New breed of NLP model learns finance better, study finds
Models trained by looking at sentences beat conventional approaches that contextualize words.

A new class of natural language processing (NLP) models trained to catch the drift of sentences, rather than the meaning of single words, may beat the models many investors are currently using to analyze text data.
Academics found in a recent study that a sentence-based NLP model outstripped standard models, including those trained specifically to understand financial terms.
The exercise is a first test, the researchers say, with more work to be done. But the findings suggest quants might wish
Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.
To access these options, along with all other subscription benefits, please contact info@waterstechnology.com or view our subscription options here: https://subscriptions.waterstechnology.com/subscribe
You are currently unable to print this content. Please contact info@waterstechnology.com to find out more.
You are currently unable to copy this content. Please contact info@waterstechnology.com to find out more.
Copyright Infopro Digital Limited. All rights reserved.
As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.
If you would like to purchase additional rights please email info@waterstechnology.com
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.
If you would like to purchase additional rights please email info@waterstechnology.com
More on Emerging Technologies
‘AI for everyone, everywhere, with everything’
Waters Wrap: Anthony looks at some interesting projects involving machine learning, generative AI, and agentic AI from the last year.
Waters Wavelength Ep. 327: Standard Chartered’s Mo Rahim
He joins the podcast to discuss data and AI governance and guardrails for AI.
Paxos files to become SEC-registered clearing agency
The application comes after the blockchain infrastructure company completed a pilot in 2021 to test its settlement service.
Generative AI brings testing times for modelers
Flagstar’s lead model validator offers some tips for safely integrating LLMs into risk models.
Genesis CEO steps down, Wells Fargo deploys agents, DTCC sells Report Hub, and more
MarketAxess has enhanced its dealer-initiated protocols, EquiLend launches a market intelligence tool powered by AI, and the summer heat fuels fury over market data prices in this week’s news roundup.
PE money tips the ‘scale’ for growing vendors
The IMD Wrap: For many businesses, being able to take the next step toward success involves the ability to scale. Max looks at two recent fundraising deals that speak volumes about where the industry is headed.
Waters Wavelength Ep. 326: Connectifi’s Nick Kolba
He joins the podcast to discuss the model context protocol, LLMs and agentic AI.
Euroclear readies upgrade to settlement efficiency platform
Euroclear, Taskize, and Meritsoft are working together to deliver real-time insights and resolution capabilities to users settling with any of Euroclear’s CSDs.