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.

The Multi-Relationship Evaluation Design Framework: Designing Testing Plans to Comprehensively Assess Advanced and Intelligent Technologies

2010 ◽  
Author(s):  
Brian A. Weiss ◽  
Linda C. Schmidt ◽  
Harry A. Scott ◽  
Craig I. Schlenoff
Keyword(s):  
Intelligent Systems ◽  
New Technologies ◽  
Evaluation Framework ◽  
Evaluation Design ◽  
Design Elements ◽  
Summative Assessments ◽  
Extensive Evaluation ◽  
Level Of Knowledge ◽  
Definition Of ◽  
Key Terms

As new technologies develop and mature, it becomes critical to provide both formative and summative assessments on their performance. Performance assessment events range in form from a few simple tests of key elements of the technology to highly complex and extensive evaluation exercises targeting specific levels and capabilities of the system under scrutiny. Typically the more advanced the system, the more often performance evaluations are warranted, and the more complex the evaluation planning becomes. Numerous evaluation frameworks have been developed to generate evaluation designs intent on characterizing the performance of intelligent systems. Many of these frameworks enable the design of extensive evaluations, but each has its own focused objectives within an inherent set of known boundaries. This paper introduces the Multi-Relationship Evaluation Design (MRED) framework whose ultimate goal is to automatically generate an evaluation design based upon multiple inputs. The MRED framework takes input goal data and outputs an evaluation blueprint complete with specific evaluation elements including level of technology to be tested, metric type, user type, and, evaluation environment. Some of MRED’s unique features are that it characterizes these relationships and manages their uncertainties along with those associated with evaluation input. The authors will introduce MRED by first presenting relationships between four main evaluation design elements. These evaluation elements are defined and the relationships between them are established including the connections between evaluation personnel (not just the users), their level of knowledge, and decision-making authority. This will be further supported through the definition of key terms. An example will be presented in which these terms and relationships are applied to the evaluation design of an automobile technology. An initial validation step follows where MRED is applied to the speech translation technology whose evaluation design was inspired by the successful use of a pre-existing evaluation framework. It is important to note that MRED is still in its early stages of development where this paper presents numerous MRED outputs. Future publications will present the remaining outputs, the uncertain inputs, and MRED’s implementation steps that produce the detailed evaluation blueprints.

Diagnosis Rule Discovery Based on Causality in the Context of Fault Diagnosis in Rotating Machinery

2014 ◽  
Vol 532 ◽  
pp. 113-117
Author(s):  
Zhou Jin ◽  
Ru Jing Wang ◽  
Jie Zhang
Keyword(s):  
Fault Diagnosis ◽  
General Framework ◽  
Complex Structure ◽  
Rotating Machinery ◽  
Massive Data ◽  
Formal Definition ◽  
Rule Discovery ◽  
Rule Based ◽  
Simple Implementation ◽  
Definition Of

The rotating machineries in a factory usually have the characteristics of complex structure and highly automated logic, which generated a large amounts of monitoring data. It is an infeasible task for uses to deal with the massive data and locate fault timely. In this paper, we explore the causality between symptom and fault in the context of fault diagnosis in rotating machinery. We introduce data mining into fault diagnosis and provide a formal definition of causal diagnosis rule based on statistic test. A general framework for diagnosis rule discovery based on causality is provided and a simple implementation is explored with the purpose of providing some enlightenment to the application of causality discovery in fault diagnosis of rotating machinery.

Age-related differences in implicit and explicit racial biases in Cameroonians.

2021 ◽  
Vol 57 (3) ◽  
pp. 386-396
Author(s):  
Miao Qian ◽  
Gail D. Heyman ◽  
Paul C. Quinn ◽  
Francoise A. Messi ◽  
Genyue Fu ◽  
...  
Keyword(s):  
Age Related ◽  
Racial Biases ◽  
Implicit And Explicit

scholarly journals Parallel Robot Translational Performance Evaluation through Direction-Selective Index (DSI)

2011 ◽  
Vol 2011 ◽  
pp. 1-14 ◽  
Author(s):  
G. Boschetti ◽  
R. Rosa ◽  
A. Trevisani
Keyword(s):  
Performance Evaluation ◽  
Performance Index ◽  
General Framework ◽  
Dynamic Performance ◽  
Parallel Manipulators ◽  
Parallel Robot ◽  
Performance Indexes ◽  
Definition Of ◽  
Performance Variations

Performance indexes usually provide global evaluations of robot performances mixing their translational and/or rotational capabilities. This paper proposes a definition of performance index, called direction-selective index (DSI), which has been specifically developed for parallel manipulators and can provide uncoupled evaluations of robot translational capabilities along relevant directions. The DSI formulation is first presented within a general framework, highlighting its relationship with traditional manipulability definitions, and then applied to a family of parallel manipulators (4-RUU) of industrial interest. The investigation is both numerical and experimental and allows highlighting the two chief advantages of the proposed DSIs over more conventional manipulability indexes: not only are DSIs more accurate in predicting the workspace regions where manipulators can best perform translational movements along specific directions, but also they allow foreseeing satisfactorily the dynamic performance variations within the workspace, though being purely kinematic indexes. The experiments have been carried out on an instrumented 4-RUU commercial robot.

