DeepAI AI Chat
Log In Sign Up

Example-Based Machine Translation from Text to a Hierarchical Representation of Sign Language

by   Élise Bertin-Lemée, et al.

This article presents an original method for Text-to-Sign Translation. It compensates data scarcity using a domain-specific parallel corpus of alignments between text and hierarchical formal descriptions of Sign Language videos in AZee. Based on the detection of similarities present in the source text, the proposed algorithm recursively exploits matches and substitutions of aligned segments to build multiple candidate translations for a novel statement. This helps preserving Sign Language structures as much as possible before falling back on literal translations too quickly, in a generative way. The resulting translations are in the form of AZee expressions, designed to be used as input to avatar synthesis systems. We present a test set tailored to showcase its potential for expressiveness and generation of idiomatic target language, and observed limitations. This work finally opens prospects on how to evaluate translation and linguistic aspects, such as accuracy and grammatical fluency.


page 1

page 2

page 3

page 4


An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation

Sign language translation systems are complex and require many component...

Synthesising Sign Language from semantics, approaching "from the target and back"

We present a Sign Language modelling approach allowing to build grammars...

Explaining CLIP through Co-Creative Drawings and Interaction

This paper analyses a visual archive of drawings produced by an interact...

Représentation graphique de la langue des signes française et édition logicielle

Cet article propose une méthode pour définir une forme graphique éditabl...

Bidirectional UML Visualisation of VDM Models

The VDM-PlantUML Plugin enables translations between the text based UML ...

Time-Aware Ancient Chinese Text Translation and Inference

In this paper, we aim to address the challenges surrounding the translat...