Dear All,
the Statistics and Probability group at the University of Nottingham organize a series of internal seminars which will be available to anyone interested, even outside the University of Nottingham.
Our next speaker is Dr *Rachel Carrington*. Seminar date and time: *11th* * of February at 2pm. *
Below you can find the Abstract and Title. Furthermore, you can find the Teams link to join the seminar.
Best Wishes, Fabrizio Leisen
You are cordially invited to the following seminar:
Rachel Carrington https://www.researchgate.net/profile/Rachel_Carrington2 (Internal Seminar) ----> *11**th** of* *February at 2pm*
*Title:* Semi-supervised word embeddings
*Abstract:* Word embeddings are a popular way of modelling language, in which words are represented as low-dimensional vectors. The aim is that distances between vectors correspond to relationships between words: words with similar meanings should be closer together in the embedding space. Recently this has been a growing area of interest, with applications including sentiment analysis, machine translation, and artificial intelligence. However, a disadvantage is that large amounts of data are generally needed to train word embedding models. In this talk I will first give an overview of how word embeddings are generated, and then I will outline a novel method of generating semi-supervised word embeddings, based on multidimensional scaling, which has the potential to reduce the amount of data needed to generate accurate word embeddings.
________________________________________________________________________________ Microsoft Teams meeting Join on your computer or mobile app Click here to join the meeting https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZDE4YWYxNmEtZTFlMC00NmQ0LThiNzItZjhmNmZkZGQ3OTk2%40thread.v2/0?context=%7b%22Tid%22%3a%2267bda7ee-fd80-41ef-ac91-358418290a1e%22%2c%22Oid%22%3a%22ac48eccb-4345-40d8-88e1-d7a8170bb19a%22%7d Learn more https://aka.ms/JoinTeamsMeeting | Meeting options https://teams.microsoft.com/meetingOptions/?organizerId=ac48eccb-4345-40d8-88e1-d7a8170bb19a&tenantId=67bda7ee-fd80-41ef-ac91-358418290a1e&threadId=19_meeting_ZDE4YWYxNmEtZTFlMC00NmQ0LThiNzItZjhmNmZkZGQ3OTk2@thread.v2&messageId=0&language=en-GB
Scusate l'ulteriore email.
L'orario sotto si riferisce a UK time. L'orario italiano è 3pm.
Cordiali Saluti,
Fabrizio Leisen Professor of Statistics University of Nottingham School of Mathematical Sciences University Park, Nottingham, NG7 2RD, UK
http://sites.google.com/site/fabrizioleisen/
---------- Forwarded message --------- Da: Fabrizio Leisen fabrizio.leisen@gmail.com Date: mer 3 feb 2021 alle ore 12:42 Subject: Statistics and Probability Seminars @University of Nottingham: Rachel Carrington To: Random@fields.dm.unipi.it
Dear All,
the Statistics and Probability group at the University of Nottingham organize a series of internal seminars which will be available to anyone interested, even outside the University of Nottingham.
Our next speaker is Dr *Rachel Carrington*. Seminar date and time: *11th* * of February at 2pm. *
Below you can find the Abstract and Title. Furthermore, you can find the Teams link to join the seminar.
Best Wishes, Fabrizio Leisen
You are cordially invited to the following seminar:
Rachel Carrington https://www.researchgate.net/profile/Rachel_Carrington2 (Internal Seminar) ----> *11**th** of* *February at 2pm*
*Title:* Semi-supervised word embeddings
*Abstract:* Word embeddings are a popular way of modelling language, in which words are represented as low-dimensional vectors. The aim is that distances between vectors correspond to relationships between words: words with similar meanings should be closer together in the embedding space. Recently this has been a growing area of interest, with applications including sentiment analysis, machine translation, and artificial intelligence. However, a disadvantage is that large amounts of data are generally needed to train word embedding models. In this talk I will first give an overview of how word embeddings are generated, and then I will outline a novel method of generating semi-supervised word embeddings, based on multidimensional scaling, which has the potential to reduce the amount of data needed to generate accurate word embeddings.
________________________________________________________________________________ Microsoft Teams meeting Join on your computer or mobile app Click here to join the meeting https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZDE4YWYxNmEtZTFlMC00NmQ0LThiNzItZjhmNmZkZGQ3OTk2%40thread.v2/0?context=%7b%22Tid%22%3a%2267bda7ee-fd80-41ef-ac91-358418290a1e%22%2c%22Oid%22%3a%22ac48eccb-4345-40d8-88e1-d7a8170bb19a%22%7d Learn more https://aka.ms/JoinTeamsMeeting | Meeting options https://teams.microsoft.com/meetingOptions/?organizerId=ac48eccb-4345-40d8-88e1-d7a8170bb19a&tenantId=67bda7ee-fd80-41ef-ac91-358418290a1e&threadId=19_meeting_ZDE4YWYxNmEtZTFlMC00NmQ0LThiNzItZjhmNmZkZGQ3OTk2@thread.v2&messageId=0&language=en-GB
-
Fabrizio Leisen