Abstract
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of the compositional tree structures for training. In the past, these were obtained using complex graphbank-specific heuristics written by experts. Here we show how they can instead be trained directly on the graphs with a neural latent-variable model, drastically reducing the amount and complexity of manual heuristics. We demonstrate that our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training, greatly facilitating the use of AM dependency parsing for new sembanks.
Original language | English |
---|---|
Title of host publication | Proceedings of the 5th Workshop on Structured Prediction for NLP |
Pages | 22-36 |
Number of pages | 15 |
DOIs | |
Publication status | Published - 6 Aug 2021 |
Event | Structured Prediction for NLP - Online Duration: 6 Aug 2021 → 6 Aug 2021 Conference number: 5 http://structuredprediction.github.io/SPNLP21 |
Workshop
Workshop | Structured Prediction for NLP |
---|---|
Abbreviated title | SPNLP |
Period | 6/08/21 → 6/08/21 |
Internet address |