Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.10394 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909493790507008 |
|---|---|
| author | Sharma, Abhishek |
| author_facet | Sharma, Abhishek |
| contents | Recent progress in Learning by Reading and Machine Reading systems has significantly increased the capacity of knowledge-based systems to learn new facts. In this work, we discuss the problem of selecting a set of learning requests for these knowledge-based systems which would lead to maximum Q/A performance. To understand the dynamics of this problem, we simulate the properties of a learning strategy, which sends learning requests to an external knowledge source. We show that choosing an optimal set of facts for these learning systems is similar to a coordination game, and use reinforcement learning to solve this problem. Experiments show that such an approach can significantly improve Q/A performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Coordination-based Approach for Focused Learning in Knowledge-Based Systems Sharma, Abhishek Artificial Intelligence Computation and Language Recent progress in Learning by Reading and Machine Reading systems has significantly increased the capacity of knowledge-based systems to learn new facts. In this work, we discuss the problem of selecting a set of learning requests for these knowledge-based systems which would lead to maximum Q/A performance. To understand the dynamics of this problem, we simulate the properties of a learning strategy, which sends learning requests to an external knowledge source. We show that choosing an optimal set of facts for these learning systems is similar to a coordination game, and use reinforcement learning to solve this problem. Experiments show that such an approach can significantly improve Q/A performance. |
| title | A Coordination-based Approach for Focused Learning in Knowledge-Based Systems |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2502.10394 |