Google Research, Brain Team（谷歌研究院，大脑团队（注：此处“Brain Team”为谷歌内部团队名称，按原文提取））
Daniel Adiwardana, Minh-Thang Luong, David R. So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu, Quoc V. Le
We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is simply trained to minimize perplexity of the next token. We also propose a human evaluation metric called Sensibleness and Specificity Average (SSA), which captures key elements of a human-like multi-turn conversation. Our experiments show strong correlation between perplexity and SSA. The fact that the best perplexity end-to-end trained Meena scores high on SSA (72% on multi-turn evaluation) suggests that a human-level SSA of 86% is potentially within reach if we can better optimize perplexity. Additionally, the full version of Meena (with a filtering mechanism and tuned decoding) scores 79% SSA, 23% higher in absolute SSA than the existing chatbots we evaluated.
National Taiwan University（国立台湾大学）；Stanford University（斯坦福大学）；Intel Labs（英特尔实验室）
Most chatbot literature that focuses on improving the fluency and coherence of a chatbot, is dedicated to making chatbots more human-like. However, very little work delves into what really separates humans from chatbots -- humans intrinsically understand the effect their responses have on the interlocutor and often respond with an intention such as proposing an optimistic view to make the interlocutor feel better. This paper proposes an innovative framework to train chatbots to possess human-like intentions. Our framework includes a guiding chatbot and an interlocutor model that plays the role…
In recent times, a large number of people have been involved in establishing their own businesses. Unlike humans, chatbots can serve multiple customers at a time, are available 24/7 and reply in less than a fraction of a second. Though chatbots perform well in task-oriented activities, in most cases they fail to understand personalized opinions, statements or even queries which later impact the organization for poor service management. Lack of understanding capabilities in bots disinterest humans to continue conversations with them. Usually, chatbots give absurd responses when they are unable …
Sichuan University（四川大学）；University of Science and Technology of China（中国科学技术大学）
Human evaluation is becoming a necessity to test the performance of Chatbots. However, off-the-shelf settings suffer the severe reliability and replication issues partly because of the extremely high diversity of criteria. It is high time to come up with standard criteria and exact definitions. To this end, we conduct a through investigation of 105 papers involving human evaluation for Chatbots. Deriving from this, we propose five standard criteria along with precise definitions.
School of Computer Science University of Lincoln（林肯大学计算机学院）；Artificial Intelligence Research Group Samsung Electronics（三星电子人工智能研究组）
Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead of infinite actions, and a simple but promising reward function based on human-likeness scores derived from human-human dialogue data. We train Deep Reinforcement Learning (DRL) agents using chitchat data in raw text---without any manual annotations. Experimental results using different splits of training data report the following. First, that our agents le…
University Of Rochester（罗切斯特大学）；Microsoft（微软）；Beijing Film Academy（北京电影学院）
As the wide adoption of intelligent chatbot in human daily life, user demands for such systems evolve from basic task-solving conversations to more casual and friend-like communication. To meet the user needs and build emotional bond with users, it is essential for social chatbots to incorporate more human-like and advanced linguistic features. In this paper, we investigate the usage of a commonly used rhetorical device by human -- metaphor for social chatbot. Our work first designs a metaphor generation framework, which generates topic-aware and novel figurative sentences. By embedding the fr…
Open-domain chatbots are supposed to converse freely with humans without being restricted to a topic, task or domain. However, the boundaries and/or contents of open-domain conversations are not clear. To clarify the boundaries of "openness", we conduct two studies: First, we classify the types of "speech events" encountered in a chatbot evaluation data set (i.e., Meena by Google) and find that these conversations mainly cover the "small talk" category and exclude the other speech event categories encountered in real life human-human communication. Second, we conduct a small-scale pilot study …
University College Dublin（都柏林大学）；Swansea University（斯旺西大学）；Bat Camp（蝙蝠营地）
Chatbots are popular machine partners for task-oriented and social interactions. Human-human computer-mediated communication research has explored how people express their gender and sexuality in online social interactions, but little is known about whether and in what way chatbots do the same. We conducted semi-structured interviews with 5 text-based conversational agents to explore this topic Through these interviews, we identified 6 common themes around the expression of gender and sexual identity: identity description, identity formation, peer acceptance, positive reflection, uncomfortable…
Apart from the coherence and fluency of responses, an empathetic chatbot emphasizes more on people's feelings. By considering altruistic behaviors between human interaction, empathetic chatbots enable people to get a better interactive and supportive experience. This study presents a framework whereby several empathetic chatbots are based on understanding users' implied feelings and replying empathetically for multiple dialogue turns. We call these chatbots CheerBots. CheerBots can be retrieval-based or generative-based and were finetuned by deep reinforcement learning. To respond in an empath…
Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses when interacting with real users. This phenomenon might mainly result from the deficiency of annotated human-human conversations and the misalignment with human preference. In this paper, we propose a novel and efficient approach Diamante to boost the open-domain chatbot, where two kinds of human feedback (including explicit demonstration and implicit preference) are collected and leveraged. By asking annotators to select or amend the model-ge…
