The (Non-)Utility of Structural Features in BiLSTM-based Dependency Parsers

05/29/2019
by   Agnieszka Faleńska, et al.
0

Classical non-neural dependency parsers put considerable effort on the design of feature functions. Especially, they benefit from information coming from structural features, such as features drawn from neighboring tokens in the dependency tree. In contrast, their BiLSTM-based successors achieve state-of-the-art performance without explicit information about the structural context. In this paper we aim to answer the question: How much structural context are the BiLSTM representations able to capture implicitly? We show that features drawn from partial subtrees become redundant when the BiLSTMs are used. We provide a deep insight into information flow in transition- and graph-based neural architectures to demonstrate where the implicit information comes from when the parsers make their decisions. Finally, with model ablations we demonstrate that the structural context is not only present in the models, but it significantly influences their performance.

READ FULL TEXT

page 5

page 7

research
08/20/2019

Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing -- A Tale of Two Parsers Revisited

Transition-based and graph-based dependency parsers have previously been...
research
08/05/2018

Combining Graph-based Dependency Features with Convolutional Neural Network for Answer Triggering

Answer triggering is the task of selecting the best-suited answer for a ...
research
05/12/2017

Arc-swift: A Novel Transition System for Dependency Parsing

Transition-based dependency parsers often need sequences of local shift ...
research
10/09/2018

Answer Extraction in Question Answering using Structure Features and Dependency Principles

Question Answering (QA) research is a significant and challenging task i...
research
09/06/2022

Multiscale major factor selections for complex system data with structural dependency and heterogeneity

Based on structured data derived from large complex systems, we computat...
research
06/03/2016

Dependency Parsing as Head Selection

Conventional graph-based dependency parsers guarantee a tree structure b...
research
04/08/2020

Dependency-Based Neural Representations for Classifying Lines of Programs

We investigate the problem of classifying a line of program as containin...

Please sign up or login with your details

Forgot password? Click here to reset