When is ACL's Deadline? A Scientific Conversational Agent

TL;DR

UKP-ATHENA is a conversational agent that helps NLP researchers access scientific literature, authors, and conference info through natural language, maintaining context and integrating multiple sources.

Contribution

This paper introduces UKP-ATHENA, a novel conversational agent that unifies access to scientific NLP research, authors, and conferences via natural language understanding and multi-source integration.

Findings

Responds to 45% of user intents with natural language queries

Achieves 37% information coverage in user interactions

Supports easy extension with new skills and domains

Abstract

Our conversational agent UKP-ATHENA assists NLP researchers in finding and exploring scientific literature, identifying relevant authors, planning or post-processing conference visits, and preparing paper submissions using a unified interface based on natural language inputs and responses. UKP-ATHENA enables new access paths to our swiftly evolving research area with its massive amounts of scientific information and high turnaround times. UKP-ATHENA's responses connect information from multiple heterogeneous sources which researchers currently have to explore manually one after another. Unlike a search engine, UKP-ATHENA maintains the context of a conversation to allow for efficient information access on papers, researchers, and conferences. Our architecture consists of multiple components with reference implementations that can be easily extended by new skills and domains. Our user-based evaluation shows that UKP-ATHENA already responds 45% of different formulations of defined intents with 37% information coverage rate.