BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913422592966656 |
|---|---|
| author | Shen, Zhewen Joshi, Aditya Chen, Ruey-Cheng |
| author_facet | Shen, Zhewen Joshi, Aditya Chen, Ruey-Cheng |
| contents | Children from bilingual backgrounds benefit from interactions with parents and teachers to re-acquire their heritage language. In this paper, we investigate how this insight from behavioral study can be incorporated into the learning of small-scale language models. We introduce BAMBINO-LM, a continual pre-training strategy for BabyLM that uses a novel combination of alternation and PPO-based perplexity reward induced from a parent Italian model. Upon evaluation on zero-shot classification tasks for English and Italian, BAMBINO-LM improves the Italian language capability of a BabyLM baseline. Our ablation analysis demonstrates that employing both the alternation strategy and PPO-based modeling is key to this effectiveness gain. We also show that, as a side effect, the proposed method leads to a similar degradation in L1 effectiveness as human children would have had in an equivalent learning scenario. Through its modeling and findings, BAMBINO-LM makes a focused contribution to the pre-training of small-scale language models by first developing a human-inspired strategy for pre-training and then showing that it results in behaviours similar to that of humans. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11418 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM Shen, Zhewen Joshi, Aditya Chen, Ruey-Cheng Computation and Language Children from bilingual backgrounds benefit from interactions with parents and teachers to re-acquire their heritage language. In this paper, we investigate how this insight from behavioral study can be incorporated into the learning of small-scale language models. We introduce BAMBINO-LM, a continual pre-training strategy for BabyLM that uses a novel combination of alternation and PPO-based perplexity reward induced from a parent Italian model. Upon evaluation on zero-shot classification tasks for English and Italian, BAMBINO-LM improves the Italian language capability of a BabyLM baseline. Our ablation analysis demonstrates that employing both the alternation strategy and PPO-based modeling is key to this effectiveness gain. We also show that, as a side effect, the proposed method leads to a similar degradation in L1 effectiveness as human children would have had in an equivalent learning scenario. Through its modeling and findings, BAMBINO-LM makes a focused contribution to the pre-training of small-scale language models by first developing a human-inspired strategy for pre-training and then showing that it results in behaviours similar to that of humans. |
| title | BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.11418 |