COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Language Technology Lab Seminars > Making Better Use of (Large) Language and Translation Models with Simple Inference Improvements.
Making Better Use of (Large) Language and Translation Models with Simple Inference Improvements.Add to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Panagiotis Fytas. In a field where the state of the art is often advanced by scale – building larger models on more data – I will make the argument that a surprising amount of progress can be achieved with simple modifications to inference algorithms. In this talk, I will focus on machine translation, where massively multilingual models and large language models have been shown to handle many translation directions, but which still suffer from problems such as hallucinations or translations in the wrong language. I will show how these issues can be reduced massively with contrastive decoding methods that pair each input with appropriate contrastive inputs. I will also discuss Minimum Bayes Risk (MBR) Decoding, a decoding method that has received renewed interest because it avoids common pitfalls in machine translation, but which suffers from a major increase in computational cost. However, I will show how the computational complexity of MBR decoding can be reduced from quadratic to linear to the number of samples by using reference aggregation. This talk is part of the Language Technology Lab Seminars series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsKinds of Hospital Beds Obtainable at Markham Cambridge Experimental and Behavioural Research Group (CEBEG) PitagogorasOther talksBiotechnological artefacts and the in vivo/in vitro problem The Cambridge Room: engagement and inclusion in spatial planning Milner Seminar - February 2024 Reconstructing humanity’s ghosts: genetic evidence for interbreeding among archaic humans Investigating cortico-cortical plasticity in motor brain control regions in young and older adults. Split and splice: a phenomenology of experimentation |