Translation systems are generally trained to optimize BLEU, but many alternative metrics are available. We explore how optimizing toward various automatic evaluation metrics (BLEU...
Daniel Cer, Christopher D. Manning, Daniel Jurafsk...
Reverse Turing tests, or CAPTCHAs, have become an ubiquitous defense used to protect open Web resources from being exploited at scale. An effective CAPTCHA resists existing mechan...
Marti Motoyama, Kirill Levchenko, Chris Kanich, Da...
Supervised sequence-labeling systems in natural language processing often suffer from data sparsity because they use word types as features in their prediction tasks. Consequently...
An efficient decoding algorithm is a crucial element of any statistical machine translation system. Some researchers have noted certain similarities between SMT decoding and the f...
Mikhail Zaslavskiy, Marc Dymetman, Nicola Cancedda
Assamese is a morphologically rich, agglutinative and relatively free word order Indic language. Although spoken by nearly 30 million people, very little computational linguistic ...