VerbAtlas: a Novel Large-Scale Verbal Semantic Resource and Its Application to Semantic Role Labeling

Abstract Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntactic information can make remarkable contributions to SRL performance; however, the necessity of syntactic information was challenged by a few recent neural SRL studies that demonstrate impressive performance without syntactic backbones and suggest that syntax information becomes much less important for neural semantic role labeling, especially when paired with recent deep neural network and large-scale pre-trained language models. Despite this notion, the neural SRL field still lacks a systematic and full investigation on the relevance of syntactic information in SRL, for both dependency and both monolingual and multilingual settings. This paper intends to quantify the importance of syntactic information for neural SRL in the deep learning framework. We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruningbased and syntax feature-based. Experiments are conducted on the CoNLL-2005, 2009, and 2012 benchmarks for all languages available, and results show that neural SRL models can still benefit from syntactic information under certain conditions. Furthermore, we show the quantitative significance of syntax to neural SRL models together with a thorough empirical survey using existing models.

Download Full-text

Tree Kernels for Semantic Role Labeling

Computational Linguistics ◽

10.1162/coli.2008.34.2.193 ◽

2008 ◽

Vol 34 (2) ◽

pp. 193-224 ◽

Cited By ~ 58

Author(s):

Alessandro Moschitti ◽

Daniele Pighin ◽

Roberto Basili

Keyword(s):

Language Processing ◽

Large Scale ◽

Kernel Functions ◽

Feature Representation ◽

Training Data ◽

Support Vector ◽

Feature Engineering ◽

Semantic Role ◽

Learning Approaches ◽

Semantic Role Labeling

The availability of large scale data sets of manually annotated predicate-argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature representation and for effective decompositions of the task in different learning models. Regarding the former choice, structural properties of full syntactic parses are largely employed as they represent ways to encode different principles suggested by the linking theory between syntax and semantics. The latter choice relates to several learning schemes over global views of the parses. For example, re-ranking stages operating over alternative predicate-argument sequences of the same sentence have shown to be very effective. In this article, we propose several kernel functions to model parse tree properties in kernel-based machines, for example, perceptrons or support vector machines. In particular, we define different kinds of tree kernels as general approaches to feature engineering in SRL. Moreover, we extensively experiment with such kernels to investigate their contribution to individual stages of an SRL architecture both in isolation and in combination with other traditional manually coded features. The results for boundary recognition, classification, and re-ranking stages provide systematic evidence about the significant impact of tree kernels on the overall accuracy, especially when the amount of training data is small. As a conclusive result, tree kernels allow for a general and easily portable feature engineering method which is applicable to a large family of natural language processing tasks.

Download Full-text

Text Rewriting Improves Semantic Role Labeling

Journal of Artificial Intelligence Research ◽

10.1613/jair.4431 ◽

2014 ◽

Vol 51 ◽

pp. 133-164 ◽

Cited By ~ 1

Author(s):

K. Woodsend ◽

M. Lapata

Keyword(s):

Gold Standard ◽

High Performance ◽

Large Scale ◽

State Of The Art ◽

The State ◽

Semantic Role ◽

Semantic Role Labeling ◽

Comparable Corpora ◽

Rewrite Rules ◽

Model Training

Large-scale annotated corpora are a prerequisite to developing high-performance NLP systems. Such corpora are expensive to produce, limited in size, often demanding linguistic expertise. In this paper we use text rewriting as a means of increasing the amount of labeled data available for model training. Our method uses automatically extracted rewrite rules from comparable corpora and bitexts to generate multiple versions of sentences annotated with gold standard labels. We apply this idea to semantic role labeling and show that a model trained on rewritten data outperforms the state of the art on the CoNLL-2009 benchmark dataset.

Download Full-text

Semi-Supervised Semantic Role Labeling via Structural Alignment

Computational Linguistics ◽

10.1162/coli_a_00087 ◽

2012 ◽

Vol 38 (1) ◽

pp. 135-171 ◽

Cited By ~ 8

Author(s):

Hagen Fürstenau ◽

Mirella Lapata

Keyword(s):

High Performance ◽

Large Scale ◽

Semantic Analysis ◽

Syntactic Structure ◽

Structural Alignment ◽

Semantic Role ◽

Semantic Role Labeling ◽

Improve Performance ◽

Underlying Assumption ◽

Alignment Problem

Large-scale annotated corpora are a prerequisite to developing high-performance semantic role labeling systems. Unfortunately, such corpora are expensive to produce, limited in size, and may not be representative. Our work aims to reduce the annotation effort involved in creating resources for semantic role labeling via semi-supervised learning. The key idea of our approach is to find novel instances for classifier training based on their similarity to manually labeled seed instances. The underlying assumption is that sentences that are similar in their lexical material and syntactic structure are likely to share a frame semantic analysis. We formalize the detection of similar sentences and the projection of role annotations as a graph alignment problem, which we solve exactly using integer linear programming. Experimental results on semantic role labeling show that the automatic annotations produced by our method improve performance over using hand-labeled instances alone.

Download Full-text

Large Scale Application of Neural Network Based Semantic Role Labeling for Automated Relation Extraction from Biomedical Texts

PLoS ONE ◽

10.1371/journal.pone.0006393 ◽

2009 ◽

Vol 4 (7) ◽

pp. e6393 ◽

Cited By ~ 30

Author(s):

Thorsten Barnickel ◽

Jason Weston ◽

Ronan Collobert ◽

Hans-Werner Mewes ◽

Volker Stümpflen

Keyword(s):

Neural Network ◽

Large Scale ◽

Relation Extraction ◽

Semantic Role ◽

Semantic Role Labeling ◽

Biomedical Texts

Download Full-text

Text Rewriting Improves Semantic Role Labeling (Extended Abstract)

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2017/729 ◽

2017 ◽

Author(s):

Kristian Woodsend ◽

Mirella Lapata

Keyword(s):

Gold Standard ◽

High Performance ◽

Large Scale ◽

State Of The Art ◽

The State ◽

Semantic Role ◽

Semantic Role Labeling ◽

Comparable Corpora ◽

Rewrite Rules ◽

Model Training

Large-scale annotated corpora are a prerequisite to developing high-performance NLP systems. Such corpora are expensive to produce, limited in size, often demanding linguistic expertise. In this paper we use text rewriting as a means of increasing the amount of labeled data available for model training. Our method uses automatically extracted rewrite rules from comparable corpora and bitexts to generate multiple versions of sentences annotated with gold standard labels. We apply this idea to semantic role labeling and show that a model trained on rewritten data outperforms the state of the art on the CoNLL-2009 benchmark dataset.

Download Full-text