# Ericson: An Interactive Open-Domain Conversational Search Agent

arXiv: https://arxiv.org/abs/2304.02233 · HTML: https://mlsanity.com/paper/2304.02233/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 5 Apr 2023.

## Builds on (most cited first, 6 of 6)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [Artificial Intelligence MArkup Language: A Brief Tutorial](https://mlsanity.com/paper/1307.3091/) (2013)
- [Learning through Dialogue Interactions by Asking Questions](https://mlsanity.com/paper/1612.04936/) (2016)
- [Attention with Intention for a Neural Network Conversation Model](https://mlsanity.com/paper/1510.08565/) (2015)

## Built on by (most cited first, 1 of 1)

- [Making a Long Story Short in Conversation Modeling](https://mlsanity.com/paper/2402.00143/) (2024)

## Abstract (arXiv)

Open-domain conversational search (ODCS) aims to provide valuable, up-to-date information, while maintaining natural conversations to help users refine and ultimately answer information needs. However, creating an effective and robust ODCS agent is challenging. In this paper, we present a fully functional ODCS system, Ericson, which includes state-of-the-art question answering and information retrieval components, as well as intent inference and dialogue management models for proactive question refinement and recommendations. Our system was stress-tested in the Amazon Alexa Prize, by engaging in live conversations with thousands of Alexa users, thus providing empirical basis for the analysis of the ODCS system in real settings. Our interaction data analysis revealed that accurate intent classification, encouraging user engagement, and careful proactive recommendations contribute most to the users satisfaction. Our study further identifies limitations of the existing search techniques, and can serve as a building block for the next generation of ODCS agents.