Semantic Role Labeling Improves Incremental Parsing

Abstract

Incremental parsing is the task of assigning a syntactic structure to an input sentence as it unfolds word by word. Incremental parsing is more difficult than fullsentence parsing, as incomplete input increases ambiguity. Intuitively, an incremental parser that has access to semantic information should be able to reduce ambiguity by ruling out semantically implausible analyses, even for incomplete input. In this paper, we test this hypothesis by combining an incremental TAG parser with an incremental semantic role labeler in a discriminative framework. We show a substantial improvement in parsing performance compared to the baseline parser, both in full-sentence F-score and in incremental F-score.

Event participant modelling with neural networks

“…Potential applications also include predicate prediction based on arguments and roles, which has been noted to be relevant for simultaneous machine translation for a verb-final to a verb-medial source language (Grissom II et al, 2014). Within cognitive modelling, our model could help to more accurately estimate semantic surprisal for broadcoverage texts, when used in combination with an incremental role labeller (e.g., Konstas and Keller, 2015), or to provide surprisal estimates for content words as a control variable for psycholinguistic experimental materials.…”

Learning distributed event representations with a multi-task approach

“…Finally, the predictive nature of this type of model can potentially enable its deployment in incremental semantic parsing (Konstas et al, 2014;Konstas and Keller, 2015) by combining the multitask design with the incremental architecture in (Tilk et al, 2016). We are continuing to develop this and other ways of employing models of event representation that simultaneously predict event participants and assess the fit of given participants.…”