scholarly journals Categories as Mathematical Models

2018 ◽  
Author(s):  
David I. Spivak
Keyword(s):  
Dynamical Systems ◽  
Mathematical Modelling ◽  
Mathematical Models ◽  
Category Theory ◽  
Vector Spaces ◽  
Mathematical Objects ◽  
Working Definition ◽  
Modelling Framework ◽  
Categorical Models ◽  
Definition Of

Category theory is presented as a mathematical modelling framework that highlights the relationships between objects, rather than the objects in themselves. A working definition of model is given, and several examples of mathematical objects, such as vector spaces, groups, and dynamical systems, are considered as categorical models.

scholarly journals The data-driven Bulgarian WordNet: BTBWN

2018 ◽  
Author(s):  
Petya Osenova ◽  
Kiril Simov
Keyword(s):  
Information Retrieval ◽  
Machine Translation ◽  
Semantic Information ◽  
Data Driven ◽  
Lexical Resources ◽  
Multilingual Information Retrieval ◽  
Cross Lingual ◽  
Princeton Wordnet ◽  
Word Senses

The data-driven Bulgarian WordNet: BTBWNThe paper presents our work towards the simultaneous creation of a data-driven WordNet for Bulgarian and a manually annotated treebank with semantic information. Such an approach requires synchronization of the word senses in both - syntactic and lexical resources, without limiting the WordNet senses to the corpus or vice versa. Our strategy focuses on the identification of senses used in BulTreeBank, but the missing senses of a lemma also have been covered through exploration of bigger corpora. The identified senses have been organized in synsets for the Bulgarian WordNet. Then they have been aligned to the Princeton WordNet synsets. Various types of mappings are considered between both resources in a cross-lingual aspect and with respect to ensuring maximum connectivity and potential for incorporating the language specific concepts. The mapping between the two WordNets (English and Bulgarian) is a basis for applications such as machine translation and multilingual information retrieval. Oparty na danych WordNet bułgarski: BTBWNW artykule przedstawiono naszą pracę na rzecz jednoczesnej budowy opartego na danych wordnetu dla języka bułgarskiego oraz ręcznie oznaczonego informacjami semantycznymi banku drzew. Takie podejście wymaga uzgodnienia znaczeń słów zarówno w zasobach składniowych, jak i leksykalnych, bez ograniczania znaczeń umieszczanych w wordnecie do tych obecnych w korpusie, jak i odwrotnie. Nasza strategia koncentruje się na identyfikacji znaczeń stosowanych w BulTreeBank, przy czym brakujące znaczenia lematu zostały również zbadane przez zgłębienie większych korpusów. Zidentyfikowane znaczenia zostały zorganizowane w synsety bułgarskiego wordnetu, a następnie powiązane z synsetami Princeton WordNet. Rozmaite rodzaje rzutowań są rozpatrywane pomiędzy obydwoma zasobami w kontekście międzyjęzykowym, a także w odniesieniu do zapewnienia maksymalnej łączności i możliwości uwzględnienia pojęć specyficznych dla języka bułgarskiego. Rzutowanie między dwoma wordnetami (angielskim i bułgarskim) jest podstawą dla aplikacji, takich jak tłumaczenie maszynowe i wielojęzyczne wyszukiwanie informacji.

scholarly journals Noospheric lines in the document studies

2018 ◽  
pp. 92-105
Author(s):  
Galina Shvetsova-Vodka
Keyword(s):  
Semantic Information ◽  
Modern Society ◽  
Information Modeling ◽  
Library Studies ◽  
Definition Of

The author examines the concept of noosphere as applied in the document studies. In 1990ies, Kim Gelman-Vinogradov used in the document studies and introduced the concepts of the ‘noospheric document environment’ and noospheric document memory’. The author also demonstrates how Gelman-Vingradov’s ideas are related with A. V. Sokolov’s interpretation of documentosphere and definition of the document. The concept of nooinformation is examined as applied to the works by Yury Stolyarov and Roman Moltulsky, along with its relation to the documents as the object of library studies and to the concept of social (semantic) information. In the works of bibliography theorists: Galina Gordukalova, V. Fokeev, Alexandra Kumanova, the concept of noosphere is used to characterize document flows, document information, information modeling, and bibliographic compression of information. Arkady Sokolov’s proposal to develop noospherology, and his idea of the libraries; role in promoting the noospheric future and educating homo noospheric, is examined. The author also suggests that the noospheric approach will become a methodological instrument in documentospheric knowledge and will be of practical use for defining the role of libraries in the modern society.

Exploring Implicit and Explicit Racial Bias in OT Professionals

2021 ◽  
Vol 75 (Supplement_2) ◽  
pp. 7512500020p1-7512500020p1
Author(s):  
Alaa Abou-Arab ◽  
Rochelle Mendonca
Keyword(s):  
United States ◽  
Exploratory Study ◽  
Racial Bias ◽  
The United States ◽  
Further Education ◽  
Negative Evaluation ◽  
Racial Biases ◽  
Implicit And Explicit ◽  
Primary Author

Abstract Date Presented 04/13/21 Racial bias is defined as the negative evaluation of a group and its members relative to another and can exist on explicit and implicit levels. This is an exploratory study to examine the presence of implicit and explicit racial bias among OT professionals across the United States. The results (N = 201) highlight the presence of implicit and explicit racial biases among OT professionals in the United States and the need for further education on racial bias. Primary Author and Speaker: Alaa Abou-Arab Additional Authors and Speakers: Alee Leteria, Kristina Zanayed, and Susanne Higgins

Sign in / Sign up

Export Citation Format

Share Document