Morphology-aware Word-Segmentation in Dialectal Arabic Adaptation of Neural Machine Translation

Tawfik, Ahmed Y.; Emam, Mahitab; Essam, Khaled; Nabil, Robert; Hassan, Hany

doi:10.18653/v1/w19-4602

Cited by 11 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work is closely related to their idea while ours are more simple and realizable. Tawfik et al (Tawfik et al, 2019) confirmed that there is some advantage from using a high accuracy dialectal segmenter jointly with a language independent word segmentation method like BPE. The main difference is that their approach needs sufficient monolingual data additionally to train a segmentation model while ours do not need any external resources, which is very convenient for word segmentation on the low-resource and morphologically-rich agglutinative languages.…”

Section: Related Workmentioning

confidence: 98%

Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation

Pan,

Li,

Yang

et al. 2020

Preprint

View full text Add to dashboard Cite

Neural machine translation (NMT) has achieved impressive performance on machine translation task in recent years. However, in consideration of efficiency, a limited-size vocabulary that only contains the top-N highest frequency words are employed for model training, which leads to many rare and unknown words. It is rather difficult when translating from the lowresource and morphologically-rich agglutinative languages, which have complex morphology and large vocabulary. In this paper, we propose a morphological word segmentation method on the sourceside for NMT that incorporates morphology knowledge to preserve the linguistic and semantic information in the word structure while reducing the vocabulary size at training time. It can be utilized as a preprocessing tool to segment the words in agglutinative languages for other natural language processing (NLP) tasks. Experimental results show that our morphologically motivated word segmentation method is better suitable for the NMT model, which achieves significant improvements on Turkish-English and Uyghur-Chinese machine translation tasks on account of reducing data sparseness and language complexity. Sennrich, Rico and Haddow, Barry and Birch, Alexandra. Improving neural machine translation models with monolingual data. In Computer Science, 2016.

show abstract

Section: Related Workmentioning

confidence: 98%

Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation

Pan,

Li,

Yang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Banerjee and Bhattacharyya (2018) combined an off-the-shelf morphological segmenter and BPE in Hindi and Bengali translations against English. Tawfik et al (2019) used a retrained version of linguistically motivated segmentation model along with statistical segmentation methods for Arabic. Pinnis et al (2017) adopted linguistic guidance to BPE for English-Latvian translation.…”

Section: Related Workmentioning

confidence: 99%

An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks

Park,

Lee,

Jang

et al. 2020

Preprint

View full text Add to dashboard Cite

Typically, tokenization is the very first step in most text processing works. As a token serves as an atomic unit that embeds the contextual information of text, how to define a token plays a decisive role in the performance of a model.Even though Byte Pair Encoding (BPE) has been considered the de facto standard tokenization method due to its simplicity and universality, it still remains unclear whether BPE works best across all languages and tasks. In this paper, we test several tokenization strategies in order to answer our primary research question, that is, "What is the best tokenization strategy for Korean NLP tasks?" Experimental results demonstrate that a hybrid approach of morphological segmentation followed by BPE works best in Korean to/from English machine translation and natural language understanding tasks such as KorNLI, KorSTS, NSMC, and PAWS-X. As an exception, for KorQuAD, the Korean extension of SQuAD, BPE segmentation turns out to be the most effective.Our code and pre-trained models are publicly available at https://github.com/ kakaobrain/kortok.

show abstract

“…Several works on morphologically-rich NMT have focused on using morphological analysis to pre-process the training data (Luong et al, 2016;Huck et al, 2017;Tawfik et al, 2019). Gulcehre et al (2015) segment each Turkish sentence into a sequence of morpheme units and remove any nonsurface morphemes for Turkish-English translation.…”

Section: Related Workmentioning

confidence: 99%

Multi-Task Neural Model for Agglutinative Language Translation

Pan

Yang³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

View full text Add to dashboard Cite

Neural machine translation (NMT) has achieved impressive performance recently by using large-scale parallel corpora. However, it struggles in the low-resource and morphologically-rich scenarios of agglutinative language translation task. Inspired by the finding that monolingual data can greatly improve the NMT performance, we propose a multi-task neural model that jointly learns to perform bi-directional translation and agglutinative language stemming. Our approach employs the shared encoder and decoder to train a single model without changing the standard NMT architecture but instead adding a token before each source-side sentence to specify the desired target outputs of the two different tasks. Experimental results on Turkish-English and Uyghur-Chinese show that our proposed approach can significantly improve the translation performance on agglutinative languages by using a small amount of monolingual data.

show abstract

Morphology-aware Word-Segmentation in Dialectal Arabic Adaptation of Neural Machine Translation

Cited by 11 publications

References 10 publications

Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation

Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation

An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks

Multi-Task Neural Model for Agglutinative Language Translation

Contact Info

Product

Resources

About