paper-with-me

Papers

A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation

2016-03-19 · ACL 2016 8 · Junyoung Chung, Kyunghyun Cho, Yoshua Bengio

The existing machine translation systems, whether phrase-based or neural, have relied almost exclusively on word-level modelling with explicit segmentation. In this paper, we ask a fundamental question: can neural machine translation generate a character sequence without any explicit segmentation? To answer this question, we evaluate an attention-based encoder-decoder with a subword-level encoder and a character-level decoder on four language pairs--En-Cs, En-De, En-Ru and En-Fi-- using the parallel corpora from WMT'15. Our experiments show that the models with a character-level decoder outperform the ones with a subword-level decoder on all of the four language pairs. Furthermore, the ensembles of neural models with a character-level decoder outperform the state-of-the-art non-neural machine translation systems on En-Cs, En-De and En-Fi and perform comparably on En-Ru.

📄 PDF Abstract BibTeX arXiv:1603.06147

Code (2)

nyu-dl/dl4mt-c2c
nyu-dl/dl4mt-cdec

Tasks

Decoderde-enMachine TranslationSegmentationTranslation

Similar Papers 제목 키워드 기반

Towards Neural Machine Translation with Latent Tree Attention

2017-09-06 · WS 2017 9 · James Bradbury, Richard Socher

Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translati…

DecoderMachine Translationreinforcement-learningReinforcement Learning+3

Fully Character-Level Neural Machine Translation without Explicit Segmentation

2016-10-10 · TACL 2017 1 · Jason Lee, Kyunghyun Cho, Thomas Hofmann

Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to …

de-enMachine TranslationNMTTranslation

SHED Light on Segmentation for Dense Prediction

2026-01-30 · Seung Hyun Lee, Sangwoo Mo, Stella X. Yu arxiv

Dense prediction infers per-pixel values from a single image and is fundamental to 3D perception and robotics. Although real-world scenes exhibit strong structure, existing methods treat it as an independent pixel-wise p…

Domain GeneralizationSemantic Segmentation3D Reconstruction

Neural Sequence-to-sequence Learning of Internal Word Structure

2017-08-01 · CONLL 2017 8 · Tatyana Ruzsics, Tanja Samard{\v{z}}i{\'c}

Learning internal word structure has recently been recognized as an important step in various multilingual processing tasks and in theoretical language comparison. In this paper, we present a neural encoder-decoder model…

DecoderLanguage ModelingLanguage ModellingMachine Translation+1

ERAS: Evaluating the Robustness of Chinese NLP Models to Morphological Garden Path Errors

2024-10-16 · Qinchan Li, Sophie Hao

In languages without orthographic word boundaries, NLP models perform word segmentation, either as an explicit preprocessing step or as an implicit step in an end-to-end computation. This paper shows that Chinese NLP mod…

SegmentationSentenceSentiment Analysis