Abstract
Abstract meaning representations (AMRs) are broad-coverage sentence-level semantic representations. AMRs represent sentences as rooted labeled directed acyclic graphs. AMR parsing is challenging partly due to the lack of annotated alignments between nodes in the graphs and words in the corresponding sentences. We introduce a neural parser which treats alignments as latent variables within a joint probabilistic model of concepts, relations and alignments. As exact inference requires marginalizing over alignments and is infeasible, we use the variational auto-encoding framework and a continuous relaxation of the discrete alignments. We show that joint modeling is preferable to using a pipeline of align and parse. The parser achieves the best reported results on the standard benchmark (73.6% on LDC2016E25).
Original language | English |
---|---|
Title of host publication | Proceedings of the 56th Annual Conference of the Association for Computational Linguistics (ACL) |
Place of Publication | Melbourne, Australia |
Publisher | Association for Computational Linguistics |
Pages | 397-407 |
Number of pages | 11 |
Publication status | Published - Jul 2018 |
Event | 56th Annual Meeting of the Association for Computational Linguistics - Melbourne Convention and Exhibition Centre, Melbourne, Australia Duration: 15 Jul 2018 → 20 Jul 2018 http://acl2018.org/ |
Conference
Conference | 56th Annual Meeting of the Association for Computational Linguistics |
---|---|
Abbreviated title | ACL 2018 |
Country/Territory | Australia |
City | Melbourne |
Period | 15/07/18 → 20/07/18 |
Internet address |
Fingerprint
Dive into the research topics of 'AMR Parsing as Graph Prediction with Latent Alignment'. Together they form a unique fingerprint.Profiles
-
Ivan Titov
- School of Informatics - Personal Chair of Natural Language Processing
- Institute of Language, Cognition and Computation
- Language, Interaction, and Robotics
Person: Academic: Research Active