Papers by Mingbin Xu
Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models (D18-1)
Copied to clipboard
| Challenge: | In this paper, we propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) in neural languages modelling, called dual-FOFE. |
| Approach: | They propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) in neural languages modelling, called dual-FOFE. |
| Outcome: | The proposed method significantly reduces the complexity and improves perplexity by 10% over the original FOFE model. |