Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913858481815552 |
|---|---|
| author | Choe, Jaeyoung Noh, Keonwoong Kim, Nayeon Ahn, Seyun Jung, Woohwan |
| author_facet | Choe, Jaeyoung Noh, Keonwoong Kim, Nayeon Ahn, Seyun Jung, Woohwan |
| contents | Over the past few years, various domain-specific pretrained language models (PLMs) have been proposed and have outperformed general-domain PLMs in specialized areas such as biomedical, scientific, and clinical domains. In addition, financial PLMs have been studied because of the high economic impact of financial data analysis. However, we found that financial PLMs were not pretrained on sufficiently diverse financial data. This lack of diverse training data leads to a subpar generalization performance, resulting in general-purpose PLMs, including BERT, often outperforming financial PLMs on many downstream tasks. To address this issue, we collected a broad range of financial corpus and trained the Financial Language Model (FiLM) on these diverse datasets. Our experimental results confirm that FiLM outperforms not only existing financial PLMs but also general domain PLMs. Furthermore, we provide empirical evidence that this improvement can be achieved even for unseen corpus groups. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_13312 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models Choe, Jaeyoung Noh, Keonwoong Kim, Nayeon Ahn, Seyun Jung, Woohwan Computation and Language Over the past few years, various domain-specific pretrained language models (PLMs) have been proposed and have outperformed general-domain PLMs in specialized areas such as biomedical, scientific, and clinical domains. In addition, financial PLMs have been studied because of the high economic impact of financial data analysis. However, we found that financial PLMs were not pretrained on sufficiently diverse financial data. This lack of diverse training data leads to a subpar generalization performance, resulting in general-purpose PLMs, including BERT, often outperforming financial PLMs on many downstream tasks. To address this issue, we collected a broad range of financial corpus and trained the Financial Language Model (FiLM) on these diverse datasets. Our experimental results confirm that FiLM outperforms not only existing financial PLMs but also general domain PLMs. Furthermore, we provide empirical evidence that this improvement can be achieved even for unseen corpus groups. |
| title | Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2310.13312 |