Machine Translation Using Improved Attentionbased Transformer with Hybrid Input

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Abrishami Mahsa; Rashti Mohammad Javad; Naderan Marjan

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Seminar Paper

Paper Information

Seminar: INTERNATIONAL CONFERENCE ON WEB RESEARCH
Year:2020 | Issue:6

Download Full-Text

View:

Download:

Information Seminar Paper

Title

Machine Translation Using Improved Attentionbased Transformer with Hybrid Input

Author(s)

Abrishami Mahsa | Rashti Mohammad Javad | Naderan Marjan

Keywords

Neural Machine Translation;Self

Attention;Multi

Head Attention;Encoder

Decoder

Abstract

Machine Translation (MT) refers to the automated software-based translation of natural language text. The embedded complexities and incompatibilities of natural languages have made MT a daunting task facing numerous challenges, especially when it is to be compared to a manual translation. With the emergence of deep-learning AI approaches, the Neural Machine Translation (NMT) has pushed MT results closer to human expectations. One of the newest deep learning approaches is the sequence-to-sequence approach based on Recurrent Neural Networks (RNN), complex convolutions, and transformers, and employing encoders/Decoder pairs. In this study, an attention-based deep learning architecture is proposed for MT, with all layers focused exclusively on multi-head attention and based on a transformer that includes multi-layer encoders/Decoders. The main contributions of the proposed model lie in the weighted combination of layers’ primary input and output of the previous layers, feeding into the next layer. This mechanism results in a more accurate transformation compared to nonhybrid inputs. The model is evaluated using two datasets for German/English translation, the WMT'14 dataset for training, and the newstest'2012 dataset for testing. The experiments are run on GPU-equipped Google Colab instances and the results show an accuracy of 36. 7 BLEU, a 5% improvement over the previous work without the hybrid-input technique.

Video

Cites

No record.

References

No record.

Cite

APA: Copy

Abrishami, Mahsa, Rashti, Mohammad Javad, & Naderan, Marjan. (2020). Machine Translation Using Improved Attentionbased Transformer with Hybrid Input. INTERNATIONAL CONFERENCE ON WEB RESEARCH. SID. https://sid.ir/paper/949234/en

Vancouver: Copy

Abrishami Mahsa, Rashti Mohammad Javad, Naderan Marjan. Machine Translation Using Improved Attentionbased Transformer with Hybrid Input. 2020. Available from: https://sid.ir/paper/949234/en

IEEE: Copy

Mahsa Abrishami, Mohammad Javad Rashti, and Marjan Naderan, “Machine Translation Using Improved Attentionbased Transformer with Hybrid Input,” presented at the INTERNATIONAL CONFERENCE ON WEB RESEARCH. 2020, [Online]. Available: https://sid.ir/paper/949234/en

Related Journal Papers

No record.

Related Seminar Papers

No record.

Related Plans

No record.

Recommended Workshops