paper-with-me

Papers

BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages

2022-03-16 · Findings (ACL) 2022 5 · Manuel Mager, Arturo Oncevay, Elisabeth Mager, Katharina Kann, Ngoc Thang Vu

Morphologically-rich polysynthetic languages present a challenge for NLP systems due to data sparsity, and a common strategy to handle this issue is to apply subword segmentation. We investigate a wide variety of supervised and unsupervised morphological segmentation methods for four polysynthetic languages: Nahuatl, Raramuri, Shipibo-Konibo, and Wixarika. Then, we compare the morphologically inspired segmentation methods against Byte-Pair Encodings (BPEs) as inputs for machine translation (MT) when translating to and from Spanish. We show that for all language pairs except for Nahuatl, an unsupervised morphological segmentation algorithm outperforms BPEs consistently and that, although supervised methods achieve better segmentation scores, they under-perform in MT challenges. Finally, we contribute two new morphological segmentation datasets for Raramuri and Shipibo-Konibo, and a parallel corpus for Raramuri--Spanish.

📄 PDF Abstract BibTeX arXiv:2203.08954

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationSegmentationTranslation

Similar Papers 제목 키워드 기반

The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation

2021-03-20 · EACL 2021 2 · Jonne Sälevä, Constantine Lignos

This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level w…

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationSegmentation+2

Quantifying Synthesis and Fusion and their Impact on Machine Translation

2022-05-06 · NAACL 2022 7 · Arturo Oncevay, Duygu Ataman, Niels van Berkel, Barry Haddow 외

Theoretical work in morphological typology offers the possibility of measuring morphological diversity on a continuous scale. However, literature in Natural Language Processing (NLP) typically labels a whole language wit…

DiversityMachine TranslationTranslation

Quantifying Synthesis and Fusion and their Impact on Machine Translation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Theoretical work in morphological typology offers the possibility of measuring morphological diversity on a continuous scale. However, literature in NLP typically labels a whole language with a strict type of morphology,…

DiversityMachine TranslationTranslation

Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text

2022-10-11 · Marwa Gaser, Manuel Mager, Injy Hamed, Nizar Habash 외

Data sparsity is one of the main challenges posed by code-switching (CS), which is further exacerbated in the case of morphologically rich languages. For the task of machine translation (MT), morphological segmentation h…

Machine TranslationSegmentation

Improving the Performance of Neural Machine Translation Involving Morphologically Rich Languages

2016-12-07 · Krupakar Hans, R S Milton

The advent of the attention mechanism in neural machine translation models has improved the performance of machine translation systems by enabling selective lookup into the source sentence. In this paper, the efficiencie…

DecoderMachine TranslationSentenceTranslation