Corpus-Level End-to-End Exploration for Interactive Systems
Authors: Zhiwen Tang, Grace Hui Yang2527-2534
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on the Text REtrieval Conference (TREC) Dynamic Domain (DD) Track show that CE3 outperforms the state-of-the-art DS systems. 5 Experiments Experimental Settings The Text REtrieval Conference (TREC) Dynamic Domain (DD) Tracks 2015 2017 (Yang, Tang, and Soboroff 2017) provides a standard testbed for DS. |
| Researcher Affiliation | Academia | Zhiwen Tang, Grace Hui Yang Info Sense, Department of Computer Science Georgetown University zt79@georgetown.edu, huiyang@cs.georgetown.edu |
| Pseudocode | Yes | Algorithm 1 describes the proposed CE3 method. It starts by sampling actions by the RL agent. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | TREC DD 2017 used LDC New York Times collections (Sandhaus 2008) as its corpus. The collection included more than 1.8 million news articles archived in the past 20 years. The Text REtrieval Conference (TREC) Dynamic Domain (DD) Tracks 2015 2017 (Yang, Tang, and Soboroff 2017) provides a standard testbed for DS. |
| Dataset Splits | No | The paper mentions constructing collections and using 'sampled trajectories' for the PPO algorithm but does not specify explicit training, validation, or test dataset splits (percentages, counts, or predefined citations) for reproducibility. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions various tools and frameworks such as PPO, word2vec, doc2vec, t-SNE, Galago, Indri, and solr, but it does not specify version numbers for any of these software dependencies. |
| Experiment Setup | Yes | The dimension of t SNE s output n is set to 3. The number of segments per document B is set to 20. Coefficients c1 and c2 in Eq. 4 are 0.5 and 0, respectively. Both the policy and value networks have 2 layers of CNNs and 1 MLP. The first CNN consists of eight 2 × 2 kernels and the second consists of 16. The hidden layer of MLP consists of 32 units and is the same for both networks. The output layer of MLP has 3 units for the policy network and 1 for the value network. |