Oliver Lemon
Biographic Data
| ID | 5121817 |
|---|---|
| NAME | Oliver Lemon |
| GIVEN NAMES | Oliver |
| FAMILY NAME | Lemon |
| SIGNATURE | LEMON O |
| AFFILIATIONS | Heriot-Watt University |
| ORCID | 0000-0001-9497-4743 |
| VERIFIED | Yes |
| TOTAL WORKS | 4 |
| TOTAL CITATIONS | 3 |
| WORKS AS AUTHOR | 4 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2008 |
| LATEST PUBLICATION YEAR | 2017 |
| H-INDEX | 1 |
Grammars as Mechanisms for Interaction
Adaptive Generation in Dialogue Systems Using Dynamic User Modeling
We address the problem of dynamically modeling and adapting to unknown users in resource-scarce domains in the context of interactive spoken dialogue systems. As an example, we show how a system can learn to choose referring expressions to refer to domain entities for users with different levels of domain expertise, and whose domain knowledge is initially unknown to the system. We approach this problem using a three step process: collecting data …
Learning and Evaluation of Dialogue Strategies for New Applications
We present a new data-driven methodology for simulation-based dialogue strategy learning, which allows us to address several problems in the field of automatic optimization of dialogue strategies: learning effective dialogue strategies when no initial data or system exists, and determining a data-driven reward function. In addition, we evaluate the result with real users, and explore how results transfer between simulated and real interactions. W…
Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets
We propose a method for learning dialogue management policies from a fixed data set. The method addresses the challenges posed by Information State Update (ISU)-based dialogue systems, which represent the state of a dialogue as a large set of features, resulting in a very large state space and a huge policy space. To address the problem that any fixed data set will only provide information about small portions of these state and policy spaces, we…
Adaptive Generation in Dialogue Systems Using Dynamic User Modeling
We address the problem of dynamically modeling and adapting to unknown users in resource-scarce domains in the context of interactive spoken dialogue systems. As an example, we show how a system can learn to choose referring expressions to refer to domain entities for users with different levels of domain expertise, and whose domain knowledge is initially unknown to the system. We approach this problem using a three step process: collecting data …
Learning and Evaluation of Dialogue Strategies for New Applications
We present a new data-driven methodology for simulation-based dialogue strategy learning, which allows us to address several problems in the field of automatic optimization of dialogue strategies: learning effective dialogue strategies when no initial data or system exists, and determining a data-driven reward function. In addition, we evaluate the result with real users, and explore how results transfer between simulated and real interactions. W…
Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets
We propose a method for learning dialogue management policies from a fixed data set. The method addresses the challenges posed by Information State Update (ISU)-based dialogue systems, which represent the state of a dialogue as a large set of features, resulting in a very large state space and a huge policy space. To address the problem that any fixed data set will only provide information about small portions of these state and policy spaces, we…
Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets
We propose a method for learning dialogue management policies from a fixed data set. The method addresses the challenges posed by Information State Update (ISU)-based dialogue systems, which represent the state of a dialogue as a large set of features, resulting in a very large state space and a huge policy space. To address the problem that any fixed data set will only provide information about small portions of these state and policy spaces, we…
Learning and Evaluation of Dialogue Strategies for New Applications
We present a new data-driven methodology for simulation-based dialogue strategy learning, which allows us to address several problems in the field of automatic optimization of dialogue strategies: learning effective dialogue strategies when no initial data or system exists, and determining a data-driven reward function. In addition, we evaluate the result with real users, and explore how results transfer between simulated and real interactions. W…
Adaptive Generation in Dialogue Systems Using Dynamic User Modeling
We address the problem of dynamically modeling and adapting to unknown users in resource-scarce domains in the context of interactive spoken dialogue systems. As an example, we show how a system can learn to choose referring expressions to refer to domain entities for users with different levels of domain expertise, and whose domain knowledge is initially unknown to the system. We approach this problem using a three step process: collecting data …
Grammars as Mechanisms for Interaction
Computer Science (4 works) · Artificial Intelligence (3 works) · Machine learning (3 works) · Reinforcement learning (3 works) · Speech and dialogue systems (3 works) · Topic Modeling (3 works) · Function (biology (2 works) · Human–computer interaction (2 works) · Multi-Agent Systems and Negotiation (2 works) · Task (project management (2 works)