On the Challenges of Fully Incremental Neural Dependency Parsing
This addresses the challenge of making syntactic parsers more psycholinguistically plausible for applications in real-time language processing, though it is incremental as it builds on existing methods.
The paper tackled the problem of fully incremental dependency parsing with modern neural architectures, finding that it lags behind bidirectional parsing, with results showing a 5-10% drop in accuracy on standard benchmarks.
Since the popularization of BiLSTMs and Transformer-based bidirectional encoders, state-of-the-art syntactic parsers have lacked incrementality, requiring access to the whole sentence and deviating from human language processing. This paper explores whether fully incremental dependency parsing with modern architectures can be competitive. We build parsers combining strictly left-to-right neural encoders with fully incremental sequence-labeling and transition-based decoders. The results show that fully incremental parsing with modern architectures considerably lags behind bidirectional parsing, noting the challenges of psycholinguistically plausible parsing.