Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface
Anupam Purwar, Rahul Sundar

TL;DR
This paper introduces a keyword-augmented retrieval framework that enhances information retrieval efficiency and cost-effectiveness, especially when integrated with speech interfaces, by reducing reliance on large language models for context discovery.
Contribution
The authors develop a novel keyword-based retrieval system that reduces inference time and costs, enabling efficient speech interface integration for knowledge retrieval tasks.
Findings
Reduces retrieval time and cost using keyword augmentation.
Enables seamless speech interface integration.
Improves context discovery efficiency.
Abstract
Retrieving answers in a quick and low cost manner without hallucinations from a combination of structured and unstructured data using Language models is a major hurdle. This is what prevents employment of Language models in knowledge retrieval automation. This becomes accentuated when one wants to integrate a speech interface on top of a text based knowledge retrieval system. Besides, for commercial search and chat-bot applications, complete reliance on commercial large language models (LLMs) like GPT 3.5 etc. can be very costly. In the present study, the authors have addressed the aforementioned problem by first developing a keyword based search framework which augments discovery of the context from the document to be provided to the LLM. The keywords in turn are generated by a relatively smaller LLM and cached for comparison with keywords generated by the same smaller LLM against the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Speech and dialogue systems · Natural Language Processing Techniques
MethodsMulti-Head Attention · Attention Is All You Need · Cosine Annealing · Adam · Residual Connection · Layer Normalization · Discriminative Fine-Tuning · Softmax · Dropout · Linear Layer
