# Who said what: using machine learning to correctly attribute quotes

DevFeed: [Who said what: using machine learning to correctly attribute quotes](<https://devfeed.tech/articles/who-said-what-using-machine-learning-to-correctly-attribute-quotes-19964.md>)

Original publisher: [Read original article](<https://www.theguardian.com/info/2023/nov/21/who-said-what-using-machine-learning-to-correctly-attribute-quotes>)

Author: Michel Schammel, Alice Morris, Anna Vissens, Paul Nathan, Alicja Polanska and Tara Tahseen

Published: 2023-11-21T11:11:31Z

Content type: tutorial

Language: en

Sources: [Guardian](<https://devfeed.tech/sources/guardian.md>)

Topics: [Machine Learning & Artificial Intelligence](<https://devfeed.tech/topics/machine-learning-artificial-intelligence.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [data](<https://devfeed.tech/tags/data.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [developer](<https://devfeed.tech/tags/developer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>)

## AI overview

The Guardian's data scientists describe a collaboration with PhD students from University College London to train a machine learning model for attributing quotes to speakers. The article explains how coreference resolution links mentions in text to the entities they refer to.

## Source excerpt

Today's blog does not come to you from any developer in product and engineering but from our talented colleagues in data and insight Here, the Guardian's data scientists share how they have teamed up with PhD students from University College London to train a machine learning model to accurately attribute quotes. Below the two teams explain how they've been teaching a machine to understand "who said what?" Sarah enjoys a nice cup of tea in the morning. She likes it with milk. Extract a series of mentions which relate to real-world entities For each mention, compute a set of features Based on those features, find the most likely antecedent for each mention Continue reading...