Exploring Neural Methods for Parsing Discourse Representation Structures

Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence neural semantic parser that is able to produce Discourse Representation Structures (DRSs) for English sentences with high accuracy, outperforming traditional DRS parsers. To facilitate the learning of the output, we represent DRSs as a sequence of flat clauses and introduce a method to verify that produced DRSs are well-formed and interpretable. We compare models using characters and words as input and see (somewhat surprisingly) that the former performs better than the latter. We show that eliminating variable names from the output using De Bruijn-indices increases parser performance. Adding silver training data boosts performance even further.

PDF Abstract TACL 2018 PDF TACL 2018 Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
DRS Parsing PMB-2.2.0 Character-level bi-LSTM seq2seq F1 83.3 # 4
DRS Parsing PMB-3.0.0 Character-level bi-LSTM seq2seq F1 84.9 # 3


No methods listed for this paper. Add relevant methods here