Solving Math Word Problems with Double-Decoder Transformer
This work addresses math word problem-solving, a domain-specific task in natural language processing, with incremental improvements over existing methods.
The paper tackles the problem of generating equations for math word problems by proposing a Transformer-based model with two decoders, achieving better results than RNN models without copy mechanisms and outperforming complex RNN models with copy and align mechanisms.
This paper proposes a Transformer-based model to generate equations for math word problems. It achieves much better results than RNN models when copy and align mechanisms are not used, and can outperform complex copy and align RNN models. We also show that training a Transformer jointly in a generation task with two decoders, left-to-right and right-to-left, is beneficial. Such a Transformer performs better than the one with just one decoder not only because of the ensemble effect, but also because it improves the encoder training procedure. We also experiment with adding reinforcement learning to our model, showing improved performance compared to MLE training.