Zero-Resource Neural Machine Translation with Multi-Agent Communication Game
Authors: Yun Chen, Yang Liu, Victor Li
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on the IAPR-TC12 and Multi30K datasets show that the proposed learning mechanism significantly improves over the state-of-the-art methods. |
| Researcher Affiliation | Academia | Department of Electrical and Electronic Engineering, The University of Hong Kong State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology, Tsinghua University, Beijing, China |
| Pseudocode | Yes | Algorithm 1 The learning algorithm in the two-agent communication game |
| Open Source Code | No | The paper references existing open-source tools ('dl4mt' and 'arctic-captions') that they leveraged, but does not provide specific access (link or statement) to their own implementation code for the proposed method. |
| Open Datasets | Yes | We evaluate our model on two publicly available multilingual image-description datasets as in (Nakayama and Nishida 2017). The IAPR-TC12 dataset (Grubinger et al. 2006)... The recently published Multi30K dataset (Elliott et al. 2016)... |
| Dataset Splits | Yes | We randomly split the dataset into training, validation and test sets with 18K, 1K and 1K images respectively. Table 2: Splits for experiments. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments were provided. |
| Software Dependencies | No | The paper mentions using 'scripts in the Moses SMT Toolkit (Koehn et al. 2007)' and 'joint byte pair encoding (BPE) (Sennrich, Haddow, and Birch 2016)', but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | No | The 'Experimental Setup' section describes the image features, model architectures, and beam search size, but it does not specify concrete hyperparameters like learning rate, batch size, or number of epochs. |