen using a validation set. |