MALA: Cross-Domain Dialogue Generation with Action Learning

Authors: Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang7977-7984

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments using multi-domain datasets, SMD and Multi WOZ, show that our proposed model achieves consistent improvements over the baselines models in terms of both task completion and language quality.
Researcher Affiliation Collaboration 1The University of Melbourne, 2Twitter Inc.
Pseudocode No The paper describes its method using textual descriptions and mathematical formulations but does not include any explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement or link indicating that the source code for the methodology is openly available.
Open Datasets Yes We use two multi-domain human-human conversational datasets: (1) SMD dataset (Eric and Manning 2017) contains 2425 dialogues, and has three domains: calendar, weather, navigation; (2) MULTIWOZ dataset (Budzianowski et al. 2018) is the largest existing taskoriented corpus spanning over seven domains.
Dataset Splits Yes We use the separation of training, validation and testing data as original SMD and MULTIWOZ dataset.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory) used for running the experiments.
Software Dependencies No The paper mentions using a 'three-layer transformer' and 'VQ-VAE' as components but does not provide specific version numbers for any software, libraries, or frameworks used in the implementation or experimentation.
Experiment Setup No The paper mentions some architectural details for the base model, such as 'a three-layer transformer... with a hidden size of 128 and 4 heads', but does not provide specific hyperparameters like learning rate, batch size, or number of epochs, nor a detailed training configuration.