THE API

The IMAGE2TEXT API provides access to our model initially trained to recognize at least 30 women politicians in our countries. We are building it in a way that allows others to contribute. If a newsroom in another country trains it to recognise politicians (or cultural figures, celebrities, athletes, etc.) they can do so and share that knowledge. The main objective is to have numerous newsrooms from different places sharing and creating knowledge.

DOWNLOAD ON GITHUB

OUR JOURNEY

Local newsrooms may be key to a more diverse AI ecosystem.

In June 2022, we – a team of journalists and technologists from Argentina, Paraguay and The Philippines – decided to collaborate in the JournalismAI Fellowship to develop a product that uses AI to describe images produced at our newsrooms. We seek to process photos, videos and infographics to automatically get tags – such as names of people – in order to categorise, distribute, and archive material more efficiently. Right from the outset, we encountered a challenge and an opportunity: most computer-vision models available in the market are not trained for our specific contexts.

On the one hand, the tools available were not created for the context of journalism. For example, we ran some trials with a video that showed the recently appointed president of Chile in his first official meeting with the president of Argentina. The AI-based tool that we used was somehow successful in describing the video, but the result tags were somewhat incomplete and out of context: “suit” (their outfit), “red carpet” (there was in fact one), “men”, and “first date” (let’s say this algorithm is sort of a romantic, and interpreted the elegance of the situation as a date?).

Although accurate (with the exception of “first date”, ok), this description wasn’t relevant for journalistic purposes. There were other elements in the images that could be more useful: journalists holding their telephones, microphones, and stands, which altogether could have been interpreted by the model as a press conference. If later on, a journalist would type “Gabriel Boric, press conference” in a search engine and get that video as a result, that would indeed be helpful.

On the other hand, the AI-based tools available were not created for the specific context of our countries. When we ran our first trials, none of the presidents and prominent political figures of our countries were recognised (unlike, for example, the president of the United States). The story behind these results is a broader one, about the way AI tools are being built: the datasets used to train the models lack diversity and representation from the Larger World. They are biased toward the regions where the most amount of AI development is being done.

So, even if what got us to collaborate in the first place was to use AI to describe images, we discovered along the way that we had other motivations in common: to contribute to a more diverse AI ecosystem by having more people from diverse regions, genders and cultures building datasets, training models, and developing AI products.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Cras et erat et metus euismod condimentum ut eget risus. Aliquam erat volutpat. Ut blandit vehicula pulvinar. Interdum et malesuada fames ac ante ipsum primis in faucibus. Integer risus ex, commodo at viverra ut, vehicula quis arcu. Donec iaculis, mauris scelerisque imperdiet egestas, risus urna varius ex, sed venenatis magna lorem in felis. Praesent auctor convallis sapien. Donec tempus rutrum nunc vitae sagittis. Suspendisse potenti. Donec porttitor venenatis laoreet. Etiam pharetra diam at elit vehicula, at dignissim arcu maximus. Cras porttitor massa quis sapien varius, in ornare purus convallis. Aenean aliquet eros libero, eu iaculis ipsum blandit ut. Praesent pharetra odio pulvinar aliquam laoreet. Nulla auctor ipsum a tempor consequat. Nam faucibus vestibulum nisl rhoncus condimentum.

Aliquam euismod non quam ut faucibus. Curabitur malesuada, tellus sed mattis porttitor, mi dui pellentesque velit, vel condimentum augue odio ac odio. Curabitur venenatis accumsan nisl vitae placerat. Morbi rhoncus neque vitae leo maximus commodo. Fusce sagittis tortor nec nisl mollis blandit. Aenean condimentum turpis eget erat viverra luctus. Pellentesque lobortis blandit mauris, sed gravida odio fringilla a. Maecenas mattis libero sed iaculis molestie. Aliquam erat volutpat. Cras eros ligula, varius vitae neque eget, pulvinar auctor leo. Fusce dapibus cursus justo vel eleifend. Aliquam mattis, enim porta porta iaculis, turpis libero convallis orci, eu sollicitudin urna nunc eget ex. Integer in mi laoreet, maximus felis vitae, condimentum turpis. Suspendisse eleifend massa vel magna tincidunt, rutrum mattis lectus pretium.

Sed vel velit magna. Maecenas tincidunt urna maximus pretium convallis. Proin tempus, elit eget sodales condimentum, ante metus tempor odio, et egestas sapien turpis et tellus. Quisque convallis rhoncus posuere. Nam nec hendrerit dolor. Quisque mattis vulputate risus eget aliquet. Cras eget ornare velit. Vestibulum rutrum massa vestibulum lorem tristique congue. Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Duis sit amet nibh gravida, hendrerit nisi ac, mollis turpis.

IMAGE2TEXT

STARTER PACK

THE API

The Team

Lucila Pinto

GRUPO OCTUBRE

Nicolas Russo

GRUPO OCTUBRE

Raymund Sarmiento

GMA NEW MEDIA

Jaemark Tordecilla

GMA NETWORK

Sara Campos

EL SURTI

OUR JOURNEY