Towards Scalable Multi-Domain Conversational Agents: The Schema-Guided Dialogue Dataset

Authors: Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, Pranav Khaitan8689-8696

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate our model on public datasets WOZ2.0 and Multi WOZ 2.1 (Eric et al. 2019). As results in Table 4 show, our model performs competitively on these datasets. In these experiments, we omit the use of fuzzy matching scores and use exact match while calculating the goal accuracies to keep our numbers comparable with other works.
Researcher Affiliation Industry Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, Pranav Khaitan Google Research, Mountain View, California, USA {abhirast, xiaoxuez, srinivasksun, raghavgupta, pranavkhaitan}@google.com
Pseudocode No The paper details the model components and their mathematical formulations but does not include any structured pseudocode or algorithm blocks.
Open Source Code Yes Our model code is available at github.com/google-research/google-research/tree/master/schema_guided_dst
Open Datasets Yes In this work, we introduce the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains. The dataset has been released at github.com/google-research-datasets/dstc8-schema-guided-dialogue
Dataset Splits Yes The 20 domains present across the train, dev and test splits are listed in Table 2.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications, or cloud instances) used for running the experiments.
Software Dependencies No The paper mentions using 'BERT' as a pre-trained model but does not specify its version or other software dependencies with their respective version numbers.
Experiment Setup No The paper describes the model architecture and its components but does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size), optimizer settings, or training schedules.