Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-36103
Title: | Compositional Generalization Requires Compositional Parsers |
Author(s): | Weißenhorn, Pia Yao, Yuekun Donatelli, Lucia Koller, Alexander |
Language: | English |
Publisher/Platform: | arXiv |
Year of Publication: | 2022 |
Publikation type: | Other |
Abstract: | A rapidly growing body of research on compositional generalization investigates the ability of a semantic parser to dynamically recombine linguistic elements seen in training into unseen sequences. We present a systematic comparison of sequence-to-sequence models and models guided by compositional principles on the recent COGS corpus (Kim and Linzen, 2020). Though seq2seq models can perform well on lexical tasks, they perform with near-zero accuracy on structural generalization tasks that require novel syntactic structures; this holds true even when they are trained to predict syntax instead of semantics. In contrast, compositional models achieve near-perfect accuracy on structural generalization; we present new results confirming this from the AM parser (Groschwitz et al., 2021). Our findings show structural generalization is a key measure of compositional generalization and requires models that are aware of complex structure. |
DOI of the first publication: | 10.48550/arXiv.2202.11937 |
URL of the first publication: | https://arxiv.org/abs/2202.11937 |
Link to this record: | hdl:20.500.11880/32885 http://dx.doi.org/10.22028/D291-36103 |
Date of registration: | 5-May-2022 |
Notes: | Preprint |
Faculty: | P - Philosophische Fakultät |
Department: | P - Sprachwissenschaft und Sprachtechnologie |
Professorship: | P - Prof. Dr. Alexander Koller |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
There are no files associated with this item.
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.