Projects & Patents

Issued Determining user affinities for content generation applications. US Patent App 17/447,908 (granted in 2021-09-16).
Issued Semantics-aware hybrid encoder for improved related conversations. US Patent App 17/454,445 (granted in 2021-11-10).

Issued System and methods for neural topic modeling using topic attention networks. US Patent App 17/644,856 (granted in 2021-12-17).

Filed Hyperbolic and Interpretable Hierarchical Topic Models.
Filed Enable marketers increase visitor engagement on B2B websites via GenAI powered conversational systems.
Filed A Novel Perspective on Content Personalisation: Tailoring Examples within Content to Resonate.
Filed A Novel method and apparatus for text-guided style transfer.

Content Gap with Session History

Session Transformer

In the rapidly evolving landscape of Generative AI, identifying which content to generate remains a challenge for marketers. Traditional analytics and SEO methods fall short in capturing the complete user journey and context. We introduce a novel framework that leverages users’ session his- tory to pinpoint gaps in existing content. We train a transformer-based model on data about what users have read and how long they spent reading it. We utilise this model to identify cluster of content attributes that users find relevant but are missing in the current repository, signifying a con- tent gap. This gap can be addressed by generating more such content, enhancing user engagement and retention.

Link to Proposal: [LINK]
Work done in collaboration with Shripad Deshmukh and Tanay Anand.

Document Recommendation

Language Model Patent Adobe Product

Product 1: Identify similar user queries on the Adobe Support Community platform (similar to Stack Exchange), with the goal of reducing the number of new queries posted for an existing one. We observed a 22% increase in user’s engagement and a 20% decrease in new posts.

Product 2: We designed a workflow to recommend blogs using search signals and different types of user interactions with posts on the Adobe Marketo Nation Community Platform. In the first 8 weeks of launch, we observed a 40% increase in engagement.

Product 3: With this new cutting-edge approach to surfacing content recommendations on Marketing Nation Community, users receive recommended content based on their interactions with Marketo's email programs with the ultimate goal of increasing adoption and Community engagement. We observed a 30% increase in new users’ engagement with the Marketo offerings.

Conversational Systems

Language Models Patent Adobe Product

[1] Sales summary generation: A concise summary for the sales agent with call to action for their leads. A fact-checking algorithm with Natural Language Inference is added to ensure that summaries and action items generated are not hallucinated. We created a golden dataset for benchmarking models on this task.

[2] Answering visitor questions: In this we use Retrieval Augmented Answer Generation (RAG) to find answer for the visitor question.

Routing user queries to experts.

Topic Models Patent Adobe Product

Adobe Support Community is a trusted online platform for Adobe customers to discuss queries about products, similar to Stack Overflow. These forums have millions of queries and it becomes difficult for the experts to find posts that they can answer. This calls for efficient and quick routing of user queries to interested experts. We proposed a routing framework, where we develop expert profiles using topic models and match it with the post topics.

Automatic topic labeling with Hyperbolic Geometry

Topic Models [CODE]

The topics generated by topic models often have words inconsistent with the theme a particular topic is representing, thus, making it difficult to interpret such topics. In this project, I worked on a solution for the automatic labeling of topics using concept hierarchies.

Page updated

Google Sites

Report abuse