# How The Guardian is using spaCy and Prodigy to identify quotes in text **URL:** \ **Category:** Uncategorized\ **Tags:** project\ **Created:** [November 26, 2021, 10:59am UTC](https://support.prodi.gy/t/how-the-guardian-is-using-spacy-and-prodigy-to-identify-quotes-in-text/5010 "2021-11-26T10:59:50Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\ **Post date:** [November 26, 2021, 10:59am UTC](https://support.prodi.gy/t/how-the-guardian-is-using-spacy-and-prodigy-to-identify-quotes-in-text/5010/1 "2021-11-26T10:59:50Z")
A great article on how The Guardian is using spaCy and Prodigy to build a model to indentify quotes in new articles ✨Highlights include: why it's so important to iterate on your data and carefully develop custom annotation schemes to deal with ambiguity in language, plus a very pretty custom UI theme for Prodigy! > **[Talking sense: using machine learning to understand quotes](https://www.theguardian.com/info/2021/nov/25/talking-sense-using-machine-learning-to-understand-quotes)** > > The Guardian’s data scientists have been working with other newsrooms on a global project to think about AI and journalism. Here they explain how they have been teaching a machine to understand what a quote is > The main challenge in building the training dataset was navigating the ambiguity of different journalistic styles. For several days, we discussed dozens of cases where it was difficult to make the right choice. > > How should we treat song lyrics or poems? What about messages on placards? What if someone quotes their thoughts, something that has not been said aloud? > > The first batch of our annotations turned out to be quite noisy and inconsistent but we were getting better and better with each iteration. > > Collectively we experienced the same teaching process we were putting our model through. The more examples we looked at, the better we became at recognising different cases. Yet the question remained – if it is difficult for a human to make these decisions, can we teach a machine to cope with this task? ---
**Author:** ![lievcin](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/lievcin/32/2616_2.png) [@lievcin](https://support.prodi.gy/u/lievcin)\ **Post date:** [November 26, 2021, 1:42pm UTC](https://support.prodi.gy/t/how-the-guardian-is-using-spacy-and-prodigy-to-identify-quotes-in-text/5010/2 "2021-11-26T13:42:33Z")
Love that they also customised the UI to the brand 😄 ---
**Author:** ![dandrade](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/dandrade/32/2626_2.png) [@dandrade](https://support.prodi.gy/u/dandrade)\ **Post date:** [December 2, 2021, 2:12pm UTC](https://support.prodi.gy/t/how-the-guardian-is-using-spacy-and-prodigy-to-identify-quotes-in-text/5010/3 "2021-12-02T14:12:01Z")
Excellent. The article has given me a better idea of what to do with the project I am into. Our quotations will be many and perhaps large, inside court decisions: 1. Large text of other court decisions. _Precedents_: They refer to a court decision that is considered as authority for deciding subsequent cases involving identical or similar facts. 2. Short text of doctrine from authors. 3. Short text of articles in any particular law. We are building an AI Legal Assistant on Constitutional Law and decided to combine OpenAI GPT3 and Prodigy. ---
**Author:** ![pkras](https://avatars.discourse-cdn.com/v4/letter/p/8dc957/32.png) [@pkras](https://support.prodi.gy/u/pkras)\ **Post date:** [December 22, 2021, 2:04pm UTC](https://support.prodi.gy/t/how-the-guardian-is-using-spacy-and-prodigy-to-identify-quotes-in-text/5010/4 "2021-12-22T14:04:52Z")
Awesome! Congratulations on the team for your excellent tools (both spaCy and Prodigy), glad to see them get the attention they deserve! If you have any other similar articles or mentions of Prodigy in the industry, please share them as well. Keep up the great work! Cheers