Review2topic: Building Topics Detection Model to Leverage Reviews Data in Booking.com

Опубликовано: 04 Ноябрь 2022
на канале: John Snow Labs
272
7

Install NLP Libraries https://www.johnsnowlabs.com/install/

Register for Healthcare NLP Summit 2023: https://www.nlpsummit.org/#register

Watch all NLP Summit 2022 sessions: https://www.nlpsummit.org/nlp-summit-...

Presented by Moran Beladev, Machine Learning Manager at Booking.com

Having billions of customers reviews, we would like to better understand them and leverage this data for different use cases. For example, finding popular activities per destination, detecting popular facilities per property, allowing the users to filter reviews by specific topics, and detecting violence in reviews.
In this talk, we will present how we build a multilingual multi-label topic classification model that supports zero-shot, to match reviews to unseen users' search topics.
We will show how fine-tuning BERT-like models on the tourism domain with a small dataset, can outperform other pre-trained models.


Connect with us:
Our website: https://www.johnsnowlabs.com/
LinkedIn:   / johnsnowlabs  
Facebook:   / johnsnowlabsinc  
Twitter:   / johnsnowlabs  


Смотрите видео Review2topic: Building Topics Detection Model to Leverage Reviews Data in Booking.com онлайн без регистрации, длительностью часов минут секунд в хорошем качестве. Это видео добавил пользователь John Snow Labs 04 Ноябрь 2022, не забудьте поделиться им ссылкой с друзьями и знакомыми, на нашем сайте его посмотрели 272 раз и оно понравилось 7 людям.