Search Results for author:
Found 7 papers, 2 papers with code
MEEP: An Open-Source Platform for Human-Human Dialog Collection and End-to-End Agent Training
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-button environment.
DiDi Labs' End-to-end System for the IWSLT 2020 Offline Speech TranslationTask
This paper describes the system that was submitted by DiDi Labs to the offline speech translation task for IWSLT 2020.
FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN
The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2020) featured this year six challenge tracks: (i) Simultaneous speech translation, (ii) Video speech translation, (iii) Offline speech translation, (iv) Conversational speech translation, (v) Open domain translation, and (vi) Non-native speech translation.
Dual Monolingual Cross-Entropy Delta Filtering of Noisy Parallel Data
We introduce a purely monolingual approach to filtering for parallel data from a noisy corpus in a low-resource scenario.
Data Selection with Cluster-Based Language Difference Models and Cynical Selection
Building on existing work on class-based language difference models, we first introduce a cluster-based method that uses Brown clusters to condense the vocabulary of the corpora.
Cynical Selection of Language Model Training Data
(2) The selected sentences are not guaranteed to be able to model the in-domain data, nor to even cover the in-domain data.
