Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Latent Intention Dialogue Models
Authors: Tsung-Hsien Wen, Yishu Miao, Phil Blunsom, Steve Young
ICML 2017 | Venue PDF | LLM Run Details | Input Tokens: 18,089 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,529 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental evaluation of LIDM shows that the model out-performs published benchmarks for both corpus-based and human evaluation, demonstrating the effectiveness of discrete latent variable models for learning goal-oriented dialogues. |
| Researcher Affiliation | Academia | 1Department of Engineering, University of Cambridge, Cambridge, United Kingdom 2Department of Computer Science, University of Oxford, Oxford, United Kingdom. |
| Pseudocode | No | The paper describes methods and processes using mathematical equations and textual explanations, but it does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The LIDM model3 Will be available at https://github.com/shawnwun/NNDIAL |
| Open Datasets | Yes | We explored the properties of the LIDM model3 using the Cam Rest676 corpus4 collected by Wen et al (2017), in which the task of the system is to assist users to find a restaurant in the Cambridge, UK area. |
| Dataset Splits | Yes | The corpus was partitioned into training, validation, and test sets in the ratio 3:1:1. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions the Adam optimizer but does not provide specific version numbers for any software dependencies or libraries used in the implementation or experimentation. |
| Experiment Setup | Yes | The LSTM hidden layer sizes were set to 50, and the vocabulary size is around 500 after pre-processing... and model s latent intention ID size I set to 50, 70, and 100, respectively. The trade-off constants λ and α were both set to 0.1. and The model is trained by Adam (Kingma & Ba, 2014) and tuned (early stopping, hyper-parameters) on the held-out validation set. ... During testing, we greedily selected the most probable intention and applied beam search with the beamwidth set to 10 when decoding the response. |