Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Daniel Hewlett"'
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. 3:20-24
We introduce Wubble World, a virtual environment for learning situated language. In Wubble World children create avatars, called wubbles, which can interact with other other children's avatars through free-form spontaneous play or structured language
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6f262489bfe495221762505ceafc308
https://doi.org/10.1609/aiide.v3i1.18776
https://doi.org/10.1609/aiide.v3i1.18776
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 32
The machine reading task, where a computer reads a document and answers questions about it, is important in artificial intelligence research. Recently, many models have been proposed to address it. Word-level models, which have words as units of inpu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70d9534d9e289b4631236309d6b345a0
https://doi.org/10.1609/aaai.v32i1.12050
https://doi.org/10.1609/aaai.v32i1.12050
Autor:
Jakob Uszkoreit, Illia Polosukhin, Eunsol Choi, Daniel Hewlett, Jonathan Berant, Alexandre Lacoste
Publikováno v:
ACL (1)
We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models. While most successful approaches for reading comprehension rely on recurrent neur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b92619a56b4951bef7f03bca3f68e43f
https://doi.org/10.18653/v1/p17-1020
https://doi.org/10.18653/v1/p17-1020
Publikováno v:
EMNLP
We introduce a hierarchical architecture for machine reading capable of extracting precise information from long documents. The model divides the document into small, overlapping windows and encodes all windows in parallel with an RNN. It then attend
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::818b7c0f2b5c9cecf910a354e3574874
https://doi.org/10.18653/v1/d17-1214
https://doi.org/10.18653/v1/d17-1214
Autor:
Jay Han, Daniel Hewlett, Andrew Fandrianto, Alexandre Lacoste, Illia Polosukhin, Matthew Kelcey, David Berthelot, Llion Jones
Publikováno v:
ACL (1)
We present WikiReading, a large-scale natural language understanding task and publicly-available dataset with 18 million instances. The task is to predict textual values from the structured knowledge base Wikidata by reading the text of the correspon
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b10bdd165e8961824b845d0d930ac01f
https://doi.org/10.18653/v1/p16-1145
https://doi.org/10.18653/v1/p16-1145
Publikováno v:
ICDL-EPIROB
This paper describes a framework for an agent to learn models of verb-phrase meanings from human teachers and combine these models with environmental dynamics to enact verb commands. The framework extends prior work in apprenticeship learning and lev
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::857dfc3123916a5eb9b2636850169353
https://doi.org/10.1109/devlrn.2011.6037340
https://doi.org/10.1109/devlrn.2011.6037340
Autor:
Daniel Hewlett, Paul R. Cohen
Publikováno v:
Proceedings of the 3d Conference on Artificial General Intelligence (AGI-10).
We argue that the ability to find meaningful chunks in sequential input is a core cognitive ability for artificial general intelligence, and that the Voting Experts algorithm, which searches for an information theoretic signature of chunks, provides
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8f7c8d76b2f145b884b90c229a1f6e76
https://doi.org/10.2991/agi.2010.31
https://doi.org/10.2991/agi.2010.31
Publikováno v:
2007 IEEE 6th International Conference on Development and Learning.
Why do children master language so quickly and thoroughly, whereas gigabytes of text and enormously sophisticated learning algorithms produce at best shallow semantics in machines? Because children have help from competent speakers who relate languag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d24472d4503df7786df77f8d3a531a82
https://doi.org/10.1109/devlrn.2007.4354034
https://doi.org/10.1109/devlrn.2007.4354034