Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling

  title={Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling},
  author={A. Akbik and Laura Chiticariu and Marina Danilevsky and Yunyao Li and Shivakumar Vaithyanathan and Huaiyu Zhu},
  booktitle={Annual Meeting of the Association for Computational Linguistics},
Semantic role labeling (SRL) is crucial to natural language understanding as it identifies the predicate-argument structure in text with semantic labels. Unfortunately, resources required to construct SRL models are expensive to obtain and simply do not exist for most languages. In this paper, we present a two-stage method to enable the construction of SRL models for resourcepoor languages by exploiting monolingual SRL and multilingual parallel data. Experimental results show that our method… 

Figures and Tables from this paper

Automatic Propbank Generation for Turkish

This paper presents the method to create an automatic Turkish PropBank by exploiting parallel data from the translated sentences of English PropBank, and shows that the method gives promising results.

Multilingual Semantic Role Labeling with Unified Labels

POLYGLOT is a multilingual semantic role labeling system capable of semantically parsing sentences in 9 different languages from 4 different language groups and treats the semantic labels of the English Proposition Bank as “universal semantic labels”.

Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus

This paper proposes a novel alternative based on corpus translation, constructing high-quality training datasets for the target languages from the source gold-standard SRL annotations, and Experimental results on Universal Proposition Bank show that the translation-based method is highly effective, and the automatic pseudo datasets can improve the target-language SRL performances significantly.

Universal Proposition Bank 2.0

This paper introduces Universal Proposition Bank 2.0 (UP2.0), with significant enhancements over UP1.0, including propbanks with higher quality by using a state-of-the-art monolingual SRL and improved auto-generation of annotations; expanded language coverage (from 7 to 9 languages); and span annotation for the decoupling of syntactic analysis.

Implicit Semantic Roles in a Multilingual Setting

This work is the first to address the detection of implicit roles from a multilingual perspective and map predicate-argument structures across English and German sentences, and develops a classifier that distinguishes implicit arguments from other translation shifts.

POLYGLOT: Multilingual Semantic Role Labeling with Unified Labels

POLYGLOT is a multilingual semantic role labeling system capable of semantically parsing sentences in 9 different languages from 4 different language groups and treats the semantic labels of the English Proposition Bank as “universal semantic labels”.

Alignment-free Cross-lingual Semantic Role Labeling

This work proposes a cross-lingual SRL model which only requires annotations in a source language and access to raw text in the form of a parallel corpus and results show that the method is highly effective, even against systems utilizing supervised features.

Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles

We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than

Using Annotation Projection for Semantic Role Labeling of Low-Resourced Language: Sinhala

The first-ever semantic role labeller (SRL) for Sinhala, an Indo-European language spoken mainly in Sri Lanka, is presented and may be easily modified to annotate other low-resource languages for which parallel corpora are available.

X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset

This work proposes a method to automatically construct an SRL corpus that is parallel in four languages: English, French, German, Spanish, with unified predicate and role annotations that are fully comparable across languages.



Cross-lingual Transfer of Semantic Role Labeling Models

This work addresses the problem of transferring an SRL model from one language to another using a shared feature representation and assesses competitive performance as compared to a state-of-the-art unsupervised SRL system and a cross-lingual annotation projection baseline.

Cross-lingual Annotation Projection for Semantic Roles

An experimental evaluation on an English-German parallel corpus is provided which demonstrates the feasibility of inducing high-precision German semantic role annotation both for manually and automatically annotated English data.

Multilingual Semantic Role Labeling

This paper describes the contribution of a pipeline of independent, local classifiers that identify the predicate sense, the arguments of the predicates, and the argument labels to the semantic role labeling task of the CoNLL-2009 shared task in the closed challenge.

Global Methods for Cross-lingual Semantic Role and Predicate Labelling

A global approach to transfer that aggregates information across the whole parallel corpus and leads to more robust labellers is presented, which shows that the combination of direct and global methods outperforms previous results.

Cross-Language Frame Semantics Transfer in Bilingual Corpora

A robust method based on a statistical machine translation step augmented with simple rule-based post-processing is presented that alleviates problems related to preprocessing errors and the complex optimization required by syntax-dependent models of the cross-lingual mapping.

Adding Semantic Role Annotation to a Corpus of Written Dutch

This work presents an approach to automatic semantic role labeling (SRL) carried out in the context of the Dutch Language Corpus Initiative (D-Coi) project, which consists of bootstrapping from a syntactically annotated corpus by means of a rule-based tagger developed for this purpose.

Crosslingual Induction of Semantic Roles

This work considers unsupervised induction of semantic roles from sentences annotated with automatically-predicted syntactic dependency representations and uses a state-of-the-art generative Bayesian non-parametric model to do so.

Using Semantic Roles to Improve Question Answering

This work introduces a general framework for answer extraction which exploits semantic role annotations in the FrameNet paradigm and views semantic role assignment as an optimization problem in a bipartite graph and answer extraction as an instance of graph matching.

Scaling up Automatic Cross-Lingual Semantic Role Annotation

This paper scales up previous efforts by using an automatic approach to semantic annotation that does not rely on a semantic ontology for the target language, and improves the quality of the transferred semantic annotations by using a joint syntactic-semantic parser.

The Proposition Bank: An Annotated Corpus of Semantic Roles

An automatic system for semantic role tagging trained on the corpus is described and the effect on its performance of various types of information is discussed, including a comparison of full syntactic parsing with a flat representation and the contribution of the empty trace categories of the treebank.