Abstract: We present a multi-way parallel corpus of Math Word Problems (MWPs) in nine languages, including six low-resource languages. To date, this is the largest multilingual MWP dataset available.
A marriage of formal methods and LLMs seeks to harness the strengths of both.
Python 3.8+ llama.cpp (already included in parent directory) Raspberry Pi 4/5 with 4GB RAM (or Mac/Linux for development) ...
The current example is trained on Alice in Wonderland, and ready to go. Use lstm_generate.py to generate runs of 400 words of varying diversities. You can provide new full-text input data in the root ...
Abstract: Math word problems (MWPs) solving has achieved promising results recently. However, most existing methods focus only on learning the mapping function between problem text and the target ...
During my time as a learning support math teacher, I always had a daily word problem on my board for students to work on when they first walked into my classroom. To be completely honest, this ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results