Will Culpepper and Thomas A. Bennett and Lixiao Zhu and Rafael Sousa Silva and Ryan Blake Jackson and Tom Williams
Annual Meeting of the Cognitive Science Society
Referring expression understanding and generation are critical for robots to communicate about the world around them. Recently there have been significant advances on the problem of referring expression understanding, also known as reference resolution, with researchers presenting approaches to both incremental reference resolution (i.e., processing referring expressions word by word in real-time as they are spoken) and open-world reference resolution (i.e., resolving references both to known and previously unknown entities). In this work, we combine insights from these approaches to present IPOWER: the first algorithm for performing reference resolution incrementally in open-world environments.