Debugging Frame Semantic Role Labeling
Alexandre Kabbach

TL;DR
This paper analyzes the performance of statistical models for frame semantic role labeling, emphasizing the impact of preprocessing, syntactic parsing, and proposing new directions for improvement.
Contribution
It provides a comprehensive analysis of factors affecting model performance and suggests novel approaches like joint parsing and neural architectures for better frame semantic parsing.
Findings
Preprocessing tools significantly impact argument identification.
Syntactic mismatch affects classifier performance.
Proposed new methods for improving semantic parsing.
Abstract
We propose a quantitative and qualitative analysis of the performances of statistical models for frame semantic structure extraction. We report on a replication study on FrameNet 1.7 data and show that preprocessing toolkits play a major role in argument identification performances, observing gains similar in their order of magnitude to those reported by recent models for frame semantic parsing. We report on the robustness of a recent statistical classifier for frame semantic parsing to lexical configurations of predicate-argument structures, relying on an artificially augmented dataset generated using a rule-based algorithm combining valence pattern matching and lexical substitution. We prove that syntactic pre-processing plays a major role in the performances of statistical classifiers to argument identification, and discuss the core reasons of syntactic mismatch between dependency…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Text Readability and Simplification
