Leveraging label hierarchy using transfer and multi-task learning: A case study on patent classification

2021 ◽  
Author(s):  
Segun Taofeek Aroyehun ◽  
Jason Angel ◽  
Navonil Majumder ◽  
Alexander Gelbukh ◽  
Amir Hussain
Keyword(s):  
Patent Classification ◽  
Task Learning

scholarly journals Construction and evaluation of gold standards for patent classification—A case study on quantum computing

2020 ◽  
Vol 61 ◽  
pp. 101961 ◽  
Author(s):  
Steve Harris ◽  
Anthony Trippe ◽  
David Challis ◽  
Nigel Swycher
Keyword(s):  
Quantum Computing ◽  
Patent Classification ◽  
Gold Standards

scholarly journals A Methodology for Evaluation and Distribution of Patent Applications to INPI-BR Patent Examiners: A Case Study in the Electricity Field

2021 ◽  
Author(s):  
Cesar Vianna Moreira Júnior ◽  
Daniel Marques Golodne ◽  
Ricardo Carvalho Rodrigues
Keyword(s):  
Principal Component ◽  
Patent Classification ◽  
Technological Field ◽  
International Patent ◽  
Relevant Variables ◽  
Pca Method ◽  
Patent Applications ◽  
Examination Process

This paper presents the development of a new methodology for evaluation and distribution of patent applications to the examiners at the Brazilian Patent Office considering a specific technological field, represented by classification of the application according to the International Patent Classification (IPC), and the variables corresponding to the volume of data of the application and its complexity for the examination process. After identifying the most relevant variables, such as the Specific Areas of Expertise (ZAE) of the examiners, a mathematical model was developed, including: (a) application of the principal component analysis (PCA) method; (b) calculation of a General Complexity Ratio (IGC); (c) classification into five classes (very light, light, moderate, heavy and very heavy) according to IGC average ranges and standard deviations; (d) implementation of a logic of distribution, compensating very heavy applications with very light ones, and light applications with heavy ones; and (e) calculation of a Distribution Balancing Ratio (IBD), considering the differences between the samples’ medians. The model was validated using a sample of patent applications including, in addition to the identified variables, the time for substantive examination by the examiner. Then, a correlation analysis of the variables with time and a comparison of the classifications according to the time and the IGC generated by the model were carried out. The results obtained showed a high correlation of the IGC with time, above 80%, as well as correct IGC classes in more than 80% of applications. The model proposed herein suggests that the three main relevant variables are: total number of pages, total number of claims, and total number of claim pages.

scholarly journals Gauging a Firm’s Innovative Performance Using an Integrated Structural Index for Patents

2017 ◽  
Vol 1 (1) ◽  
pp. 6-27
Author(s):  
Xiaojun Hu ◽  
Ronald Rousseau
Keyword(s):  
Pharmaceutical Industry ◽  
Structural Index ◽  
Innovative Performance ◽  
Patent Classification ◽  
Innovation Activities ◽  
International Patent ◽  
Nested Case Control ◽  
Structural Indices ◽  
Control Methodology

AbstractPurposeIn this contribution we try to find new indicators to measure characteristics of a firm’s patents and their influence on a company’s profits.Design/methodology/approachWe realize that patent evaluation and influence on a company’s profits is a complicated issue requiring different perspectives. For this reason we design two types of structural h-indices, derived from the International Patent Classification (IPC). In a case study we apply not only basic statistics but also a nested case-control methodology.FindingsThe resulting indicator values based on a large dataset (19,080 patents in total) from the pharmaceutical industry show that the new structural indices are significantly correlated with a firm’s profits.Research limitationsThe new structural index and the synthetic structural index have just been applied in one case study in the pharmaceutical industry.Practical implicationsOur study suggests useful implications for patentometric studies and leads to suggestions for different sized firms to include a healthy research and development (R&D) policy management. The structural h-index can be used to gauge the profits resulting from the innovative performance of a firm’s patent portfolio.Originality/valueTraditionally, the breadth and depth of patents of a firm and their citations are considered separately. This approach, however, does not provide an integrated insight in the major characteristics of a firm’s patents. The Sh(Y) index, proposed in our investigation, can reflect a firm’s innovation activities, its technological breadth, and its influence in an integrated way.

Stimulating idea generation for new product applications

2018 ◽  
Vol 10 (4) ◽  
pp. 454-474 ◽  
Author(s):  
Lorenzo Fiorineschi ◽  
Francesco Saverio Frillici ◽  
Giovanni Gregori ◽  
Federico Rotini
Keyword(s):  
Product Information ◽  
Idea Generation ◽  
New Product ◽  
Step Method ◽  
Content Type ◽  
Patent Classification ◽  
Novel Approach ◽  
International Patent ◽  
New Applications

Purpose This paper aims to provide suggestions for the identification of potential new applications for the existing products and/or technologies. Design/methodology/approach A nine-step method has been developed for extracting information about a product or technology, processing the international patent database (IPD) and extracting useful hints for potential new applications. An academic case study has been used to perform the first application of the proposal. Findings A novel approach for processing IPD aimed at supporting the identification of new opportunities for exploiting existing products/technologies. The case study application shows that the proposal allows to extract potentially useful and non-obvious suggestions for new product applications. Research limitations/implications Although some limits inevitably affect this preliminary version of the proposal, important hints for future developments have been inferred for a more comprehensive exploitation of both the firm internal knowledge and the suggestions provided by the international patent database. Practical implications The achieved results can support firms in expanding market opportunities for their products or technologies. Originality/value The proposed approach offers a new structured path for stimulating idea generation for new product applications, by exploiting product information and the cooperative patent classification.

