Posts tagged with 'nlp'

Bei Yu Analyzes Exaggerated Claims in Science Communications

Feb. 12, 2018

Bei Yu

By Hana Maeda

In the information age of rapid news sharing, iSchool professor Bei Yu has started a project about misinformation to better understand scientific research. Yu, whose research area is in applied Natural Language Processing (NLP), is taking an NLP approach to analyze exaggerated claims in science communications. Specifically, Yu and her team is building a computational model on the language of certainty, gathering and comparing science claims from prior research. Their findings will help the public understand how people describe similar topics in different ways. For instance, how news stories and social media communication might be different from what scientists are saying. “I think [our findings] can be training materials for science education, so the public can get more familiar with scientists’ language as a primary source,” Yu says.

Ultimately, her goal is to monitor the quality of science communications in society with this automated tool. Yu feels that original findings from scientists aren’t directly presented to the public, whether the findings are hard to understand or difficult to locate. Now that anyone can report science claims online, she finds that there’s more public information. For Yu, the challenge is to develop better methods of accessing ...


Read More

Deep Learning Talk by Dr. Nancy McCracken

Dec. 17, 2016

The Center for Computational and Data Sciences in the ISchool hosted the following talk:

Title:  Deep Learning for NLP
Speaker:  Dr. Nancy McCracken
Date:  Wednesday, December 14th
Time:  3:00 PM - 4:00 PM 
Location:  Katzer Room (Hinds Hall)
Recorded presentation:   Click here
Presentation slides:  Click here

Description:  In this talk, I introduce Deep Learning as a technique in machine learning that automatically learns classification features.  Deep learning tasks will be surveyed, including those for NLP.  The main focus of the talk will be on the NLP task of learning dense word similarity vectors, such as those popularized by the word2vec software.  We will show examples with both word2vec (the gensim implementation) and Deep Tensor software for this task in python.

Bio: Dr. McCracken is a Research Associate Professor in the iSchool.  Her general research interests are in applying the principles and tools of computational linguistics to making information accessible and understandable for people.  Recent research projects include an NSF funded project for using natural language processing and machine learning to assist social scientists in content analysis of text, an NSF funded project for building a qualitative data repository and working with the campaign research project group in using social ...


Read More

Daniel Acuna: First Year iSchool Assistant Professor and CCDS Affiliate

Sept. 17, 2016

Daniel Acuna.png

By Jerry Robinson

As one of the iSchool's newest data science hires, Daniel Acuna has an affiliation with the Center for Computational and Data Science (CCDS). Acuna is an Assistant Professor at the Syracuse University School of Information Studies.  He earned his Ph.D. in Computer Science from the University of Minnesota, Twin Cities, and completed a postdoc at the Rehabilitation Institute of Chicago and Northwestern University before joining the iSchool this fall.

Acuna's work crosses multiple disciplines including cognitive science, computer science, machine learning, and neuroscience. Currently, he most identifies with the relatively new but growing field of Science of Science.

Acuna research and tools help scientists and funding agencies to make high-quality decisions around hiring, promotion, literature search, and expertise matching.  He believes his work is possible because of data science:  "Data science is a fundamental area that allows me to enter a number of fields and use data to answer critical questions in those fields."

Acuna regularly relies on his background knowledge to design useful computational tools that help scientists and funders make sense of data and answer important questions in their specific domain.  For instance, cognitive science helps him to understand how uncertainty factors ...


Read More

Yatish Hedge: CCDS Researcher Discusses Illuminating 2016 and other Center Projects

June 6, 2016

Yatish Hegde

Hedge is a research staff member at the Center for Computational and Data Science (CCDS). He reflects on how his education and experience as a software engineer at Alcatel Lucent have given him the chance to better understand, engage and analyze different datasets and projects.

By Amanda Quick

Yatish Hedge is no stranger to working with large datasets. Since his first day on the job four years ago, Hegde has had the opportunity to work on various data-related projects while engaging with faculty from both the NLP and data science departments in the iSchool.

“One of the main opportunities is working with data,” said Hegde of his experience so far at the CCDS. “Students learn how to correct, analyze and collect data. The data is already here and they can work with all real datasets.”

Hegde graduated from the iSchool at Syracuse University with a master’s degree in Information Management in 2010. He also holds an undergraduate degree in Computer Science from R.V College of Engineering, according to his bio. Hegde’s education and work experience as a software engineer have prepared him to become a key research member of the CCDS.

“My role in the Center is ...


Read More