Explicit Sentence Compression for Neural Machine Translation

Authors: Zuchao Li, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Zhuosheng Zhang, Hai Zhao8311-8318

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical tests on the WMT English-to-French and English-to-German translation tasks show that the proposed sentence compression method significantly improves the translation performances over strong baselines.
Researcher Affiliation Collaboration 1Department of Computer Science and Engineering, Shanghai Jiao Tong University 4National Institute of Information and Communications Technology (NICT), Kyoto, Japan
Pseudocode No No pseudocode or algorithm blocks are provided in the paper.
Open Source Code No No explicit statement or link to open-source code for the described methodology is provided in the paper.
Open Datasets Yes We used the Annotated Gigaword corpus (Napoles, Gormley, and Van Durme 2012) as the benchmark (Rush, Chopra, and Weston 2015b). ... The proposed NMT model was evaluated on the WMT14 English-to-German (EN-DE) and English-to-French (EN-FR) tasks, which are both standard large-scale corpora for NMT evaluation.
Dataset Splits Yes The data includes approximately 3.8 M training samples, 400 K validation samples, and 2 K test samples. ... The newstest2013 and newstest2014 datasets were used as the dev set and test set, respectively. ... Newstest12 and newstest13 were combined for validation and the newstest14 was the test set, following the setting of Gehring et al. (2017).
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments.
Software Dependencies No The paper mentions using the BPE algorithm and Transformer architecture but does not specify software dependencies with version numbers (e.g., Python version, specific deep learning framework versions like PyTorch or TensorFlow).
Experiment Setup Yes We use beam search with a beam size of 5, the length length normalization of 0.5, and the coverage penalty of 0.2.