Automatic Semantic Role Labeling on Non-revised Syntactic Trees of Journalistic Texts

@inproceedings{Hartmann2016AutomaticSR,
  title={Automatic Semantic Role Labeling on Non-revised Syntactic Trees of Journalistic Texts},
  author={Nathan Siegle Hartmann and Magali Sanches Duran and Sandra M. Alu{\'i}sio},
  booktitle={PROPOR},
  year={2016}
}
Semantic Role Labeling (SRL) is a Natural Language Processing task that enables the detection of events described in sentences and the participants of these events. For Brazilian Portuguese (BP), there are two studies recently concluded that perform SRL in journalistic texts. [1] obtained F1-measure scores of 79.6, using the PropBank.Br corpus, which has syntactic trees manually revised; [8], without using a treebank for training, obtained F1-measure scores of 68.0 for the same corpus. However… Expand
An automatic semantic role labeler for the portuguese language
Semantic Role Labeling (SRL) is Natural Language Processing task that provides the means to analyze, from the semantic point of view, the information expressed through text or speech. Its purpose isExpand
Semi-supervised Semantic Role Labeling for Brazilian Portuguese
TLDR
This article investigates semi-supervised learning methods in the classification of semantic roles for the Brazilian Portuguese, a relatively resource-poor language and demonstrates that self-training heuristic outperforms other SSL and supervised methods, even when the latter are trained on a high number of labeled arguments. Expand
A Rule-Based AMR Parser for Portuguese
TLDR
An approach for a rule-based parser with generic rules in order to overcome a gap between English and other languages is introduced and evaluated on a manually annotated corpus in Portuguese, achieving promising results and outperforming one of the current parser development strategies. Expand
Exploring Classical and Linguistically Enriched Knowledge-based Methods for Sense Disambiguation of Verbs in Brazilian Portuguese News Texts
TLDR
A study on general purpose WSD methods for verbs in Brazilian Portuguese that emphasizes the free availability of the sense-annotated corpus and the use of a verb-focused repository to support classical methods in a new way. Expand
Using Recurrent Neural Networks for Semantic Role Labeling in Portuguese
TLDR
An end-to-end semantic role labeler for the Portuguese language, which leans on a deep bidirectional long short-term memory neural network architecture, and provides a detailed analysis of the effects of word embedding dimensionality and network depth on the overall performance. Expand
Improving semantic role labeling using high-level classification in complex networks
TLDR
Results in the verb-specific scenario revealed that the high-level system is able to obtain a considerable gain in terms of predictive performance, even over a state-of-the-art algorithm for SRL. Expand
Semantic Role Labeling in Portuguese: Improving the State of the Art with Transfer Learning and BERT-based Models
Semantic role labeling is the natural language processing task of determining "Who did what to whom", "when", "where", "how", etc. In this thesis, we explored state of the art techniques for thisExpand
Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning
TLDR
A model architecture with only a pre-trained Transformer-based model, a linear layer, softmax and Viterbi decoding is explored, substantially improving the state-of-the-art performance in Portuguese by over 15 F1. Expand
Transformers and Transfer Learning for Improving Portuguese Semantic Role Labeling
TLDR
A model architecture with only a pretrained BERT-based model, a linear layer, softmax and Viterbi decoding is explored, and an heuristic is presented that supports the choice of the most appropriate model considering the available resources. Expand

References

SHOWING 1-10 OF 15 REFERENCES
The Proposition Bank: An Annotated Corpus of Semantic Roles
TLDR
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. Expand
Semantic Role Labeling for Brazilian Portuguese: A Benchmark
TLDR
This work presents a benchmark for comparing SRL systems for Brazilian Portuguese, based on the CoNLL Shared Tasks on SRL for English, and implements a supervised SRL system which outperforms the baseline (17 points better in F 1 measure). Expand
Propbank-Br: a Brazilian Treebank annotated with semantic role labels
TLDR
A new annotation guide ― called Propbank-Br ― has been generated to deal with specific language phenomena and parser problems, and the annotation of a Brazilian Portuguese Treebank with semantic role labels following Propbank guidelines is reported. Expand
A Global Joint Model for Semantic Role Labeling
We present a model for semantic role labeling that effectively captures the linguistic intuition that a semantic argument frame is a joint structure, with strong dependencies among the arguments. WeExpand
A two-step convolutional neural network approach for semantic role labeling
  • E. Fonseca, J. Rosa
  • Computer Science
  • The 2013 International Joint Conference on Neural Networks (IJCNN)
  • 2013
TLDR
A two-step convolutional neural architecture is employed to label semantic arguments in Brazilian Portuguese texts, and avoid the use of external NLP tools. Expand
Assessing Agreement on Classification Tasks: The Kappa Statistic
  • J. Carletta
  • Computer Science, Sociology
  • Comput. Linguistics
  • 1996
TLDR
What is wrong with reliability measures as they are currently used for discourse and dialogue work in computational linguistics and cognitive science, and it is argued that the field would be better off as a field adopting techniques from content analysis. Expand
SALTO - A Versatile Multi-Level Annotation Tool
TLDR
The SALTO tool was originally developed for the annotation of semantic roles in the frame semantics paradigm, but can be used for graphical annotation of treebanks with general relational information in a simple drag-and-drop fashion. Expand
The measurement of observer agreement for categorical data.
TLDR
A general statistical methodology for the analysis of multivariate categorical data arising from observer reliability studies is presented and tests for interobserver bias are presented in terms of first-order marginal homogeneity and measures of interob server agreement are developed as generalized kappa-type statistics. Expand
Anotação Lingǘıstica em XML do Corpus PLN-BR
  • NILC–TR–09–08. Tech. rep., University of São Paulo, Brazil
  • 2008
...
1
2
...