
Kenneth Church
hate speech detection
adversarial training
multilingual
domain adaptation
generalizability
language and vision
multi-agent
diversity
art
early exits
emotions
large language model
multicultural
debate simulation
3
presentations
11
number of views
SHORT BIO
Kenneth “Ken” Ward Church has worked on many topics in computational linguistics including: web search, language modeling, text analysis, spelling correction, word-sense disambiguation, terminology, translation, lexicography, compression, speech (recognition, synthesis & diarization), and OCR. He also worked on applications that go beyond computational linguistics such as revenue assurance and virtual integration (using screen scraping and web crawling to integrate legacy systems in billing, customer care, provisioning, maintenance, etc.). Mr. Church earned his undergraduate and graduate degrees from MIT, and has worked at AT&T, Microsoft, Hopkins and IBM. He was the president of ACL in 2012, and SIGDAT (the group that organizes EMNLP) from 1993 until 2011. He became an AT&T Fellow in 2001 and ACL Fellow in 2015. Mr. Church enjoys working with large corpora, and in the late 1980s started with newswire (1 million words per week of Associated Press). By the mid-1990s, he was working with larger datasets such as telephone call logs (1-10 billion records per month). At Microsoft, Mr. Church worked with search logs, and more recently at IBM, he had been working with logs from Siri-like speech services. Google Scholar:https://scholar.google.com/citations?user=E6aqGvYAAAAJ&hl=en
Presentations

ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture
Youssef Mohamed and 6 other authors

A Gentle Introduction to Deep Nets and Opportunities for the Future: Simple Uses of Deep Nets
Kenneth Church and 5 other authors

Data Collection vs. Knowledge Graph Completion: What is Needed to Improve Coverage?
Kenneth Church and 1 other author