no code implementations • INLG (ACL) 2020 • Mihir Kale, Scott Roy
Since the structured data is generally expressed in English, text generation into other languages involves elements of translation, transliteration and copying - elements already encoded in neural machine translation systems.
no code implementations • 9 Jul 2021 • Scott Roy, Cliff Brunk, Kyu-Young Kim, Justin Zhao, Markus Freitag, Mihir Kale, Gagan Bansal, Sidharth Mudgal, Chris Varano
One of the challenges in a task oriented natural language application like the Google Assistant, Siri, or Alexa is to localize the output to many languages.
no code implementations • 5 Apr 2020 • Mihir Kale, Scott Roy
Since the structured data is generally expressed in English, text generation into other languages involves elements of translation, transliteration and copying - elements already encoded in neural machine translation systems.
Ranked #1 on Data-to-Text Generation on Czech Restaurant NLG
no code implementations • WS 2019 • Markus Freitag, Isaac Caswell, Scott Roy
In this work, we train an Automatic Post-Editing (APE) model and use it to reveal biases in standard Machine Translation (MT) evaluation procedures.
1 code implementation • EMNLP 2018 • Markus Freitag, Scott Roy
Generating text from structured data is important for various tasks such as question answering and dialog systems.
no code implementations • 19 Feb 2016 • Shalini Ghosh, Oriol Vinyals, Brian Strope, Scott Roy, Tom Dean, Larry Heck
We evaluate CLSTM on three specific NLP tasks: word prediction, next sentence selection, and sentence topic prediction.
no code implementations • NeurIPS 2008 • Deepak Agarwal, Bee-Chung Chen, Pradheep Elango, Nitin Motgi, Seung-Taek Park, Raghu Ramakrishnan, Scott Roy, Joe Zachariah
It is now deployed on a major Internet portal, and selects articles to serve to hundreds of millions of user visits per day, significantly increasing the number of user clicks over the original manual approach, in which editors periodically selected articles to display.