Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing

By Jean Maillard, Stephen Clark. 2018

18 citations recorded by the source corpus.

Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the composition order. This work contributes (a) a new latent tree learning model based on shift-reduce parsing, with competitive downstream performance and non-trivial induced trees, and (b) an analysis of the trees learned by our shift-reduce model and by a chart-based model.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Grammar-Based Grounded Lexicon Learning (2022, methodology): “Beyond enumerating all possible parsing trees as in [29], G2L2 considers all possible programs associated with each span.”
Analysis Methods in Neural Language Processing: A Survey (2018, background): “Finally, a couple of papers discovered that models trained with latent trees perform better on natural language inference (NLI) (Williams et al., 2018; Maillard and Clark, 2018) than ones trained with linguistically annotated trees.”
Visually Grounded Neural Syntax Acquisition (2019, unknown): “…has proposed several approaches for inducing latent syntactic structures, including constituency trees (Choi et al., 2018; Yogatama et al., 2017; Maillard and Clark, 2018; Havrylov et al., 2019; Kim et al., 2019; Drozdov et al., 2019) and dependency trees (Shi et al., 2019), from the distant…”
Unsupervised Recurrent Neural Network Grammars (2019, unknown): “, 2019), or differentiable relaxations (Choi et al., 2018; Maillard and Clark, 2018).”