184 citations · 455 across the 25 of their papers we have counts for
27 papers
Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
Rami Botros, Rohit Prabhavalkar, Johan Schalkwyk +3
In end-to-end (E2E) speech recognition models, a representational tight-coupling inevitably emerges between the encoder and the decoder. We build upon recent work that has begun to…
Towards Computationally Verifiable Semantic Grounding for Language Models
Chris Alberti, Kuzman Ganchev, Michael Collins +2
The paper presents an approach to semantic grounding of language models (LMs) that conceptualizes the LM as a conditional model generating text given a desired semantic message for…
Scaling Laws for Neural Machine Translation
Behrooz Ghorbani, Orhan Firat, Markus Freitag +5
We present an empirical study of scaling properties of encoder-decoder Transformer models used in neural machine translation (NMT). We show that cross-entropy loss as a function of…
Data Troubles in Sentence Level Confidence Estimation for Machine Translation
Ciprian Chelba, Junpei Zhou, Yuezhang +4
The paper investigates the feasibility of confidence estimation for neural machine translation models operating at the high end of the performance spectrum. As a side product of th…
Multi-Stage Influence Function
Hongge Chen, Si Si, Yang Li +4
Multi-stage training and knowledge transfer, from a large-scale pretraining task to various finetuning tasks, have revolutionized natural language processing and computer vision re…
Practical Perspectives on Quality Estimation for Machine Translation
Junpei Zhou, Ciprian Chelba, Yuezhang +1
Sentence level quality estimation (QE) for machine translation (MT) attempts to predict the translation edit rate (TER) cost of post-editing work required to correct MT output. We…