Weighted posets: Learning surface order from dependency trees

Abstract

This paper presents a novel algorithm for generating a surface word order for a sentence given its dependency tree using a two-stage process. Using dependency-based word embeddings and a Graph Neural Network, the algorithm first learns how to rewrite a dependency tree as a partially ordered set (poset) with edge-weights representing dependency distance. The subsequent topological sort of this poset reflects a surface word order. The algorithm is evaluated against a naive baseline of average dependency distances across 14 languages, performing well in terms of rank correlation and resulting rate of projectivity based on Universal Dependencies corpora.

An Error Analysis Framework for Shallow Surface Realization

“…Zhang et al (2012), Zhang (2013), Zhang and Clark (2015), Puduppully et al (2016), andSong et al (2018) used BLEU;Schmaltz et al (2016) parsed their outputs and calculated the UAS parsing metric; Filippova and Strube (2009) used Kendall correlation together with edit-distance to account for English word order. Similarly, Dyer (2019) used Spearman correlation between produced and gold word order for a dozen of languages. White and Rajkumar (2012), in their CCG-based realization, calculated average dependency lengths between grammar-generated sentences and gold standard.…”

DepDist: Surface realization via regex and learned dependency-distance tolerance

“…The DepDist approach to linearization relies on dependency distance tolerance, the idea that a dependent and head tolerate a certain contextual distance, measured as the number of intervening words, relative to other words in a sentence (Dyer, 2019). This dependency distance tolerance is learned from training data via a graph neural network (GNN) implemented within the Graph Nets framework (Battaglia et al, 2018) based on word2vecf syntactic embeddings (Levy and Goldberg, 2014).…”