New York: Researchers at Massachusetts Institute of Technology have created a system that could be used to automatically update factual inconsistencies in Wikipedia articles, reducing time and effort spent by human editors who now do the task manually.
Wikipedia comprises millions of articles that are in constant need of edits to reflect new information.
That can involve article expansions, major rewrites, or more routine modifications such as updating numbers, dates, names, and locations. Currently, humans across the globe volunteer their time to make these edits.
In a paper presented at the AAAI Conference on Artificial Intelligence in New York, the researchers described a text-generating system that pinpoints and replaces specific information in relevant Wikipedia sentences, while keeping the language similar to how humans write and edit.
The idea is that humans would type into an interface an unstructured sentence with updated information, without needing to worry about style or grammar. The system would then search Wikipedia, locate the appropriate page and outdated sentence, and rewrite it in a humanlike fashion.
In the future, the researchers said, there's potential to build a fully automated system that identifies and uses the latest information from around the web to produce rewritten sentences in corresponding Wikipedia articles that reflect updated information.
"There are so many updates constantly needed to Wikipedia articles. It would be beneficial to automatically modify exact portions of the articles, with little to no human intervention," said Darsh Shah, a PhD student in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and one of the lead authors.
"Instead of hundreds of people working on modifying each Wikipedia article, then you'll only need a few, because the model is helping or doing it automatically. That offers dramatic improvements in efficiency," Shah said.
Many other bots exist that make automatic Wikipedia edits. Typically, those work on mitigating vandalism or dropping some narrowly defined information into predefined templates, Shah said.
The researchers' model, he said, solves a harder artificial intelligence problem: Given a new piece of unstructured information, the model automatically modifies the sentence in a humanlike fashion.
"The other [bot] tasks are more rule-based, while this is a task requiring reasoning over contradictory parts in two sentences and generating a coherent piece of text," he said.
For all the latest News, Opinions and Views, download ummid.com App.
Select Language To Read in Urdu, Hindi, Marathi or Arabic.
2020 Poll Results: New Delhi Assembly to have 05 Muslim MLAs
Also Read
After hours of tense moments, Manish Sisodia pulls off a thriller
Lawyers cite Greta Thunberg, children being called Pakistanis in SC on Shaheen Bagh infant's death
Imran Hussain of AAP is leading by more than 35,000 votes in Ballimaran
Amanatullah Khan now leading in Okhla by over 35,000 votes
BJP deserves to lose Delhi
People from all sections of the society rallied behind AAP: Delhi Exit Polls
Stop NPR until there's clarity on NRC: Ex-IAS officer to PM Modi
"Till Now...": Modi govt issues clarification on NRC, NPR in Parliament
AAP to sweep Delhi state elections 2020: Exit Polls
Delhi Polls 2020: What a loss would mean for Kejriwal or Shah
Budget 2020-21: Rs.99.3k cr for Education, Rs.3k cr for Skill Development
Budget 2020: Breaking down the new Income Tax structure
Watch: Amit Shah's speeches that fuelled anti-CAA protests across India
'When your ancesters were licking boots of British': Awhad tears into BJP govt over CAA
Are Adivasis Hindus?
Delhi Police plan to arrest en masse CAA-NRC protesters, put them in 'detention centre' exposed
Shaheen Bagh Response To Goli Maro: Desh ke in Pyaro Par, Phool Barsao Saro Par