Shafiq Joty, Ahmed Masry, Xuan Do, Long, Jia Qing, Enamul Hoque
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.
Charts are very popular for analyzing data. When exploring charts, people often ask a variety of complex reasoning questions that involve several logical and arithmetic operations. They also commonly refer to visual features of a chart in their questions. However, most existing datasets do not focus on such complex reasoning questions as their questions are template-based and answers come from a fixedvocabulary. In this work, we present a largescale benchmark covering 9.6K human-written questions as well as 23.1K questions generated from human-written chart summaries. To address the unique challenges in our benchmark involving visual and logical reasoning over charts, we present two transformer-based models that combine visual features and the data table of the chart in a unified way to answer questions. While our models achieve the state-of-the-art results on the previous datasets as well as on our benchmark, the evaluation also reveals several challenges in answering complex reasoning questions. Q1: Which year has the most divergent opinions about Brazil's economy? Answer: 2015 Q2: What is the peak value of the orange line? Answer: 87
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.10244")
get_code_for_paper("2203.10244")
have("2203.10244")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.10244.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.10244)
Connect an agent — have() is free.