| 67220 |
Creator |
81226b931d8904b22774bbfe1edd33a0 |
| 67220 |
Creator |
ext-09b16631a28c6d37aa2e69bab0e08779 |
| 67220 |
Creator |
ext-3ddd3529fcf5f9dd300ca010ff553b31 |
| 67220 |
Creator |
ext-9f4a61f6a40813d16c3edbe5176c0ae8 |
| 67220 |
Creator |
ext-b7bf01c67b6e21d4151d453af7f9beaa |
| 67220 |
Date |
2019 |
| 67220 |
Date |
2020-01 |
| 67220 |
Is Part Of |
repository |
| 67220 |
Is Part Of |
p00043702 |
| 67220 |
abstract |
The presence of robots in everyday life is increasing day by day at a growing pace.
Industrial and working environments, health-care assistance in public or domestic
areas can benefit from robots' services to accomplish manifold tasks that are difficult
and annoying for humans. In such scenarios, Natural Language interactions, enabling
collaboration and robot control, are meant to be situated, in the sense that both
the user and the robot access and make reference to the environment. Contextual knowledge
may thus play a key role in solving inherent ambiguities of grounded language as,
for example, the prepositional phrase attachment. <br></br><br></br>In this work,
we present a linguistic pipeline for semantic processing of robotic commands, that
combines discriminative structured learning, distributional semantics and contextual
evidence extracted from the working environment. The final goal is to make the interpretation
process of linguistic exchanges depending on physical, cognitive and language-dependent
aspects. We present, formalize and discuss an adaptive Spoken Language Understanding
chain for robotic commands, that explicitly depends on the operational context during
both the learning and processing stages. The resulting framework allows to model heterogeneous
information concerning the environment (e.g., positional information about the objects
and their properties) and to inject it in the learning process. Empirical results
demonstrate a significant contribution of such additional dimensions, achieving up
to a 25% of relative error reduction with respect to a pipeline that only exploits
linguistic evidence. |
| 67220 |
authorList |
authors |
| 67220 |
status |
peerReviewed |
| 67220 |
uri |
http://data.open.ac.uk/oro/document/987347 |
| 67220 |
uri |
http://data.open.ac.uk/oro/document/987348 |
| 67220 |
uri |
http://data.open.ac.uk/oro/document/987349 |
| 67220 |
uri |
http://data.open.ac.uk/oro/document/987350 |
| 67220 |
uri |
http://data.open.ac.uk/oro/document/987351 |
| 67220 |
uri |
http://data.open.ac.uk/oro/document/987352 |
| 67220 |
uri |
http://data.open.ac.uk/oro/document/987786 |
| 67220 |
volume |
278 |
| 67220 |
type |
AcademicArticle |
| 67220 |
type |
Article |
| 67220 |
label |
Vanzo, Andrea; Croce, Danilo; Bastianelli, Emanuele ; Basili, Roberto and Nardi,
Daniele (2019). Grounded Language Interpretation of Robotic Commands through Structured
Learning. Artificial Intelligence (In press). |
| 67220 |
label |
Vanzo, Andrea; Croce, Danilo; Bastianelli, Emanuele ; Basili, Roberto and Nardi, Daniele
(2020). Grounded Language Interpretation of Robotic Commands through Structured Learning.
Artificial Intelligence, 278, article no. 103181. |
| 67220 |
Title |
Grounded Language Interpretation of Robotic Commands through Structured Learning |
| 67220 |
in dataset |
oro |