Search Results for author: Mihir Kale

Found 16 papers, 5 papers with code

Machine Translation Pre-training for Data-to-Text Generation - A Case Study in Czech

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.

Data-to-Text Generation Translation +2

Improving Compositional Generalization with Self-Training for Data-to-Text Generation

no code implementations16 Oct 2021 Sanket Vaibhav Mehta, Jinfeng Rao, Yi Tay, Mihir Kale, Ankur Parikh, Hongtao Zhong, Emma Strubell

In this work, we systematically study the compositional generalization of current state-of-the-art generation models in data-to-text tasks.

Data-to-Text Generation

nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?

no code implementations ACL 2021 Mihir Kale, Aditya Siddhant, Rami Al-Rfou, Linting Xue, Noah Constant, Melvin Johnson

Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks.

Language Modelling Machine Translation +2

Using Machine Translation to Localize Task Oriented NLG Output

no code implementations9 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.

Domain Adaptation Machine Translation +1

Automatic Construction of Evaluation Suites for Natural Language Generation Datasets

no code implementations16 Jun 2021 Simon Mille, Kaustubh D. Dhole, Saad Mahamood, Laura Perez-Beltrachini, Varun Gangal, Mihir Kale, Emiel van Miltenburg, Sebastian Gehrmann

By applying this framework to the GEM generation benchmark, we propose an evaluation suite made of 80 challenge sets, demonstrate the kinds of analyses that it enables and shed light onto the limits of current generation models.

Text Generation

nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?

no code implementations3 Jun 2021 Mihir Kale, Aditya Siddhant, Noah Constant, Melvin Johnson, Rami Al-Rfou, Linting Xue

Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks.

Language Modelling Machine Translation +2

mT5: A massively multilingual pre-trained text-to-text transformer

5 code implementations NAACL 2021 Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel

The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks.

Common Sense Reasoning Natural Language Inference +3

Template Guided Text Generation for Task-Oriented Dialogue

1 code implementation EMNLP 2020 Mihir Kale, Abhinav Rastogi

Virtual assistants such as Google Assistant, Amazon Alexa, and Apple Siri enable users to interact with a large number of services and APIs on the web using natural language.

Data-to-Text Generation Language Modelling

Machine Translation Pre-training for Data-to-Text Generation -- A Case Study in Czech

no code implementations5 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.

Data-to-Text Generation Translation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.