Ilias Chalkidis, Manos Fergadiotis, Ion Androutsopoulos, Prodromos Malakasiotis, Lefteris Loukas, Eirini Spyropoulou, George Paliouras
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Publicly traded companies are required to submit periodic reports with eXtensive Business Reporting Language (xbrl) word-level tags. Manually tagging the reports is tedious and costly. We, therefore, introduce xbrl tagging as a new entity extraction task for the financial domain and release finer-139, a dataset of 1.1M sentences with gold xbrl tags. Unlike typical entity extraction datasets, finer-139 uses a much larger label set of 139 entity types. Most annotated tokens are numeric, with the correct tag per token depending mostly on context, rather than the token itself. We show that subword fragmentation of numeric expressions harms bert's performance, allowing word-level bilstms to perform better. To improve bert's performance, we propose two simple and effective solutions that replace numeric expressions with pseudotokens reflecting original token shapes and numeric magnitudes. We also experiment with fin-bert, an existing bert model for the financial domain, and release our own bert (sec-bert), pre-trained on financial filings, which performs best. Through data and error analysis, we finally identify possible limitations to inspire future work on xbrl tagging.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.06482")
get_code_for_paper("2203.06482")
have("2203.06482")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.06482.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.06482)
Connect an agent — have() is free.