Cross-lingual Annotation Projection for Semantic Roles

Abstract

This article considers the task of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We propose a general framework that is based on annotation projection, phrased as a graph optimization problem. It is relatively inexpensive and has the potential to reduce the human effort involved in creating role-semantic resources. Within this framework, we present projection models that exploit lexical and syntactic information. We provide an experimental evaluation on an English-German parallel corpus which demonstrates the feasibility of inducing high-precision German semantic role annotation both for manually and automatically annotated English data.

References in corpus (1)

• Cross-lingual Annotation Projection for Semantic Roles

Cited by in corpus (13)

• An Autoencoder Approach to Learning Bilingual Word Representations
• Cross-lingual Annotation Projection for Semantic Roles
• Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction
• Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual Transfer
• Aligning Coordinated Text Streams through Burst Information Network Construction and Decipherment
• Entity Projection via Machine Translation for Cross-Lingual NER
• A Bayesian Model of Multilingual Unsupervised Semantic Role Induction
• Multilingual Open Relation Extraction Using Cross-lingual Projection
• Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles
• A Discriminative Neural Model for Cross-Lingual Word Alignment
• Cross-lingual Semantic Role Labeling with Model Transfer
• Neural Unsupervised Semantic Role Labeling
• Building a Hebrew Semantic Role Labeling Lexical Resource from Parallel Movie Subtitles