Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing

Alberto Muñoz-Ortiz, Universidade da Coruña, CITIC, Spain, Michalina Strzyz, David Vilares, Universidade da Coruña, CITIC, Spain, Priberam Labs, Portugal, Universidade da Coruña, CITIC, Spain
2021 Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Methods and Applications   unpublished
Different linearizations have been proposed to cast dependency parsing as sequence labeling and solve the task as: (i) a head selection problem, (ii) finding a representation of the token arcs as bracket strings, or (iii) associating partial transition sequences of a transition-based parser to words. Yet, there is little understanding about how these linearizations behave in low-resource setups. Here, we first study their data efficiency, simulating data-restricted setups from a diverse set of
more » ... ich-resource treebanks. Second, we test whether such differences manifest in truly low-resource setups. The results show that head selection encodings are more data-efficient and perform better in an ideal (gold) framework, but that such advantage greatly vanishes in favour of bracketing formats when the running setup resembles a real-world low-resource configuration.
doi:10.26615/978-954-452-072-4_111 fatcat:5w5m3e4zhvcgbihp42k3pa4yme