[webMeetup] Abstractive Summarization and Explainability for Legal Documents

Join our 37th NLP Zurich tech shindig 3rd November 2020 online! Nina Hristozova (Thomson Reuters Labs) talks about an application of text summarization to Legal Court Documents and her colleague Nadja Herger (Thomson Reuters Labs) gives us a glimpse into the emerging field of Explainable AI and how it is applied to the summarization use case. We are looking forward to welcoming you!

Agenda

17:55 Join the webinar
18:00 Nina Hristozova & Nadja Herger (Thomson Reuters Labs): DL-Driven Abstractive Summarization and Explainability for Legal Court Documents
18:40 Q&A
19:00 Virtual Hugs and Kisses ⊂(◉‿◉)つ

Talk Summary
We will talk about how we added AI capabilities to an existing product at Thomson Reuters. This product monitors more than 200 courts across the US and sends out alerts to customers based on pre-defined filters. Behind the scenes, the product is supported by a team of editors who monitor and collect new court cases and perform various editorial tasks. One of the most challenging tasks is to write a summary of the key legal issues in a given court case. It therefore helps our customers to understand the essence of a case without having to read the entire complaint, react faster, and work more efficiently.

To speed up the editorial process, an AI-powered summarization model was built to automatically generate a first version of those summaries. We experimented with a summarization model trained on court cases and associated editor-written summaries – nearly 1 million documents that are mostly 5’000 words in length each!

This was not a straightforward task – the court cases consist of complex legal language and the summaries were not extractive. Thankfully, the democratization and advances of Deep Learning (DL) models for sequence generation enabled us to tackle this challenging task and achieve close to human-level performance.

Now, put yourself in the shoes of our editors – you push a button, and you see an auto-generated summary for a given court case. Wouldn’t you want to know how the DL model arrived at it? We learned that having an auto-generated summary already helps our editors a lot in terms of time savings. An explainability layer on top of that helped them become even more efficient and it strengthened their trust in the AI system.

What model did we use to summarize the court documents and how did we add an extra layer of explainability? Tune in on November 3rd to learn more!

About the speakers:

Nina Hristozova
LinkedIn: linkedin.com/in/nina-hristozova-80245baa
Twitter: NHristozova
Nina Hristozova is a Data Scientist at Thomson Reuters Labs. She has a BSc in Computer Science from the University of Glasgow, Scotland. As part of her role at the Labs she has worked on a wide range of projects applying Machine Learning and Deep Learning to a variety of NLP problems. Her current focus is on applied summarization with Transfer Learning. Outside of work she is a Co-organizer of the NLP Zurich Meetup to spread the love and knowledge for NLP and plays & coaches volleyball in Zug.

Nadja Herger
Nadja Herger is a Data Scientist at Thomson Reuters Labs, based in Switzerland. She is primarily focusing on Deep Learning PoCs within the Labs, where she is working on applied NLP projects in the legal and news domains, applying her skills to text classification, metadata extraction, and summarization tasks. Before joining Thomson Reuters, she obtained her Ph.D. in Climate Science from the University of New South Wales, Australia. She has successfully made the transition from working with Spatio-temporal data to working with text-based data on the job. Nadja is passionate about education, which is reflected in her ongoing mentorship of students within Thomson Reuters, as well as South African students from disadvantaged groups who are aspiring to get into Data Science.

NLP Zurich
Meetup.com: https://www.meetup.com/NLP-Zurich/
Linkedin: https://www.linkedin.com/company/nlp-zurich
Twitter: https://twitter.com/nlp_zurich