Abstract | ||
---|---|---|
Recent advances in spoken language technologies and the introduction of many customer facing products, have given rise to a wide customer reliance on smart personal assistants for many of their daily tasks. In this paper, we present a system to reduce users’ cognitive load by extending personal assistants with long-term personal memory where users can store and retrieve by voice, arbitrary pieces of information. The problem is framed as a neural retrieval based question answering system where answers are selected from previously stored user memories. We propose to directly optimize the end-to-end retrieval performance, measured by the F1-score, using reinforcement learning, leading to better performance on our experimental test set(s). |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/slt.2018.8639562 | 2018 IEEE Spoken Language Technology Workshop (SLT) |
Keywords | DocType | Volume |
Optimization,Task analysis,Training,Knowledge discovery,Measurement,Speech recognition,Computer architecture | Conference | abs/1810.00679 |
ISSN | Citations | PageRank |
2639-5479 | 0 | 0.34 |
References | Authors | |
17 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rasool Fakoor | 1 | 9 | 3.79 |
Amanjit Kainth | 2 | 0 | 0.34 |
Siamak Shakeri | 3 | 0 | 0.34 |
Christopher Winestock | 4 | 0 | 0.34 |
Abdel-rahman Mohamed | 5 | 3772 | 266.13 |
Ruhi Sarikaya | 6 | 698 | 64.49 |