We introduce a novel re-ranking model that aims to augment the functiona...
This document chronicles this author's attempt to explore how words come...
Vision language tasks, such as answering questions about or generating
c...
Software architectures for conversational robots typically consist of
mu...
The increasing reliability of automatic speech recognition has prolifera...
Using online information discovery as a case study, in this position pap...
We synthesize the reported results and recommendations of recent worksho...
Automated speech and text interfaces are continuing to improve, resultin...
Humans' experience of the world is profoundly multimodal from the beginn...
Past and current research has typically focused on ensuring that search
...
The words-as-classifiers model of grounded lexical semantics learns a
se...
As spoken dialogue systems and chatbots are gaining more widespread adop...
Essential to meaningful interaction is grounding at the symbolic,
conver...
A common use of language is to refer to visually present objects. Modell...