Natural Language Processing (NLP) applies the power of computing to the complexity and nuance of human language. At 成人快手 R&D, we are exploring how NLP can help us better understand and serve our audiences.
Project from 2011 - present
What we are doing
Our research focuses on a variety of NLP applications, such as semantic search, summarisation and sentiment analysis. We are interested in both established NLP techniques and emerging methods based on Large Language Models (LLMs).
The 成人快手 absorbs and creates large amounts of textual material during its day-to-day operations. To help staff exploit this information 成人快手 R&D has developed several text tools.
|
Tool Name |
Function |
Description |
|---|---|---|
| Starfruit | Tag suggestion | Tag suggestion system based on previous choices by journalists |
| Citron | Quote extraction | Quote extraction and attribution system |
| Vox | Abuse detection | Detects personal abuse and offensive comments |
| Emo | Sentiment analysis | Predicts the emotional impact of news articles |
| Yuzu | Topic segmentation | Segments news bulletins and magazine programmes by topic |
| Primo | Semantic search & analysis | Applies Large Language Models to document collections |
How it works
We use state-of-the-art techniques and apply Large Language Models to news articles, subtitle streams and speech-to-text transcripts.
Outcomes
Project Team
-
Internet Research and Future Services section
The Internet Research and Future Services section is an interdisciplinary team of researchers, technologists, designers, and data scientists who carry out original research to solve problems for the 成人快手. Our work focuses on the intersection of audience needs and public service values, with digital media and machine learning. We develop research insights, prototypes and systems using experimental approaches and emerging technologies.