most citedSemantic Tagging with Deep Residual Networks

62 citations · 94 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL20171 cited

Parsing Universal Dependencies without training

Héctor Martínez Alonso, Željko Agić, Barbara Plank +1

We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step de…

cs.CL20175 cited

When is multitask learning effective? Semantic sequence prediction under varying data conditions

Héctor Martínez Alonso, Barbara Plank

Multitask learning has been applied successfully to a range of tasks, mostly morphosyntactic. However, little is known on when MTL works and whether there are data characteristics…

cs.CL2016

When silver glitters more than gold: Bootstrapping an Italian part-of-speech tagger for Twitter

Barbara Plank, Malvina Nissim

We bootstrap a state-of-the-art part-of-speech tagger to tag Italian Twitter data, in the context of the Evalita 2016 PoSTWITA shared task. We show that training the tagger on nati…

cs.CL201662 cited

Semantic Tagging with Deep Residual Networks

Johannes Bjerva, Barbara Plank, Johan Bos

We propose a novel semantic tagging task, sem-tagging, tailored for the purpose of multilingual semantic parsing, and present the first tagger using deep residual networks (ResNets…

cs.CL20169 cited

Keystroke dynamics as signal for shallow syntactic parsing

Barbara Plank

Keystroke dynamics have been extensively used in psycholinguistic and writing research to gain insights into cognitive processing. But do keystroke logs contain actual signal that…

cs.CL201617 cited

What to do about non-standard (or non-canonical) language in NLP

Barbara Plank

Real world data differs radically from the benchmark corpora we use in natural language processing (NLP). As soon as we apply our technologies to the real world, performance drops.…