Saved in:
Bibliographic Details
Main Authors: Kondo, Shuhei, Sudoh, Katsuhito, Matsumoto, Yuji
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.27938
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915898287194112
author Kondo, Shuhei
Sudoh, Katsuhito
Matsumoto, Yuji
author_facet Kondo, Shuhei
Sudoh, Katsuhito
Matsumoto, Yuji
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27938
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Top-down string-to-dependency Neural Machine Translation
Kondo, Shuhei
Sudoh, Katsuhito
Matsumoto, Yuji
Computation and Language
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.
title Top-down string-to-dependency Neural Machine Translation
topic Computation and Language
url https://arxiv.org/abs/2603.27938