paper-with-me

홈 › Papers

Improving English to Sinhala Neural Machine Translation using Part-of-Speech Tag

2022-02-17 · Ravinga Perera, Thilakshi Fonseka, Rashmini Naranpanawa, Uthayasanker Thayasivam

The performance of Neural Machine Translation (NMT) depends significantly on the size of the available parallel corpus. Due to this fact, low resource language pairs demonstrate low translation performance compared to high resource language pairs. The translation quality further degrades when NMT is performed for morphologically rich languages. Even though the web contains a large amount of information, most people in Sri Lanka are unable to read and understand English properly. Therefore, there is a huge requirement of translating English content to local languages to share information among locals. Sinhala language is the primary language in Sri Lanka and building an NMT system that can produce quality English to Sinhala translations is difficult due to the syntactic divergence between these two languages under low resource constraints. Thus, in this research, we explore effective methods of incorporating Part of Speech (POS) tags to the Transformer input embedding and positional encoding to further enhance the performance of the baseline English to Sinhala neural machine translation model.

📄 PDF Abstract BibTeX arXiv:2202.08882

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTPOSTAGTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Evolutionary Algorithm for Sinhala to English Translation

2019-07-06 · J. K. Joseph, W. M. T. Chathurika, A. Nugaliyadde, Y. Mallawarachchi

Machine Translation (MT) is an area in natural language processing, which focus on translating from one language to another. Many approaches ranging from statistical methods to deep learning approaches are used in order …

Machine TranslationSentenceTranslation

Neural Machine Translation for Sinhala-English Code-Mixed Text

2021-09-01 · RANLP 2021 9 · Archchana Kugathasan, Sagara Sumathipala

Code-mixing has become a moving method of communication among multilingual speakers. Most of the social media content of the multilingual societies are written in code-mixed text. However, most of the current translation…

DecoderMachine TranslationNMTTranslation

Data Augmentation and Terminology Integration for Domain-Specific Sinhala-English-Tamil Statistical Machine Translation

2020-11-05 · Aloka Fernando, Surangika Ranathunga, Gihan Dias

Out of vocabulary (OOV) is a problem in the context of Machine Translation (MT) in low-resourced languages. When source and/or target languages are morphologically rich, it becomes even worse. Bilingual list integration …

Data AugmentationMachine TranslationTranslation

A Multi-way Parallel Named Entity Annotated Corpus for English, Tamil and Sinhala

2024-12-03 · Surangika Ranathunga, Asanka Ranasinghea, Janaka Shamala, Ayodya Dandeniyaa 외

This paper presents a multi-way parallel English-Tamil-Sinhala corpus annotated with Named Entities (NEs), where Sinhala and Tamil are low-resource languages. Using pre-trained multilingual Language Models (mLMs), we est…

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine Translationnamed-entity-recognition+5

Findings of the WMT 2020 Shared Task on Quality Estimation

2020-11-01 · WMT (EMNLP) 2020 11 · Lucia Specia, Frédéric Blain, Marina Fomicheva, Erick Fonseca 외

We report the results of the WMT20 shared task on Quality Estimation, where the challenge is to predict the quality of the output of neural machine translation systems at the word, sentence and document levels. This edit…

Machine TranslationSentenceTranslation