Sunday, January 23, 2022

Training computers to tease out the subtext behind the text

- Advertisement -
- Advertisement -
- Advertisement -


Credit: Pixabay/CC0 Public Domain

It is tough sufficient for people to interpret the deeper that means and context of social media and information articles. Asking computers to do it’s a practically inconceivable activity. Even C-3PO, fluent in over 6 million types of communication, misses the subtext a lot of the time.

Natural processing, the subfield of connecting computers with languages, makes use of statistical strategies to analyze language, usually with out incorporating the real-world context wanted for understanding the shifts and currents of human society. To do this, you’ve got to translate on-line communication, and the context from which it emerges, into one thing the computers can parse and cause over.

Dan Goldwasser, affiliate professor of laptop science at Purdue University, and different members of his group attempt to handle that by creating new methods to mannequin human language and permit computers to higher perceive us.

“The motivation of our work is to get a better understanding of public , how different issues are discussed, the arguments made and the perspectives underlying these arguments,” Goldwasser stated. “We would like to represent the points of view expressed by the thousands, or even more, of people describing their experiences online. Understanding the language used to discuss issues can help shed light on the different considerations behind decision-making processes, including both individual health and well-being choices and broader policy decisions.”

Goldwasser emphasizes that a part of the problem is that a lot of on-line communication depends on readers already figuring out the context—whether or not it is shorthand on Twitter or the foundation of understanding a meme. To analyze the communication, the context is an important a part of the message.

“In many of the scenarios we study, progress relies on finding new ways to conceptualize language understanding, by grounding it in a real-world context,” he stated. “Operationalizing it requires developing new technical solutions.”

Goldwasser and his college students use methods distilled from the mixed knowledge of science, synthetic intelligence and computational social science.

Goldwasser’s lab research the language used on social media, conventional media tales and in legislative texts to perceive the and assumptions of the audio system and writers. In a world the place the written phrase is flourishing and each particular person with an web connection can act as a journalist, having the ability to examine and analyze that writing in an unbiased method is essential to human understanding of our personal society.


Siri, what’s AI good for? Expert explains why that could be a tough query


More info:
Understanding Politics through Contextualized Discourse Processing, by Rajkumar Pujari, Dan Goldwasser. Presented at 2021 convention on Empirical Methods in Natural Language Processing. More info is obtainable at aclanthology.org/2021.emnlp-main.102.pdf

Provided by
Purdue University


Citation:
Training computers to tease out the subtext behind the text (2021, November 30)
retrieved 30 November 2021
from https://techxplore.com/news/2021-11-subtext-text.html

This doc is topic to copyright. Apart from any honest dealing for the objective of personal examine or analysis, no
half could also be reproduced with out the written permission. The content material is offered for info functions solely.





Source hyperlink

- Advertisement -

More from the blog

Lawmakers approve Big Tech antitrust overhaul, but with strings attached

Congress is one step nearer to actualizing transformative antitrust reform for the tech {industry} after sending their most viable invoice to...