Skip to Main Content
Table 3: 
Results of the conditional perplexity experiment (§4), reported as perplexity per punctuation slot, where an unpunctuated sentence of n words has n + 1 slots. Column “Attn.” is the BiGRU tagger with attention, and “CRF” stands for the BiLSTM-CRF tagger. “Attach” is the ablated version of our model where surface punctuation is directly attached to the nodes. Our full model “+NC” adds NoisyChannel to transduce the attached punctuation into surface punctuation. Dir is the learned direction (§2.2) of our full model’s noisy channel PFST: Left-to-right or Right-to-left. Our models are given oracle parse trees T. The best perplexity is boldfaced, along with all results that are not significantly worse (paired permutation test, p < 0.05).
Attn.CRFAttach+NCDir
Arabic 1.4676 1.3016 1.2230 1.1526 
Chinese 1.6850 1.4436 1.1921 1.1464 
English 1.5737 1.5247 1.5636 1.4276 
Hindi 1.1201 1.1032 1.0630 1.0598 
Spanish 1.4397 1.3198 1.2364 1.2103 
Attn.CRFAttach+NCDir
Arabic 1.4676 1.3016 1.2230 1.1526 
Chinese 1.6850 1.4436 1.1921 1.1464 
English 1.5737 1.5247 1.5636 1.4276 
Hindi 1.1201 1.1032 1.0630 1.0598 
Spanish 1.4397 1.3198 1.2364 1.2103 
Close Modal

or Create an Account

Close Modal
Close Modal