TY - GEN
T1 - Parsing as tagging
AU - Vacareanu, Robert
AU - Barbosa, George C.G.
AU - Valenzuela-Escarcega, Marco A.
AU - Surdeanu, Mihai
N1 - Funding Information:
This work was funded by the Bill and Melinda Gates Foundation HBGDki Initiative. Marco Valenzuela-Escárcega and Mihai Surdeanu declare a financial interest in lum.ai. This interest has been properly disclosed to the University of Arizona Institutional Review Committee and is managed in accordance with its conflict of interest policies.
Publisher Copyright:
© European Language Resources Association (ELRA), licensed under CC-BY-NC
PY - 2020
Y1 - 2020
N2 - We propose a simple yet accurate method for dependency parsing that treats parsing as tagging (PaT). That is, our approach addresses the parsing of dependency trees with a sequence model implemented with a bidirectional LSTM over BERT embeddings, where the “tag” to be predicted at each token position is the relative position of the corresponding head. For example, for the sentence John eats cake, the tag to be predicted for the token cake is -1 because its head (eats) occurs one token to the left. Despite its simplicity, our approach performs well. For example, our approach outperforms the state-of-the-art method of (Fernández-González and Gómez-Rodríguez, 2019) on Universal Dependencies (UD) by 1.76% unlabeled attachment score (UAS) for English, 1.98% UAS for French, and 1.16% UAS for German. On average, on 15 UD languages, our method with minimal tuning performs comparably with this state-of-the-art approach, being only 0.16% UAS, and 0.82% LAS behind.
AB - We propose a simple yet accurate method for dependency parsing that treats parsing as tagging (PaT). That is, our approach addresses the parsing of dependency trees with a sequence model implemented with a bidirectional LSTM over BERT embeddings, where the “tag” to be predicted at each token position is the relative position of the corresponding head. For example, for the sentence John eats cake, the tag to be predicted for the token cake is -1 because its head (eats) occurs one token to the left. Despite its simplicity, our approach performs well. For example, our approach outperforms the state-of-the-art method of (Fernández-González and Gómez-Rodríguez, 2019) on Universal Dependencies (UD) by 1.76% unlabeled attachment score (UAS) for English, 1.98% UAS for French, and 1.16% UAS for German. On average, on 15 UD languages, our method with minimal tuning performs comparably with this state-of-the-art approach, being only 0.16% UAS, and 0.82% LAS behind.
KW - Dependency parsing
KW - Sequence methods
UR - http://www.scopus.com/inward/record.url?scp=85096531590&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096531590&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85096531590
T3 - LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
SP - 5225
EP - 5231
BT - LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
A2 - Calzolari, Nicoletta
A2 - Bechet, Frederic
A2 - Blache, Philippe
A2 - Choukri, Khalid
A2 - Cieri, Christopher
A2 - Declerck, Thierry
A2 - Goggi, Sara
A2 - Isahara, Hitoshi
A2 - Maegaard, Bente
A2 - Mariani, Joseph
A2 - Mazo, Helene
A2 - Moreno, Asuncion
A2 - Odijk, Jan
A2 - Piperidis, Stelios
PB - European Language Resources Association (ELRA)
T2 - 12th International Conference on Language Resources and Evaluation, LREC 2020
Y2 - 11 May 2020 through 16 May 2020
ER -