Fast BTG-Forest-Based Hierarchical Sub-sentential Alignment

11/20/2017
by   Hao Wang, et al.
0

In this paper, we propose a novel BTG-forest-based alignment method. Based on a fast unsupervised initialization of parameters using variational IBM models, we synchronously parse parallel sentences top-down and align hierarchically under the constraint of BTG. Our two-step method can achieve the same run-time and comparable translation performance as fast_align while it yields smaller phrase tables. Final SMT results show that our method even outperforms in the experiment of distantly related languages, e.g., English-Japanese.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/21/2020

Subword Sampling for Low Resource Word Alignment

Annotation projection is an important area in NLP that can greatly contr...
research
11/01/2016

Faster decoding for subword level Phrase-based SMT between related languages

A common and effective way to train translation systems between related ...
research
01/14/2019

Unsupervised Neural Machine Translation with SMT as Posterior Regularization

Without real bilingual corpus available, unsupervised Neural Machine Tra...
research
12/08/2020

Globetrotter: Unsupervised Multilingual Translation from Visual Alignment

Multi-language machine translation without parallel corpora is challengi...
research
02/23/2017

Utilizing Lexical Similarity between Related, Low-resource Languages for Pivot-based SMT

We investigate pivot-based translation between related languages in a lo...
research
11/19/2012

A Rule-Based Approach For Aligning Japanese-Spanish Sentences From A Comparable Corpora

The performance of a Statistical Machine Translation System (SMT) system...
research
01/27/2020

Optimization of Passive Chip Components Placement with Self-Alignment Effect for Advanced Surface Mounting Technology

Surface mount technology (SMT) is an enhanced method in electronic packa...

Please sign up or login with your details

Forgot password? Click here to reset