Continuous learning mechanism of NLU-ML models boosted by human feedback

Abinaya, G.; Ranjan, Gyan; Karthik, Pullalarevu

doi:10.1109/iccids.2019.8862102

Search citation statements

Order By: Relevance

Paper Sections

Select...

Arquitecturas Basadas En Nlp1

Future Work1

Citation Types

Supporting

Mentioning

Contrasting

Unclassified

Year Published

2021

Publication Types

Select...

Other2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Actualmente el NLP y especialmente el NLU lidian con algunos problemas, en este caso se orientarán estos problemas en el contexto de lo chatbots ya que es el tema de interés de este proyecto [66]:…”

Section: Arquitecturas Basadas En Nlpunclassified

Serverless computing: economic and architectural impact

Adzic¹,

Chatley

2017

Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering

124

View full text Add to dashboard Cite

show abstract

Section: Arquitecturas Basadas En Nlpunclassified

Serverless computing: economic and architectural impact

Adzic¹,

Chatley

2017

Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering

124

View full text Add to dashboard Cite

show abstract

“…Individual components of the current pipeline will perform better as a result of these signals being plugged into various pipeline sub-modules. One area of improvement, as proposed by G. Abinaya et al [22], is designing a system capable of ingesting such feedback. The aforementioned structure will include dedicated modules that determine which section of the pipeline feedback should flow into, the cadence at which feedback should be reflected in the module, and the weights that should be assigned to feedback based on its importance, user preferences, and other factors.…”

Section: Future Workmentioning

confidence: 99%

Untitled

2021

IJNLC

View full text Add to dashboard Cite

Question Answering has been a well-researched NLP area over recent years. It has become necessary for users to be able to query through the variety of information available -be it structured or unstructured. In this paper, we propose a Question Answering module which a) can consume a variety of data formats -a heterogeneous data pipeline, which ingests data from product manuals, technical data forums, internal discussion forums, groups, etc. b) addresses practical challenges faced in real-life situations by pointing to the exact segment of the manual or chat threads which can solve a user query c) provides segments of texts when deemed relevant, based on user query and business context. Our solution provides a comprehensive and detailed pipeline that is composed of elaborate data ingestion, data parsing, indexing, and querying modules. Our solution is capable of handling a plethora of data sources such as text, images, tables, community forums, and flow charts. Our studies performed on a variety of business-specific datasets represent the necessity of custom pipelines like the proposed one to solve several real-world document question-answering.

show abstract

Continuous learning mechanism of NLU-ML models boosted by human feedback

Cited by 2 publications

References 2 publications

Serverless computing: economic and architectural impact

Serverless computing: economic and architectural impact

Untitled

Contact Info

Product

Resources

About