74 citations · 153 across the 14 of their papers we have counts for
15 papers
A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism
Brian Thompson, Mehak Preet Dhaliwal, Peter Frisch +2
We show that content on the web is often translated into many languages, and the low quality of these multi-way translations indicates they were likely created using Machine Transl…
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
Juan Zuluaga-Gomez, Zhaocheng Huang, Xing Niu +5
Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversat…
Speaker Diarization of Scripted Audiovisual Content
Yogesh Virkar, Brian Thompson, Rohit Paturi +2
The media localization industry usually requires a verbatim script of the final film or TV production in order to create subtitles or dubbing scripts in a foreign language. In part…
Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters
Proyag Pal, Brian Thompson, Yogesh Virkar +3
To translate speech for automatic dubbing, machine translation needs to be isochronous, i.e. translated speech needs to be aligned with the source in terms of speech durations. We…
Jointly Optimizing Translations and Speech Timing to Improve Isochrony in Automatic Dubbing
Alexandra Chronopoulou, Brian Thompson, Prashant Mathur +3
Automatic dubbing (AD) is the task of translating the original speech in a video into target language speech. The new target language speech should satisfy isochrony; that is, the…
Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing
William Brannon, Yogesh Virkar, Brian Thompson
We investigate how humans perform the task of dubbing video content from one language into another, leveraging a novel corpus of 319.57 hours of video from 54 professionally produc…
Improving Robustness of Retrieval Augmented Translation via Shuffling of Suggestions
Cuong Hoang, Devendra Sachan, Prashant Mathur +2
Several recent studies have reported dramatic performance improvements in neural machine translation (NMT) by augmenting translation at inference time with fuzzy-matches retrieved…
Improving Retrieval Augmented Neural Machine Translation by Controlling Source and Fuzzy-Match Interactions
Cuong Hoang, Devendra Sachan, Prashant Mathur +2
We explore zero-shot adaptation, where a general-domain model has access to customer or domain specific parallel data at inference time, but not during training. We build on the id…
Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metric
Giorgos Vernikos, Brian Thompson, Prashant Mathur +1
We hypothesize that existing sentence-level machine translation (MT) metrics become less effective when the human reference contains ambiguities. To verify this hypothesis, we pres…
Improving Arabic Diacritization by Learning to Diacritize and Translate
Brian Thompson, Ali Alshehri
We propose a novel multitask learning method for diacritization which trains a model to both diacritize and translate. Our method addresses data sparsity by exploiting large, readi…
Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity
Brian Thompson, Matt Post
Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompso…
Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
Brian Thompson, Matt Post
We frame the task of machine translation evaluation as one of scoring machine translation output with a sequence-to-sequence paraphraser, conditioned on a human reference. We propo…
Simulated Multiple Reference Training Improves Low-Resource Machine Translation
Huda Khayrallah, Brian Thompson, Matt Post +1
Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings…
Exploiting Sentence Order in Document Alignment
Brian Thompson, Philipp Koehn
We present a simple document alignment method that incorporates sentence order information in both candidate generation and candidate re-scoring. Our method results in 61% relative…
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
Brian Thompson, Huda Khayrallah, Antonios Anastasopoulos +7
To better understand the effectiveness of continued training, we analyze the major components of a neural machine translation system (the encoder, decoder, and each embedding space…