ELIZA—a computer program for the study of natural language communication between man and machine

By Joseph Weizenbaum. 1966

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Experience Grounds Language (2020, background): “Framing, such as suggesting that a chatbot speaks English as a second language (Sample and Hern, 2014), can create the appearance of genuine content where there is none (Weizenbaum, 1966).”
CoQA: A Conversational Question Answering Challenge (2018, background): “Due to the conversational nature of questions and answers, our work can also be defined as an instantiation of a dialog problem (Weizenbaum, 1966; Cohen et al., 1982; Young et al., 2013; Serban et al., 2018).”
Alignment of Language Agents (2021, methodology): “We focus on language agents that have been trained from data, in contrast to pattern-matching systems like ELIZA (Weizenbaum, 1966).”
Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data (2020, background): “There are many anecdotes, going all the way back to ELIZA (Weizenbaum, 1966), of systems that managed to fool their users into”
Neural Approaches to Conversational AI (2018, neutral): “ystem. The empathy model provides a context-aware strategy that can drive the conversation when needed. 6.3 Chatbots There have been publicly-available conversational systems going back many decades (Weizenbaum, 1966; Colby, 1975). However, these precursors of today’s chatbot systems relied heavily ”
A Deep Reinforcement Learning Chatbot (2017, background): “Early work on dialogue systems (Weizenbaum 1966, Colby 1981, Aust et al. 1995, McGlashan et al. 1992, Simpson & Eraser 1993) were based mainly on states and rules hand-crafted by human experts.”
The Design and Implementation of XiaoIce, an Empathetic Social Chatbot (2018, methodology): “Early conversational systems, such as Eliza [1], Parry [2], and Alice [3], were designed to mimic human behavior in a text-based conversation, hence to pass the Turing Test within a controlled scope.”
Conversational AI: The Science Behind the Alexa Prize (2018, methodology): “…or use a hybrid approach with complementary modules (e.g. retrieval using generative models, generative models to create templates for a retrieval or rule-based module, etc.) Most of the teams used AIML, ELIZA (Weizenbaum, 1966), or Alicebot (Alicebot, 2017) for rule-based and templated responses.”
On the Binding Problem in Artificial Neural Networks (2020, background): “…rules to interpret written English; And knowledge bases such as semantic networks (networks of concepts and relations) that could be used to answer basic questions (Weizenbaum, 1966), solve basic algebra word problems (Bobrow, 1964), or control simple virtual block worlds (Winograd, 1971).”
On Evaluating and Comparing Conversational Agents (2018, background): “While modern chatbots have progressed since ELIZA (Weizenbaum, 1966), current state-of-the-art systems are still a long way from being able to have coherent, natural conversations with humans (Levesque, 2017).”
Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations (2020, methodology): “While ELIZA-like systems (Weizenbaum et al., 1966) attempt this via templated repetition of user phrases, they lack the naturalness and depth of real human conversations.”
Challenges in Building Intelligent Open-domain Dialog Systems (2019, background): “Early dialog systems such as Eliza [103], Parry [8], and Alice [95], despite being instrumental to significantly advancing machine intelligence, worked well only in constrained environments.”
Patient and Consumer Safety Risks When Using Conversational Assistants for Medical Information: An Observational Study of Siri, Alexa, and Google Assistant (2018, background): “The earliest such program is the ELIZA system, developed to simulate a Rogerian psychotherapist [18].”
From Eliza to XiaoIce: challenges and opportunities with social chatbots (2018, methodology): “Nevertheless, many users believed they were talking to a real person when Eliza first came out.”
Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner (2016, neutral): “This test is evidently not valid, as theoretically, ’thinking’ is not a well defined psychological construct, but rather a polysemous folk psychology concept, and empirically, it is rather easy to fool human observers using rather simplistic text manipulation rules (see ELIZA, Weizenbaum, 1966).”
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset (2019, background): “The NLU and NLG components of dialog systems starting from the early research work (Weizenbaum, 1966) to the present commercially available personal assistants largely rely on rule-based systems.”
SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems (2022, background): “One of the early examples is Weizenbaum (1983)’s famous chatbot ELIZA, which simply parroted back patterns of what users just said (Bassett, 2019).”
Response Generation by Context-aware Prototype Editing (2018, background): “Research on chatbots goes back to the 1960s when ELIZA was designed (Weizenbaum 1966) with a huge amount of 1 conditional setting means the editor should consider the context (dialogue history) except in a response itself in the revision.”