A Cognitive Neural Architecture Able to Learn and Communicate through Natural Language
- Submitting institution
-
Manchester Metropolitan University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2356
- Type
- D - Journal article
- DOI
-
10.1371/journal.pone.0140866
- Title of journal
- PLOS ONE
- Article number
- e0140866
- First page
- -
- Volume
- 10
- Issue
- 11
- ISSN
- 1932-6203
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2015
- URL
-
https://e-space.mmu.ac.uk/622797/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
A - Data Science
- Citation count
- 13
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work presents a cognitive system, entirely based on a large-scale neural architecture, which was developed to shed light on the procedural knowledge involved in language elaboration. Findings around the potential of AI to develop language skills led to widespread public and scientific interest picked up in news articles (The Times, Daily Mail), international blogs (World Economic Forum) and lots of further attention and discussion on social media platforms such as twitter. Altmetrics ranks the attention received by the paper amongst the top 5% of articles of all time. The paper is complemented by a publicly accessible dataset on GittHub.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -