Natural Language Processing (Almost) from Scratch

6.7 Engineering a Sweet Spot

1. What is SENNA?
   The standalone C implementation of the networks (about 2500 lines): under 150 MB of memory and under a millisecond per word for all tags. With a few features it matched or beat benchmarks (POS 97.29, chunking 94.32, NER 89.59; SRL 75.49), and ran far faster with much less memory than existing taggers, e.g. SRL in 51 s vs 6253 s.
   • Collobert et al., 2011, Natural Language Processing (Almost) from Scratch (Journal of Machine Learning Research), §6.7, pp. 2526–2527