Lexically constrained decoding for sequence generation using grid beam search

C Hokamp, Q Liu - arXiv preprint arXiv:1704.07138, 2017 - arxiv.org
We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the
inclusion of pre-specified lexical constraints. The algorithm can be used with any model that …

Computer-Assisted Language Comparison: State of the ArtW

MS Wu, NE Schweikhard, T Bodt… - Journal of Open …, 2020 - eprints.soas.ac.uk
Historical language comparison opens windows onto a human past, long before the
availability of written records. Since traditional language comparison within the framework of …

[HTML][HTML] Is there a role for statistics in artificial intelligence?

S Friedrich, G Antes, S Behr, H Binder… - Advances in Data …, 2022 - Springer
The research on and application of artificial intelligence (AI) has triggered a comprehensive
scientific, economic, social and political discussion. Here we argue that statistics, as an …

[PDF][PDF] Interactive assistance to human translators using statistical machine translation methods

P Koehn, B Haddow - … of Machine Translation Summit XII: Papers, 2009 - aclanthology.org
We investigate novel types of assistance for human translators, based on statistical machine
translation methods. We developed Caitra, a tool that makes suggestions for sentence …

Mapping the design space of human-ai interaction in text summarization

R Cheng, A Smith-Renner, K Zhang… - arXiv preprint arXiv …, 2022 - arxiv.org
Automatic text summarization systems commonly involve humans for preparing data or
evaluating model performance, yet, there lacks a systematic understanding of humans' roles …

EDITOR: An edit-based transformer with repositioning for neural machine translation with soft lexical constraints

W Xu, M Carpuat - Transactions of the Association for Computational …, 2021 - direct.mit.edu
We introduce an Edi t-Based T ransf O rmer with R epositioning (EDITOR), which makes
sequence generation flexible by seamlessly allowing users to specify preferences in output …

Gradient-guided unsupervised lexically constrained text generation

L Sha - Proceedings of the 2020 Conference on Empirical …, 2020 - aclanthology.org
Lexically constrained generation requires the target sentence to satisfy some lexical
constraints, such as containing some specific words or being the paraphrase to a given …

Interactive neural machine translation

Á Peris, M Domingo, F Casacuberta - Computer Speech & Language, 2017 - Elsevier
Despite the promising results achieved in last years by statistical machine translation, and
more precisely, by the neural machine translation systems, this technology is still not error …

[HTML][HTML] Process mining for individualized behavior modeling using wireless tracking in nursing homes

C Fernández-Llatas, JM Benedi, JM García-Gómez… - Sensors, 2013 - mdpi.com
The analysis of human behavior patterns is increasingly used for several research fields.
The individualized modeling of behavior using classical techniques requires too much time …

A process study of computer-aided translation

P Koehn - Machine Translation, 2009 - Springer
We investigate novel types of assistance for human translators, based on statistical machine
translation methods. We developed the computer-aided tool Caitra that makes suggestions …