Published models
Evaluating language
beyond the surface.
These models focus on specific questions in natural language processing: how well a query is formed, and how much meaningful variety a paraphrase adds. The linked model cards contain the technical details, usage examples and available files.
Text classification / RoBERTa
Query well-formedness scoring
This model scores grammatical correctness and sentence completeness. It is sensitive to capitalization, helping distinguish a complete, well-formed query from fragments or grammatically inconsistent text.
The model card describes applications in chatbot query validation, educational tools and content review. It includes an example using Hugging Face Transformers to score several sentences together.
The score describes the form of the language. Factual correctness and task relevance require separate evaluation.
Apache 2.0Text classificationGoogle Wellformed Query dataset
Read the model card and usage examples ↗Model citation · DOI 10.57967/hf/1980 ↗
Text ranking / Paraphrase evaluation
Paraphrase diversity ranking
This model distinguishes semantic variation from surface-level wording changes in paraphrases. It supports workflows that generate several candidate paraphrases and then rank them for diversity.
The model card recommends first filtering for semantic similarity using a model trained on natural language inference or semantic textual similarity, then applying the diversity ranker. That separates preserving the source meaning from assessing useful variation.
The public examples reference the Salesken model namespace. The model card provides the original training context and usage guidance.
Apache 2.0Text rankingParaphrase evaluation
Read the model card and usage examples ↗
More published experiments in language generation, context resolution and text processing are available on my Hugging Face profile.
Technical writing
Questions from
building AI products.
My articles explore language understanding, training data, language generation and the relationship between AI research and practical products. Each title below links to its original publication.
Active.Ai / 2018
AI hype, benchmark results and the practical work of building products from research.
Natural language understanding / 2019
A look at understanding in conversational systems and the challenges involved in building a chatbot.
Conversational AI / 2020
Training datasets and their role in the development and adoption of conversational AI.
Natural language generation / 2020
Exploring whether an open-domain dialogue model can be fine-tuned for more specific language generation tasks.
Haptik / Conversations on AI
Brain–computer interfaces, bionics and nonverbal signals as possible directions for virtual assistants.
Industry perspectives
Research and
enterprise context.
My career spans conversational banking at Active.Ai, language understanding at Reliance Jio Haptik, sales intelligence at Salesken, applied AI at Ola Krutrim and AI and data platforms at Tata Group. That background connects the technical work on this page with enterprise products and AI leadership.
Past contributions to Forbes Technology Council cover technology and business topics. The historical contributor profile lists my Salesken role at the time.