mlsanityData to 14 Oct 2026

Top-down string-to-dependency Neural Machine Translation

arXiv 2603.27938 ↗First posted 30 Mar 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 30 Mar 2026.

Builds on

28 of 49 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Layer Normalizationcited by 5,669
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  7. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  8. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  9. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  10. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  11. 2016Using the Output Embedding to Improve Language Modelscited by 272
  12. 2015A Theoretically Grounded Application of Dropout in Recurrent Neural Networkscited by 161
16 more
  1. 2016Recurrent Neural Network Grammarscited by 109
  2. 2018The Best of Both Worlds: Combining Recent Advances in Neural Machine Translationcited by 102
  3. 2016Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modelingcited by 92
  4. 2022Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scalecited by 41
  5. 2016Tree-to-Sequence Attentional Neural Machine Translationcited by 28
  6. 2017Towards String-to-Tree Neural Machine Translationcited by 19
  7. 2018Scheduled Multi-Task Learning: From Syntax to Translationcited by 18
  8. 2018A Tree-based Decoder for Neural Machine Translationcited by 18
  9. 2017Learning to Parse and Translate Improves Neural Machine Translationcited by 16
  10. 2017Improved Neural Machine Translation with a Syntax-Aware Encoder and Decodercited by 16
  11. 2017Predicting Target Language CCG Supertags Improves Neural Machine Translationcited by 15
  12. 2015Top-down Tree Long Short-Term Memory Networkscited by 12
  13. 2017Modeling Source Syntax for Neural Machine Translationcited by 12
  14. 2023Explicit Syntactic Guidance for Neural Text Generationcited by 8
  15. 2024Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Modelscited by 8
  16. 2018Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMTcited by 2

Built on by

Not cited yet.