Year: 2024
Type: preprint
Abstract: We study incremental constituent parsers to assess their capacity to output trees based on prefix representations alone. Guided by strictly left-to-right generative language models and tree-decoding modules, we build parsers that adhere to a strong definition of incrementality across languages. This builds upon work that asserted incrementality, but that mostly only enforced it on either the encoder or the decoder. Finally, we conduct an analysis against non-incremental and partially incremental models.
Source: arXiv (Cornell University)
Authors: Ezquerro, Ana, Gómez-Rodríguez, Carlos, Vilares, David
Institution: Universidade da Coruña
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1175115578, G121809054, G1496055848, G1622782223, G1855990336, efficient Syntactic Analysis for Large-scale Sentiment Analysis, G2199665848, G2262748287, G2309174360, G2371466228, G2660406951, G279363373, G300979063, G3259478102, G34346518, G3435981892, G3480869486, G3694284866, G4092263876, G410571670, G425668148, G430777504, G451917667, G5080475149, G5421974903, G5539308778, G5805502524, G5967599077, G7084143925, G8118709007, G8920660035, G897484643, G929308097, G99296377
OpenAlex ID: W4391591360