researcher

Joseph Chee Chang

I am a research scientist at the Allen Institute for AI (Ai2) working on the Asta project. I received my PhD from the Language Technologies Institute and the Human-Computer Interaction Institute at Carnegie Mellon University. My research sits at the intersection of human-computer interaction and AI, with the goal of building systems that help people navigate, understand, and synthesize large amounts of information. I primarily publish in HCI venues (e.g., CHI, UIST) and occationally in NLP conf

12 papers hereh-index 201.3k citations29 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position

first author2
middle author8
last author2

Across the 12 of 12 papers where every author was matched, so the position is known.

fields

affiliations

I am a research scientist at the Allen Institute for AI (Ai2) working on the Asta project. I received my PhD from the Language Technologies Institute and the Human-Computer Interaction Institute at Carnegie Mellon University. My research sits at the intersection of human-computer interaction and AI, with the goal of building systems that help people navigate, understand, and synthesize large amounts of information. I primarily publish in HCI venues (e.g., CHI, UIST) and occationally in NLP conf

Homepage

same name

Joseph Chee Chang — 1 paper

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity

20142023

most citedEvorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time

65 citations · 396 across the 12 of their papers we have counts for

collaborators

Showing 2018Show all

1 paper · 1 filter

cs.HC2018★ 65 cited

Evorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time

Ting-Hao 'Kenneth' Huang, Joseph Chee Chang, Jeffrey P. Bigham

Crowd-powered conversational assistants have been shown to be more robust than automated systems, but do so at the cost of higher response latency and monetary costs. A promising d…