12 citations · 22 across the 4 of their papers we have counts for
5 papers · 1 filter
Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation
Hieu Hoang, Amittai Axelrod
Simultaneous speech translation must emit useful target text before the source is complete while preserving every committed token. We adapt a full-utterance speech language model u…
Dynamic Lagging using Stable-Prefix Training for Simultaneous Translation
Hieu Hoang, Amittai Axelrod, Matt Post
In streaming simultaneous speech translation, the speech translation system is trained to learn a read-write policy that alternates between consuming source words and generating ta…
MEEP: An Open-Source Platform for Human-Human Dialog Collection and End-to-End Agent Training
Arkady Arkhangorodsky, Amittai Axelrod, Christopher Chu +6
We create a new task-oriented dialog platform (MEEP) where agents are given considerable freedom in terms of utterances and API calls, but are constrained to work within a push-but…
Data Selection with Cluster-Based Language Difference Models and Cynical Selection
Lucía Santamaría, Amittai Axelrod
We present and apply two methods for addressing the problem of selecting relevant training data out of a general pool for use in tasks such as machine translation. Building on exis…
Cynical Selection of Language Model Training Data
Amittai Axelrod
The Moore-Lewis method of "intelligent selection of language model training data" is very effective, cheap, efficient... and also has structural problems. (1) The method defines re…