Neuron Interaction Based Representation Composition for Neural Machine Translation

22 Nov 2019Jian LiXing WangBaosong YangShuming ShiMichael R. LyuZhaopeng Tu

Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better capture complex information by composing the linguistic properties embedded in individual neurons... (read more)

PDF Abstract


No code implementations yet. Submit your code now

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper