scholarly journals Cross-lingual Annotation Projection for Semantic Roles

2009 ◽  
Vol 36 ◽  
pp. 307-340 ◽  
Author(s):  
S. Pado ◽  
M. Lapata
Keyword(s):  
General Framework ◽  
Optimization Problem ◽  
Semantic Role ◽  
Semantic Roles ◽  
Role Semantic ◽  
Graph Optimization ◽  
Syntactic Information ◽  
Human Effort ◽  
Cross Lingual ◽  
Semantic Resources

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.

scholarly journals The Proposition Bank: An Annotated Corpus of Semantic Roles

2005 ◽  
Vol 31 (1) ◽  
pp. 71-106 ◽  
Author(s):  
Martha Palmer ◽  
Daniel Gildea ◽  
Paul Kingsbury
Keyword(s):  
Automatic System ◽  
Semantic Representation ◽  
Higher Order ◽  
Practical Approach ◽  
Semantic Role ◽  
Syntactic Parsing ◽  
Semantic Roles ◽  
Syntactic Structures ◽  
Annotation Process ◽  
Types Of Information

The Proposition Bank project takes a practical approach to semantic representation, adding a layer of predicate-argument information, or semantic role labels, to the syntactic structures of the Penn Treebank. The resulting resource can be thought of as shallow, in that it does not represent coreference, quantification, and many other higher-order phenomena, but also broad, in that it covers every instance of every verb in the corpus and allows representative statistics to be calculated. We discuss the criteria used to define the sets of semantic roles used in the annotation process and to analyze the frequency of syntactic/semantic alternations in the corpus. We describe an automatic system for semantic role tagging trained on the corpus and discuss the effect on its performance of various types of information, including a comparison of full syntactic parsing with a flat representation and the contribution of the empty “trace” categories of the treebank.

scholarly journals Syntax Role for Neural Semantic Role Labeling

2021 ◽  
pp. 1-48
Author(s):  
Zuchao Li ◽  
Hai Zhao ◽  
Shexia He ◽  
Jiaxun Cai
Keyword(s):  
Argument Structure ◽  
Large Scale ◽  
Language Models ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Empirical Survey ◽  
Learning Framework ◽  
Syntactic Information ◽  
Feature Based ◽  
Predicate Argument Structure

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.

scholarly journals A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces

2020 ◽  
Vol 34 (05) ◽  
pp. 8131-8138
Author(s):  
Anne Lauscher ◽  
Goran Glavaš ◽  
Simone Paolo Ponzetto ◽  
Ivan Vulić
Keyword(s):  
General Framework ◽  
Semantic Information ◽  
Evaluation Framework ◽  
Vector Spaces ◽  
Racial Biases ◽  
Definition Of ◽  
Cross Lingual ◽  
Experimental Findings ◽  
Implicit And Explicit ◽  
Embedding Methods

Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have consequently been proposed. However, existing models and studies (1) operate on under-specified and mutually differing bias definitions, (2) are tailored for a particular bias (e.g., gender bias) and (3) have been evaluated inconsistently and non-rigorously. In this work, we introduce a general framework for debiasing word embeddings. We operationalize the definition of a bias by discerning two types of bias specification: explicit and implicit. We then propose three debiasing models that operate on explicit or implicit bias specifications and that can be composed towards more robust debiasing. Finally, we devise a full-fledged evaluation framework in which we couple existing bias metrics with newly proposed ones. Experimental findings across three embedding methods suggest that the proposed debiasing models are robust and widely applicable: they often completely remove the bias both implicitly and explicitly without degradation of semantic information encoded in any of the input distributional spaces. Moreover, we successfully transfer debiasing models, by means of cross-lingual embedding spaces, and remove or attenuate biases in distributional word vector spaces of languages that lack readily available bias specifications.

scholarly journals Semantic Roles of The Verb “To See” in Javenese of Kertosono

2019 ◽  
Vol 5 (2) ◽  
pp. 122-129
Author(s):  
A.A.A Ngr. Adriyanti Weda Ningrat ◽  
I Nyoman Kardana ◽  
Mirsa Umiyati
Keyword(s):  
Qualitative Research ◽  
Data Analysis ◽  
Role Theory ◽  
Shape Function ◽  
Semantic Role ◽  
Semantic Roles ◽  
Qualitative Research Design ◽  
Semantic Fields ◽  
General Semantic

This study reveals the semantic fields from the "to see" verb in Javanese. The aims of this research is to describe the shape, function, meaning and role of semantic of each variant of the verb "to see". To realize this goal, qualitative research design was applied in this study and the semantic role theory of Vole and Van Valin (1984). Was also oriented in data analysis. Verbs that have semantic fields that are associated with the "to see" verb with intentional entities numbering 33. Each of them is ndêlok, ndêlêng, ningali, mirsani, ndeleng sacleraman, ndêlêng tênanên, ningali saestu, mirsani saestu, ningali sekedhap, mirsani sekedhap, mlengos, ngwasi, ngêmatake, ngematakên, ndhangak, dingkluk, nginceng, ngêlirêk, mêntêlêngi, ndelok mburi, and maca. The semantic roles of the arguments of each verb consist of agents and themes. This study only sheds light on the meaning field verb "to see" of the type of variant and a little about the general semantic role. For this reason, a more detailed study of the specific role of each variant of the verb is a topic that can be raised in the next study.

scholarly journals A General Framework for Portfolio Theory. Part III: Multi-Period Markets and Modular Approach

