Abstract
We present a transfer learning approach for Title Detection in FinToC 2020 challenge. Our proposed approach relies on the premise that the geometric layout and character features of the titles and non-titles can be learnt separately from a large corpus, and their learning can then be transferred to a domain-specific dataset. On a domain-specific dataset, we train a Deep Neural Net on the text of the document along with a pre-trained model for geometric and character features. We achieved an F-Score of 83.25 on the test set and secured top rank in the title detection task in FinToC 2020.- Anthology ID:
- 2020.fnp-1.26
- Volume:
- Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Venue:
- FNP
- SIG:
- Publisher:
- COLING
- Note:
- Pages:
- 153–157
- Language:
- URL:
- https://aclanthology.org/2020.fnp-1.26
- DOI:
- Cite (ACL):
- Dhruv Premi, Amogh Badugu, and Himanshu Sharad Bhatt. 2020. AMEX-AI-LABS: Investigating Transfer Learning for Title Detection in Table of Contents Generation. In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, pages 153–157, Barcelona, Spain (Online). COLING.
- Cite (Informal):
- AMEX-AI-LABS: Investigating Transfer Learning for Title Detection in Table of Contents Generation (Premi et al., FNP 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.fnp-1.26.pdf