Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2307.02615 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913506803056640 |
|---|---|
| author | Bao, Yuwei Lattimer, Barrett Martin Chai, Joyce |
| author_facet | Bao, Yuwei Lattimer, Barrett Martin Chai, Joyce |
| contents | Human language acquisition is an efficient, supervised, and continual process. In this work, we took inspiration from how human babies acquire their first language, and developed a computational process for word acquisition through comparative learning. Motivated by cognitive findings, we generated a small dataset that enables the computation models to compare the similarities and differences of various attributes, learn to filter out and extract the common information for each shared linguistic label. We frame the acquisition of words as not only the information filtration process, but also as representation-symbol mapping. This procedure does not involve a fixed vocabulary size, nor a discriminative objective, and allows the models to continually learn more concepts efficiently. Our results in controlled experiments have shown the potential of this approach for efficient continual learning of grounded words. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_02615 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition Bao, Yuwei Lattimer, Barrett Martin Chai, Joyce Computation and Language Artificial Intelligence Machine Learning Human language acquisition is an efficient, supervised, and continual process. In this work, we took inspiration from how human babies acquire their first language, and developed a computational process for word acquisition through comparative learning. Motivated by cognitive findings, we generated a small dataset that enables the computation models to compare the similarities and differences of various attributes, learn to filter out and extract the common information for each shared linguistic label. We frame the acquisition of words as not only the information filtration process, but also as representation-symbol mapping. This procedure does not involve a fixed vocabulary size, nor a discriminative objective, and allows the models to continually learn more concepts efficiently. Our results in controlled experiments have shown the potential of this approach for efficient continual learning of grounded words. |
| title | Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2307.02615 |