Combination Strategies for Semantic Role Labeling

by   M. Surdeanu, et al.

This paper introduces and analyzes a battery of inference models for the problem of semantic role labeling: one based on constraint satisfaction, and several strategies that model the inference as a meta-learning problem using discriminative classifiers. These classifiers are developed with a rich set of novel features that encode proposition and sentence-level information. To our knowledge, this is the first work that: (a) performs a thorough analysis of learning-based inference models for semantic role labeling, and (b) compares several inference strategies in this context. We evaluate the proposed inference strategies in the framework of the CoNLL-2005 shared task using only automatically-generated syntactic information. The extensive experimental evaluation and analysis indicates that all the proposed inference strategies are successful -they all outperform the current best results reported in the CoNLL-2005 evaluation exercise- but each of the proposed approaches has its advantages and disadvantages. Several important traits of a state-of-the-art SRL combination strategy emerge from this analysis: (i) individual models should be combined at the granularity of candidate arguments rather than at the granularity of complete solutions; (ii) the best combination strategy uses an inference model based in learning; and (iii) the learning-based inference benefits from max-margin classifiers and global feedback.


page 1

page 2

page 3

page 4


Improving Aspect-Based Sentiment with End-to-End Semantic Role Labeling Model

This paper presents a series of approaches aimed at enhancing the perfor...

Multi-Domain Active Learning: A Comparative Study

Building classifiers on multiple domains is a practical problem in the r...

A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

We introduce a simple and accurate neural model for dependency-based sem...

Neural Semantic Role Labeling with Dependency Path Embeddings

This paper introduces a novel model for semantic role labeling that make...

Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments

Implicit semantic role labeling (iSRL) is the task of predicting the sem...

Transition-based Semantic Role Labeling with Pointer Networks

Semantic role labeling (SRL) focuses on recognizing the predicate-argume...

Feature Generation for Robust Semantic Role Labeling

Hand-engineered feature sets are a well understood method for creating r...

Please sign up or login with your details

Forgot password? Click here to reset