Incremental dialogue model components produce a sequence of output prefixes based on incoming input. Mistakes can occur due to local ambiguities or to wrong hypotheses, making the ability to revise past outputs a desirable property that can be governed by a policy. In this work, we formalise and characterise edits and revisions in incremental sequence labelling and propose metrics to evaluate revision policies. We then apply our methodology to profile the incremental behaviour of three Transformer-based encoders in various tasks, paving the road for better revision policies.Comment: Accepted at SIGdial 202
Revision is an essential part of the human writing process. It tends to be strategic, adaptive, and,...
Incrementality is a fundamental feature of language in real world use. To this point, however, the v...
Eshghi is supported by the EPSRC BABBLE project (grant number EP/M01553X/1) and Hough by the DUEL pr...
Incremental dialogue model components produce a sequence of output prefixes based on incoming input....
Language production is a complex task, and despite limited resources, humans can speak fluently at a...
Incremental spoken dialogue systems, which process user input as it unfolds, pose additional enginee...
Writing is, by nature, a strategic, adaptive, and more importantly, an iterative process. A crucial ...
This response discusses the experiment reported in Krahmer et al.’s Letter to the Editor of Cognitiv...
Baumann T, Atterer M, Schlangen D. Assessing and Improving the Performance of Speech Recognition for...
Large sequence to sequence models for tasks such as Neural Machine Translation (NMT) are usually tra...
In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may con...
Buß O, Schlangen D. DIUM – An Incremental Dialogue Manager That Can Produce Self-Corrections. In: P...
The study of revision has been a topic of interest in writing research over the past decades. Numero...
A brief introduction to the topics discussed in the special issue, and to the individual pape...
Heintze S, Baumann T, Schlangen D. Comparing Local and Sequential Models for Statistical Incremental...
Revision is an essential part of the human writing process. It tends to be strategic, adaptive, and,...
Incrementality is a fundamental feature of language in real world use. To this point, however, the v...
Eshghi is supported by the EPSRC BABBLE project (grant number EP/M01553X/1) and Hough by the DUEL pr...
Incremental dialogue model components produce a sequence of output prefixes based on incoming input....
Language production is a complex task, and despite limited resources, humans can speak fluently at a...
Incremental spoken dialogue systems, which process user input as it unfolds, pose additional enginee...
Writing is, by nature, a strategic, adaptive, and more importantly, an iterative process. A crucial ...
This response discusses the experiment reported in Krahmer et al.’s Letter to the Editor of Cognitiv...
Baumann T, Atterer M, Schlangen D. Assessing and Improving the Performance of Speech Recognition for...
Large sequence to sequence models for tasks such as Neural Machine Translation (NMT) are usually tra...
In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may con...
Buß O, Schlangen D. DIUM – An Incremental Dialogue Manager That Can Produce Self-Corrections. In: P...
The study of revision has been a topic of interest in writing research over the past decades. Numero...
A brief introduction to the topics discussed in the special issue, and to the individual pape...
Heintze S, Baumann T, Schlangen D. Comparing Local and Sequential Models for Statistical Incremental...
Revision is an essential part of the human writing process. It tends to be strategic, adaptive, and,...
Incrementality is a fundamental feature of language in real world use. To this point, however, the v...
Eshghi is supported by the EPSRC BABBLE project (grant number EP/M01553X/1) and Hough by the DUEL pr...