paper-with-me

Papers

Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation

2020-01-02 · Yirong Pan, Xiao Li, Yating Yang, Rui Dong

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 low-resource and morphologically-rich agglutinative languages, which have complex morphology and large vocabulary. In this paper, we propose a morphological word segmentation method on the source-side 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.

📄 PDF Abstract BibTeX arXiv:2001.01589

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTSegmentationTranslation

Similar Papers 제목 키워드 기반

Building Morphological Chains for Agglutinative Languages

2017-05-05 · Serkan Ozen, Burcu Can

In this paper, we build morphological chains for agglutinative languages by using a log-linear model for the morphological segmentation task. The model is based on the unsupervised morphological segmentation system calle…

Segmentation

Morphologically-Guided Segmentation For Translation of Agglutinative Low-Resource Languages

2021-08-01 · MTSummit 2021 8 · William Chen, Brett Fazio

Neural Machine Translation (NMT) for Low Resource Languages (LRL) is often limited by the lack of available training data, making it necessary to explore additional techniques to improve translation quality. We propose t…

Machine TranslationNMTSegmentationTranslation

A Morphology-Based Representation Model for LSTM-Based Dependency Parsing of Agglutinative Languages

2018-10-01 · CONLL 2018 10 · {\c{S}}aziye Bet{\"u}l {\"O}zate{\c{s}}, Arzucan {\"O}zg{\"u}r, Tunga G{\"u}ng{\"o}r, Balk{\i}z {\"O}zt{\"u}rk

We propose two word representation models for agglutinative languages that better capture the similarities between words which have similar tasks in sentences. Our models highlight the morphological features in words and…

Dependency ParsingWord Embeddings

Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation

2023-05-11 · Francois Meyer, Jan Buys

Subword segmenters like BPE operate as a preprocessing step in neural machine translation and other (conditional) language models. They are applied to datasets before training, so translation or text generation quality r…

Machine TranslationSentenceText GenerationTranslation

Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation

2019-06-01 · WS 2019 6 · Vladislav Mikhailov, Lorenzo Tosi, Anastasia Khorosheva, Oleg Serikov

The paper describes initial experiments in data-driven cross-lingual morphological analysis of open-category words using a combination of unsupervised morpheme segmentation, annotation projection and an LSTM encoder-deco…

DecoderMorphological Analysis