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 > How to Pay Attention: Learning to Transfer Knowledge between Sentences and Tokens
How to Pay Attention: Learning to Transfer Knowledge between Sentences and TokensAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Edoardo Maria Ponti. Self-attention architectures allow models to dynamically decide which areas of the input should receive more focus. During the construction of text representations, attention weights also provide a way of quantifying the importance of different input areas. In this talk, we investigate how attention mechanisms can be turned into sequence labelers, opening up some new and interesting applications. These networks learn to predict labels for individual tokens, based only on sentence-level supervision, even without having seen any examples of sequence labeling. In addition, optimizing on the token level explicitly teaches the model where it should be focusing, leading to improvements in text classification. We will also discuss experiments with learning directly from the human cognitive signal, guiding the models to internally behave more like their users. The resulting architectures for text classification and sequence labeling are more accurate, more interpretable and make decisions in more predictable ways. 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 listsType the title of a new list here CUSPE Forum Mendeley Data - Viewer - 1975 PhD math international bio synthesis ... https://data.mendeley.com/.../2966f1cd-3b53-45bf-a685-1513718... Traduire cette page 7 nov. 2016 - ... Boudemagh, N (2016), “ENERGY EFFCIENCY”, Mendeley Data, v1 http://dx.doi.org/Other talksThe evolution of the interstellar medium in merging galaxies Batchelor lecture 1: Forces when moving in a granular medium: stirring, drilling and segregation “Stay in your shell, that will be of use to you:” The miniature shell collection in Petronella Brandt’s dollhouse Can machine learning trump theory in communication system design? Welcome and Introduction Polymer bioelectronics: Devices, tissue engineering and therapeutics |