Multilingual Semantic Role Labeling

By Anders Björkelund, Love Hafdell, Pierre Nugues. 2009

238 citations recorded by the source corpus.

This paper describes our contribution to the semantic role labeling task (SRL-only) of the CoNLL-2009 shared task in the closed challenge (Hajic et al., 2009). Our system consists of a pipeline of independent, local classifiers that identify the predicate sense, the arguments of the predicates, and the argument labels. Using these local models, we carried out a beam search to generate a pool of candidates. We then reranked the candidates using a joint learning approach that combines the local models and proposition features. To address the multilingual nature of the data, we implemented a feature selection procedure that systematically explored the feature space, yielding significant gains over a standard set of features. Our system achieved the second best semantic score overall with an average labeled semantic F1 of 80.31. It obtained the best F1 score on the Chinese and German data and the second best one on English.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, methodology): “Also, as we focus here solely on identifying arguments and labeling them with semantic roles, for predicate disambiguation (i.e., marking makes as make.01 ) we use of an off-the-shelf disambiguation model (Roth and Lapata, 2016; Bj¨orkelund et al., 2009).”
Movie Script Summarization as Graph-based Scene Extraction (2015, methodology): “They were also annotated with semantic roles (e.g., ARG0, ARG1), using the MATE tools (Björkelund et al., 2009).”
YiSi - a Unified Semantic MT Quality Evaluation and Estimation Metric for Languages with Different Levels of Available Resources (2019, methodology): “There are a handful of shallow semantic parsers available publicly. mate-tools (Björkelund et al., 2009) is an SVM classifier based on features extracted from a dependency parse.”
Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling (2015, methodology): “We then train an off-the-shelf SRL system (Björkelund et al., 2009) on each generated corpus and use it to relabel the corpus.”
A High-Performance Syntactic and Semantic Dependency Parser (2010, methodology): “To speed up processing, we disabled the reranker used in the CoNLL 2009 sys-tem (Bj¨orkelund et al., 2009).”
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs (2016, background): “Many of these systems use expert-crafted features derived from full syntactic parses in a pipeline of classifiers followed by a global reranker (Björkelund et al., 2009; Björkelund et al., 2010; Roth and Woodsend, 2014); we have not used these features or reranking. Lei et al. (2015) use syntactic p”