scholarly journals Loss-Balanced Task Weighting to Reduce Negative Transfer in Multi-Task Learning

2019 ◽  
Vol 33 ◽  
pp. 9977-9978 ◽  
Author(s):  
Shengchao Liu ◽  
Yingyu Liang ◽  
Anthony Gitter
Keyword(s):  
Computational Chemistry ◽  
Task Performance ◽  
Negative Transfer ◽  
Learning Models ◽  
Improve Performance ◽  
Single Task ◽  
Task Learning ◽  
Model Training

In settings with related prediction tasks, integrated multi-task learning models can often improve performance relative to independent single-task models. However, even when the average task performance improves, individual tasks may experience negative transfer in which the multi-task model’s predictions are worse than the single-task model’s. We show the prevalence of negative transfer in a computational chemistry case study with 128 tasks and introduce a framework that provides a foundation for reducing negative transfer in multitask models. Our Loss-Balanced Task Weighting approach dynamically updates task weights during model training to control the influence of individual tasks.

scholarly journals An approach framework of transfer learning, adversarial training and hierarchical multi-task learning - a case study of disinformation detection with offensive text

2022 ◽  
Vol 2161 (1) ◽  
pp. 012049
Author(s):  
Shravan Chandra ◽  
Bhaskarjyoti Das
Keyword(s):  
Transfer Learning ◽  
Error Feedback ◽  
Task Learning ◽  
Learning Tasks ◽  
Linguistic Patterns ◽  
Social Media Platforms ◽  
Adversarial Training ◽  
Hierarchical Nature ◽  
Definition Of

Abstract With society going online and disinformation getting accepted as a phenomena that we have to live with, there is a growing need to automatically detect offensive text on modern social media platforms. But the lack of enough balanced labeled data, constantly evolving socio-linguistic patterns and ever-changing definition of offensive text make it a challenging task. This is a common pattern witnessed in all disinformation detection tasks such as detection of propaganda, rumour, fake news, hate etc. The work described in this paper improves upon the existing body of techniques by bringing in an approach framework that can surpass the existing benchmarks. Firstly, it addresses the imbalanced and insufficient nature of available labeled dataset. Secondly, learning using relates tasks through multi-task learning has been proved to be an effective approach in this domain but it has the unrealistic requirement of labeled data for all related tasks. The framework presented here suitably uses transfer learning in lieu of multi-task learning to address this issue. Thirdly, it builds a model explicitly addressing the hierarchical nature in the taxonomy of disinformation being detected as that delivers a stronger error feedback to the learning tasks. Finally, the model is made more robust by adversarial training. The work presented in this paper uses offensive text detection as a case study and shows convincing results for the chosen approach. The framework adopted can be easily replicated in other similar learning tasks facing a similar set of challenges.

The Genesis and Internal Dynamics of El Salvador's People's Revolutionary Army, 1970–1976

2014 ◽  
Vol 38 (01) ◽  
pp. 102-129
Author(s):  
ALBERTO MARTÍN ÁLVAREZ ◽  
EUDALD CORTINA ORERO
Keyword(s):  
Latin America ◽  
El Salvador ◽  
Early Years ◽  
Left Wing ◽  
Internal Dynamics ◽  
Internal Coherence ◽  
The 1960S

AbstractUsing interviews with former militants and previously unpublished documents, this article traces the genesis and internal dynamics of the Ejército Revolucionario del Pueblo (People's Revolutionary Army, ERP) in El Salvador during the early years of its existence (1970–6). This period was marked by the inability of the ERP to maintain internal coherence or any consensus on revolutionary strategy, which led to a series of splits and internal fights over control of the organisation. The evidence marshalled in this case study sheds new light on the origins of the armed Salvadorean Left and thus contributes to a wider understanding of the processes of formation and internal dynamics of armed left-wing groups that emerged from the 1960s onwards in Latin America.

Culture and the plasticity of perception

2020 ◽  
Vol 43 ◽  
Author(s):  
Michael Lifshitz ◽  
T. M. Luhrmann
Keyword(s):  
Cultural Context ◽  
Sensory Experience ◽  
Cultural Learning ◽  
The World

Abstract Culture shapes our basic sensory experience of the world. This is particularly striking in the study of religion and psychosis, where we and others have shown that cultural context determines both the structure and content of hallucination-like events. The cultural shaping of hallucinations may provide a rich case-study for linking cultural learning with emerging prediction-based models of perception.

Dual systems for all: Higher-order, role-based relational reasoning as a uniquely derived feature of human cognition

2019 ◽  
Vol 42 ◽  
Author(s):  
Daniel J. Povinelli ◽  
Gabrielle C. Glorioso ◽  
Shannon L. Kuznar ◽  
Mateja Pavlic
Keyword(s):  
Temporal Reasoning ◽  
Higher Order ◽  
Important Case ◽  
Human Cognition ◽  
Relational Reasoning ◽  
Dual Systems ◽  
First Order ◽  
Reasoning System ◽  
Role Based

Abstract Hoerl and McCormack demonstrate that although animals possess a sophisticated temporal updating system, there is no evidence that they also possess a temporal reasoning system. This important case study is directly related to the broader claim that although animals are manifestly capable of first-order (perceptually-based) relational reasoning, they lack the capacity for higher-order, role-based relational reasoning. We argue this distinction applies to all domains of cognition.

Sign in / Sign up

Export Citation Format

Share Document