Risks ◽  
2019 ◽  
Vol 7 (2) ◽  
pp. 60
Author(s):  
Stanislaus Maier-Paape ◽  
Andreas Platen ◽  
Qiji Jim Zhu
Keyword(s):  
General Framework ◽  
Optimization Problem ◽  
Risk Measure ◽  
Efficient Frontier ◽  
Portfolio Theory ◽  
Trading Strategies ◽  
Performance Criteria ◽  
Market Model ◽  
Constant Weight ◽  
New Approach

This is Part III of a series of papers which focus on a general framework for portfolio theory. Here, we extend a general framework for portfolio theory in a one-period financial market as introduced in Part I [Maier-Paape and Zhu, Risks 2018, 6(2), 53] to multi-period markets. This extension is reasonable for applications. More importantly, we take a new approach, the “modular portfolio theory”, which is built from the interaction among four related modules: (a) multi period market model; (b) trading strategies; (c) risk and utility functions (performance criteria); and (d) the optimization problem (efficient frontier and efficient portfolio). An important concept that allows dealing with the more general framework discussed here is a trading strategy generating function. This concept limits the discussion to a special class of manageable trading strategies, which is still wide enough to cover many frequently used trading strategies, for instance “constant weight” (fixed fraction). As application, we discuss the utility function of compounded return and the risk measure of relative log drawdowns.

Identifying semantic role clusters and alignment types via microrole coexpression tendencies

2014 ◽  
Vol 38 (3) ◽  
pp. 463-484 ◽  
Author(s):  
Iren Hartmann ◽  
Martin Haspelmath ◽  
Michael Cysouw
Keyword(s):  
Multidimensional Scaling ◽  
Quantitative Methods ◽  
Semantic Role ◽  
Semantic Roles ◽  
Conceptual Space ◽  
Index Sets ◽  
Set Up ◽  
The Individual

In this paper, we illustrate a method for identifying clusters of semantic roles by cross-linguistic comparison. On the basis of data from 25 languages drawn from the ValPaL (Valency Patterns Leipzig) database, we show how one can visualize coexpression tendencies using quantitative methods (in particular, multidimensional scaling). Traditionally, the coexpression of semantic microroles (such as the breaker and the broken thing of the ‘break’ verb, the helper and the helpee of the ‘help’ verb, etc.) has been studied for particular languages, with generalized macroroles such as “agent”, “actor”, and “undergoer” being compared across languages in a next step. We set up a conceptual space of 87 microroles based on their coexpression tendencies, i.e. the extent to which they are expressed identically (via flagging and indexing) across our languages. The individual coding means (cases, adpositions, index-sets) can then be mapped onto this conceptual space, revealing broader alignment patterns.

scholarly journals The grammar of syntactic coreference

2019 ◽  
Vol 75 (1) ◽  
pp. 21-35
Author(s):  
Milivoj Alanovic
Keyword(s):  
The Other ◽  
Semantic Role ◽  
Propositional Function ◽  
Semantic Roles ◽  
Other Hand ◽  
The Difference ◽  
The One ◽  
Syntactic Relations ◽  
Main Language

Since the notions of semantic and syntactic coreference, in the conceptual, terminological and theoretical sense, have long been known to the linguistic public, we consider it appropriate and worthwhile to point out the ways in which this type of connection between the grammatical units in the sentence is materialized. We especially wanted to draw attention to the inherent mechanisms of language which directly signal that the two forms, not necessarily different, are connected with the same meaning, and related to the same semantic role, for which it is directly responsible - the same propositional function they have. Although it may seem that the difference between semantic and syntactic coreference is not so significant, it has been revealed that in the latter case, the syntactic relations are the main language means of expressing propositional functions and corresponding semantic roles. Therefore, the purpose of this study is to highlight the syntagmatic mechanisms of language, with the help of which the structural, informative and informative hierarchy of the sentence members is carried out. The purpose of such hierarchization is not so much to streamline or rethink the structure of the sentence, but rather to ensure the integration of complex content on the one hand, and settle the situational significance of individual participants on the other hand.

scholarly journals Generalization of Semantic Roles in Automatic Semantic Role Labeling

2014 ◽  
Vol 21 (4) ◽  
pp. 841-875
Author(s):  
Yuichiroh Matsubayashi ◽  
Naoaki Okazaki ◽  
Jun’ichi Tsujii
Keyword(s):  
Semantic Role ◽  
Semantic Role Labeling ◽  
Semantic Roles

scholarly journals Applying Genetic Algorithm to Optimization Second-Order Bandpass MGMFB Filter

2020 ◽  
Vol 28 (4) ◽  
Author(s):  
Maad Mohsin Mijwil ◽  
Rana Ali Abttan
Keyword(s):  
Genetic Algorithm ◽  
Optimization Problem ◽  
Optimization Methods ◽  
Second Order ◽  
Active Filters ◽  
Multi Objective Optimization ◽  
Complex Situation ◽  
Human Effort ◽  
True Values ◽  
Selection Of

In this paper, we have applied the genetic algorithm to the selection of the true values for RC (resistors/capacitors) as an essential role in the development of analogue active filters. The classic method of incorporating passive elements is a complex situation and can attend to errors. In order to reduce the frequency of errors and the human effort, evolutionary optimization methods are employed to select the RC values. In this study, Genetic algorithm (GA) is proposed to optimize the second-order active filter. It must find the values of the passive elements RC to get a filter configuration that reduces the sensitivities to variations as well as reduces design errors less than a defined height value, concerning certain specifications. The optimization problem which is one of the problems that must be solved by GA is a multi-objective optimization problem (MOOP). GA was carried out taking into account two possible situations about the values that resistors and capacitors could adopt. The obtained experimental results show that GA can be used to obtain filter configurations that meet the specified standard.

Sign in / Sign up

Export Citation Format

Share Document