Graph-Based Decoding for Task Oriented Semantic Parsing
Autor: | Cole, Jeremy R., Jiang, Nanjiang, Pasupat, Panupong, He, Luheng, Shaw, Peter |
---|---|
Rok vydání: | 2021 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic parsing as a dependency parsing task, applying graph-based decoding techniques developed for syntactic parsing. We compare various decoding techniques given the same pre-trained Transformer encoder on the TOP dataset, including settings where training data is limited or contains only partially-annotated examples. We find that our graph-based approach is competitive with sequence decoders on the standard setting, and offers significant improvements in data efficiency and settings where partially-annotated data is available. Comment: To appear in EMNLP 5 pages 4 figures |
Databáze: | arXiv |
Externí odkaz: |