Bidirectional American Sign Language to English Translation
This work addresses communication barriers for the deaf and hard-of-hearing community by enabling bidirectional ASL-English translation, though it appears incremental as it builds on existing IBM models.
The authors tackled the problem of bidirectional translation between American Sign Language (ASL) and English by using an adjusted IBM word-alignment model 1 to generate translations that maximize posterior distributions, enabling quantification of translation fluency and faithfulness.
We outline a bidirectional translation system that converts sentences from American Sign Language (ASL) to English, and vice versa. To perform machine translation between ASL and English, we utilize a generative approach. Specifically, we employ an adjustment to the IBM word-alignment model 1 (IBM WAM1), where we define language models for English and ASL, as well as a translation model, and attempt to generate a translation that maximizes the posterior distribution defined by these models. Then, using these models, we are able to quantify the concepts of fluency and faithfulness of a translation between languages.