37 Main Conference and 19 Findings Papers Accepted from LTI-Affiliated Authors
by Bryan Burtner | Friday, November 20, 2020

An impressive 46 papers by LTI faculty and students were accepted at the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), including 37 main conference accepted papers and 19 papers accepted to the newly added Findings publication.

Organized by the Association for Computational Linguisitcs, and now in its 25th year, EMNLP is one of the premier conferences worldwide in the fields of Natual Language Processing and Computational Linguistics. This year's conference was... Read More

by LTI Webmaster | Monday, September 21, 2020

Note: The application deadline has passed, thank everyone who has applied for your interest!

The Language Technologies Institute in Carnegie Mellon University is recruiting interns for Summer 2021. The topic of the internship will be “Language Technology For All,” where you will focus on performing research on cutting-edge language systems to make them more accurate, efficient, or inclusive.

Specific topics include:

  • Natural Language Processing (including machine translation, language analysis, question answering, etc.)
  • Vision... Read More
System Developed by LTI Researchers Uses Social Media Posts to Assess Building Damage
by Byron Spice | Friday, September 4, 2020

It wasn't long after Hurricane Laura hit the Gulf Coast Thursday that people began flying drones to record the damage and posting videos on social media. Those videos are a precious resource, say researchers at Carnegie Mellon University, who are working on ways to use them for rapid damage assessment.

By using artificial intelligence, the researchers are developing a system that can automatically identify buildings and make an initial determination of whether they are damaged and how serious that damage might be.

"Current damage assessments are mostly based on individuals... Read More

LTI and CMU researchers work to automatically make requests more polite
by Byron Spice | Tuesday, July 7, 2020

In a tense time when a pandemic rages, politicians wrangle for votes and protesters demand racial justice, a little politeness and courtesy go a long way. Now researchers at Carnegie Mellon University have developed an automated method for making communications more polite.

Specifically, the method takes nonpolite directives or requests — those that use either impolite or neutral language — and restructures them or adds words to make them more well-mannered. "Send me the data," for instance, might become "Could you please send me the data?"

The researchers will present... Read More

Tuesday, June 9, 2020

Dear Members of the LTI Community,

Like many of you, I was horrified by the recent deaths of George Floyd, Breonna Taylor,... Read More

38 Papers from LTI-affiliated Authors Accepted
by Bryan Burtner | Thursday, April 9, 2020

The 2020 Annual Conference of the Association for Computational Linguistics (ACL 2020) features a bevy of accepted papers from LTI faculty and students – 38 in all. In addition to the large contingent of LTI-authored papers, a number of LTI students and faculty members are involved in workshops affiliated with the ACL conference, either as members of organizing committees, or as invited speakers.

The ACL conference, now in its 58th year, bills itself as "the premier conference of the field of computational linguistics, covering... Read More

Pioneering Professor Left Indelible Mark on the World of Computer Science
by Byron Spice | Friday, February 28, 2020

Jaime Carbonell foresaw a world where people could freely communicate with each other, no matter what language they spoke. He knew that making this dream a reality would require automation, so he spent his career building machines that could understand human language.

He knew full well that earlier attempts at machine translation had largely come to naught. Nevertheless, as a young computer science professor at Carnegie Mellon University in 1985, Carbonell persuaded his superiors to let him start a Center for Machine Translation. For the next 35 years... Read More

Hate Speech Countered by Detecting, Highlighting "Help Speech"
by Byron Spice | Wednesday, January 15, 2020

Complete the following sentence: Rohingya refugees should go to­­­ —

A. Pakistan.
B. Bangladesh.
C. Hell.

These aren't good choices, but all are sentiments that have been expressed repeatedly on social media. The Rohingyas, who began fleeing Myanamar in 2017 to avoid ethnic cleansing, are ill-equipped to defend themselves from these online attacks, but innovations from Carnegie Mellon University's ... Read More

LTI computer model aims to turn film scripts into animations
by Byron Spice | Tuesday, September 10, 2019

Researchers at Carnegie Mellon University have developed a computer model that can translate text describing physical movements directly into simple computer-generated animations, a first step toward someday generating movies directly from scripts.

Scientists have made tremendous leaps in getting computers to understand natural language, as well as in generating a series of physical poses to create realistic animations. These capabilities might as well exist in separate worlds, however, because the link between natural language and physical poses has... Read More

LTI Team Helps Computers Concoct Interesting Endings
by Byron Spice | Thursday, August 1, 2019

Nothing disappoints quite like a good story with a lousy finish. So researchers at Carnegie Mellon University who work in the young field of automated storytelling don't think they're getting ahead of themselves by devising better endings.

The problem is that most algorithms for generating... Read More