Zhiyu Chen, William Wang, Shiyang Li, Sameena Shah, Zhiqiang Ma, Charese Smiley
We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| czyssrs/convfinqa | canonical | 7 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| cleanhtml | Ran | czyssrs/convfinqa/code/utils/general_utils.py code served (permissive licence) · get_code("c7368d407afb9277") |
| format_time | Ran | czyssrs/convfinqa/code/finqanet_generator/utils.py code served (permissive licence) · get_code("8d7ec010c29e813b") |
| prog_token_to_indices | Ran | czyssrs/convfinqa/code/finqanet_generator/finqa_utils.py code served (permissive licence) · get_code("21ff8e9f6a35119e") |
| read_txt | Ran | czyssrs/convfinqa/code/finqanet_generator/utils.py code served (permissive licence) · get_code("5312b6b693f09d8e") |
| remove_space | Ran | czyssrs/convfinqa/code/utils/general_utils.py code served (permissive licence) · get_code("edc24c5af3e1a7cd") |
| str_to_num | Ran | czyssrs/convfinqa/code/finqanet_generator/finqa_utils.py code served (permissive licence) · get_code("227ac417efac55e8") |
| table_row_to_text | Ran | czyssrs/convfinqa/code/utils/general_utils.py code served (permissive licence) · get_code("3c93e9aa942bd60c") |
| indices_to_prog | Not yet run | czyssrs/convfinqa/code/finqanet_generator/finqa_utils.py code served (permissive licence) · get_code("6b93716e4bdcdfde") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
With the recent advance in large pre-trained language models, researchers have achieved record performances in NLP tasks that mostly focus on language pattern matching. The community is experiencing the shift of the challenge from how to model language to the imitation of complex reasoning abilities like human beings. In this work, we investigate the application domain of finance that involves realworld, complex numerical reasoning. We propose a new large-scale dataset, CONVFINQA, aiming to study the chain of numerical reasoning in conversational question answering. Our dataset poses great challenge in modeling longrange, complex numerical reasoning paths in real-world conversations. We conduct comprehensive experiments and analyses with both the neural symbolic methods and the promptingbased methods, to provide insights into the reasoning mechanisms of these two divisions. We believe our new dataset should serve as a valuable resource to push forward the exploration of real-world, complex reasoning tasks as the next research focus. Our dataset and code is publicly available 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.03849")
get_code_for_paper("2210.03849")
have("2210.03849")
Connect an agent — have() is free.