Connectionist F-structure transfer
暂无分享,去创建一个
A traditional transfer system in machine translation maps between language structures and an intermediate representation. Our connectionist transfer system maps from f-structures of one language to f-structures of another language. It encodes the intermediate representation implicitly in neural networks' activation patterns. The system is learnable, therefore it does not need any e ort in handcrafting the representation and mapping rules. Experiments show the system has good scalability and generalizability performance.
[1] Lonnie Chrisman,et al. Learning Recursive Distributed Representations for Holistic Computation , 1991 .
[2] M. Baltin,et al. The Mental representation of grammatical relations , 1985 .
[3] R. Miikkulainen,et al. A modular neural network architecture for sequential paraphrasing of script-based stories , 1989, International 1989 Joint Conference on Neural Networks.
[4] Ye-Yi Wang. Dual-Coding Theory and Connectionist Lexical Selection , 1994, ACL.