Context-aware Frame-Semantic Role Labeling
TL
TL;DR
This paper presents a semantic role labeling system that takes into account sentence and discourse context and introduces several new features which are motivated based on linguistic insights and experimentally demonstrate that they lead to significant improvements over the current state-of-the-art in FrameNet-based semantic role labeled.
Abstract
Frame semantic representations have been useful in several applications ranging from text-to-scene generation, to question answering and social network analysis. Predicting such representations from raw text is, however, a challenging task and corresponding models are typically only trained on a small set of sentence-level annotations. In this paper, we present a semantic role labeling system that takes into account sentence and discourse context. We introduce several new features which we motivate based on linguistic insights and experimentally demonstrate that they lead to significant improvements over the current state-of-the-art in FrameNet-based semantic role labeling.
References42 items
1
Dependency-Based Semantic Role Labeling using Convolutional Neural Networks
2
High-Order Low-Rank Tensors for Semantic Role Labeling
3
Efficient Inference and Structured Learning for Semantic Role Labeling
4
GloVe: Global Vectors for Word Representation
5