Recent conditional language models are able to continue any kind of text...
Incremental dialogue model components produce a sequence of output prefi...
Instruction Clarification Requests are a mechanism to solve communicatio...
NLP tasks are typically defined extensionally through datasets containin...
Recent work has proposed a methodology for the systematic evaluation of
...
The ability to pick up on language signals in an ongoing interaction is
...
Language is by its very nature incremental in how it is produced and
pro...
How does one measure "ability to understand language"? If it is a person...
In visual instruction-following dialogue games, players can engage in re...
Even in our increasingly text-intensive times, the primary site of langu...
The striking recent advances in eliciting seemingly meaningful language
...
Cognitively plausible visual dialogue models should keep a mental scoreb...
This paper presents the slurk software, a lightweight interaction server...
Incremental processing allows interactive systems to respond based on pa...
Coherent discourse is distinguished from a mere collection of utterances...
While humans process language incrementally, the best language encoders
...
A suitable state representation is a fundamental part of the learning pr...
It has become a common pattern in our field: One group introduces a lang...
Fully data driven Chatbots for non-goal oriented dialogues are known to
...
Learned dynamic weighting of the conditioning signal (attention) has bee...
Where early work on dialogue in Computational Linguistics put much empha...
"This paper introduces a new task and a new dataset", "we improve the st...
Building computer systems that can converse about their visual environme...
Zero-shot learning in Language & Vision is the task of correctly labelli...
Propelling, and propelled by, the "deep learning revolution", recent yea...
A common use of language is to refer to visually present objects. Modell...