A hybrid formalism to parse Sign Languages
This work addresses the lack of annotated corpora and consistent models for sign language syntactic analysis, which is an incremental advancement in computational linguistics for sign language processing.
The paper tackles the problem of automatic annotation for sign language syntax by introducing a hybrid formalism that combines constituency-based and dependency-based models, and reports results from experiments on both real and synthetic corpora.
Sign Language (SL) linguistic is dependent on the expensive task of annotating. Some automation is already available for low-level information (eg. body part tracking) and the lexical level has shown significant progresses. The syntactic level lacks annotated corpora as well as complete and consistent models. This article presents a solution for the automatic annotation of SL syntactic elements. It exposes a formalism able to represent both constituency-based and dependency-based models. The first enable the representation the structures one may want to annotate, the second aims at fulfilling the holes of the first. A parser is presented and used to conduct two experiments on the solution. One experiment is on a real corpus, the other is on a synthetic corpus.