arXiv Open Access 2026

Top-down string-to-dependency Neural Machine Translation

Shuhei Kondo Katsuhito Sudoh Yuji Matsumoto

Lihat Sumber

Abstrak

Most of modern neural machine translation (NMT) models are based on an encoder-decoder framework with an attention mechanism. While they perform well on standard datasets, they can have trouble in translation of long inputs that are rare or unseen during training. Incorporating target syntax is one approach to dealing with such length-related problems. We propose a novel syntactic decoder that generates a target-language dependency tree in a top-down, left-to-right order. Experiments show that the proposed top-down string-to-tree decoding generalizes better than conventional sequence-to-sequence decoding in translating long inputs that are not observed in the training data.

Topik & Kata Kunci

cs.CL

Penulis (3)

Shuhei Kondo

Katsuhito Sudoh

Yuji Matsumoto

Format Sitasi

APA MLA BibTeX

Kondo, S., Sudoh, K., Matsumoto, Y. (2026). Top-down string-to-dependency Neural Machine Translation. https://arxiv.org/abs/2603.27938

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2026
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