Conference paper Open Access

Efficient Bilingual Generalization from Neural Transduction Grammar Induction

Yan, Yuchen; Wu, Dekai; Kumyol, Serkan

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Yan, Yuchen</dc:creator>
  <dc:creator>Wu, Dekai</dc:creator>
  <dc:creator>Kumyol, Serkan</dc:creator>
  <dc:description>We introduce (1) a novel neural network structure for bilingual modeling of sentence pairs that allows efficient capturing of bilingual relationship via biconstituent composition, (2) the concept of neural network biparsing, which applies to not only machine translation (MT) but also to a variety of other bilingual research areas, and (3) the concept of a biparsing-backpropagation training loop, which we hypothesize that can efficiently learn complex biparse tree patterns. Our work distinguishes from sequential attention-based models, which are more traditionally found in neural machine translation (NMT) in three aspects. First, our model enforces compositional constraints. Second, our model has a smaller search space in terms of discovering bilingual relationships from bilingual sentence pairs. Third, our model produces explicit biparse trees, which enable transparent error analysis during evaluation and external tree constraints during training.</dc:description>
  <dc:title>Efficient Bilingual Generalization from Neural Transduction Grammar Induction</dc:title>
All versions This version
Views 124124
Downloads 9292
Data volume 35.4 MB35.4 MB
Unique views 115115
Unique downloads 8080


Cite as