Friday, 19th May - 11am Machel Reid : Seminar Title: Learning to Edit for Text Generation Abstract: In this talk, we will go over work on text editing for text generation. First, we will cover targeted editing (e.g. style transfer), then we will go over learnings from how humans edit on Wikipedia, culminating in a generic sdit-based text-generation method, DiffusER, based on denoising diffusion models. DiffusER is able to perform edit-based generation, allowing it to revise existing text, a capability that many current models inherently lack. In addition to being a strong generative model on its own, DiffusER can also perform other types of generation, such as allowing a user to condition generation on a prototype or incomplete sequence and revise based on previous edits. Bio: Machel Reid is a research scientist at Google DeepMind working on NLP research, with a focus on multilingual NLP. He was previously a visiting student at Carnegie Mellon University, advised by Graham Neubig and researcher at the University of Tokyo at Matsuo Lab with Yutaka Matsuo Add to your calendar vCal iCal May 19 2023 11.00 - 12.00 Friday, 19th May - 11am Machel Reid : Seminar This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk. Informatics Forum, G.03 and by online invitation Contact
Friday, 19th May - 11am Machel Reid : Seminar Title: Learning to Edit for Text Generation Abstract: In this talk, we will go over work on text editing for text generation. First, we will cover targeted editing (e.g. style transfer), then we will go over learnings from how humans edit on Wikipedia, culminating in a generic sdit-based text-generation method, DiffusER, based on denoising diffusion models. DiffusER is able to perform edit-based generation, allowing it to revise existing text, a capability that many current models inherently lack. In addition to being a strong generative model on its own, DiffusER can also perform other types of generation, such as allowing a user to condition generation on a prototype or incomplete sequence and revise based on previous edits. Bio: Machel Reid is a research scientist at Google DeepMind working on NLP research, with a focus on multilingual NLP. He was previously a visiting student at Carnegie Mellon University, advised by Graham Neubig and researcher at the University of Tokyo at Matsuo Lab with Yutaka Matsuo Add to your calendar vCal iCal May 19 2023 11.00 - 12.00 Friday, 19th May - 11am Machel Reid : Seminar This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk. Informatics Forum, G.03 and by online invitation Contact
May 19 2023 11.00 - 12.00 Friday, 19th May - 11am Machel Reid : Seminar This event is co-organised by ILCC and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk.