Customer service is a setting that calls for empathy in live human agent responses. Recent advances have demonstrated how open-domain chatbots can be trained to demonstrate empathy when responding to live human utterances. We show that a blended skills chatbot model that responds to customer queries is more likely to resemble actual human agent response if it is trained to recognize emotion and exhibit appropriate empathy, than a model without such training. For our analysis, we leverage a Twitter customer service dataset containing several million customer<->agent dialog examples in customer …
University of Lincoln（林肯大学）；Samsung Research（三星研究院）
Trainable chatbots that exhibit fluent and human-like conversations remain a big challenge in artificial intelligence. Deep Reinforcement Learning (DRL) is promising for addressing this challenge, but its successful application remains an open question. This article describes a novel ensemble-based approach applied to value-based DRL chatbots, which use finite action sets as a form of meaning representation. In our approach, while dialogue actions are derived from sentence clustering, the training datasets in our ensemble are derived from dialogue clustering. The latter aim to induce specialis…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent Inc（腾讯公司）
A good open-domain chatbot should avoid presenting contradictory responses about facts or opinions in a conversational session, known as its consistency capacity. However, evaluating the consistency capacity of a chatbot is still challenging. Employing human judges to interact with chatbots on purpose to check their capacities is costly and low-efficient, and difficult to get rid of subjective bias. In this paper, we propose the Addressing Inquiries about History (AIH), an efficient and practical framework for the consistency evaluation. At the conversation stage, AIH attempts to address appro…
IBM Research（IBM研究院）；New York University（纽约大学）；Johns Hopkins Bloomberg School of Public Health（约翰斯·霍普金斯大学布隆伯格公共卫生学院）
Public trust in medical information is crucial for successful application of public health policies such as vaccine uptake. This is especially true when the information is offered remotely, by chatbots, which have become increasingly popular in recent years. Here, we explore the challenging task of human-bot turn-level trust classification. We rely on a recently released data of observationally-collected (rather than crowdsourced) dialogs with VIRA chatbot, a COVID-19 Vaccine Information Resource Assistant. These dialogs are centered around questions and concerns about COVID-19 vaccines, where…
Human interactions and human-computer interactions are strongly influenced by style as well as content. Adding a persona to a chatbot makes it more human-like and contributes to a better and more engaging user experience. In this work, we propose a design for a chatbot that captures the "style" of Star Trek by incorporating references from the show along with peculiar tones of the fictional characters therein. Our Enterprise to Computer bot (E2Cbot) treats Star Trek dialog style and general dialog style differently, using two recurrent neural network Encoder-Decoder models. The Star Trek dialo…
University of California, Davis（加州大学戴维斯分校）；Columbia University（哥伦比亚大学）
Humans are increasingly interacting with machines through language, sometimes in contexts where the user may not know they are talking to a machine (like over the phone or a text chatbot). We aim to understand how system designers and researchers might allow their systems to confirm its non-human identity. We collect over 2,500 phrasings related to the intent of ``Are you a robot?". This is paired with over 2,500 adversarially selected utterances where only confirming the system is non-human would be insufficient or disfluent. We compare classifiers to recognize the intent and discuss the prec…
Conventionally, generation of natural language for dialogue agents may be viewed as a statistical learning problem: determine the patterns in human-provided data and generate appropriate responses with similar statistical properties. However, dialogue can also be regarded as a goal directed process, where speakers attempt to accomplish a specific task. Reinforcement learning (RL) algorithms are designed specifically for solving such goal-directed problems, but the most direct way to apply RL -- through trial-and-error learning in human conversations, -- is costly. In this paper, we study how o…
In this work we explore a deep learning-based dialogue system that generates sarcastic and humorous responses from a conversation design perspective. We trained a seq2seq model on a carefully curated dataset of 3000 question-answering pairs, the core of our mean, grumpy, sarcastic chatbot. We show that end-to-end systems learn patterns very quickly from small datasets and thus, are able to transfer simple linguistic structures representing abstract concepts to unseen settings. We also deploy our LSTM-based encoder-decoder model in the browser, where users can directly interact with the chatbot…
In this work, we present the Chatbot Interaction with Artificial Intelligence (CI-AI) framework as an approach to the training of deep learning chatbots for task classification. The intelligent system augments human-sourced data via artificial paraphrasing in order to generate a large set of training data for further classical, attention, and language transformation-based learning approaches for Natural Language Processing. Human beings are asked to paraphrase commands and questions for task identification for further execution of a machine. The commands and questions are split into training a…
This paper reports the findings of a study conducted on the application of an on-line human-computer dialog system with natural language (chatbot) on the teaching of foreign languages. A keywords-based human-computer dialog system makes it possible that the user could chat with the computer using a natural language, i.e. in English or in German to some extent. So an experiment has been made using this system online to work as a chat partner with the users learning the foreign languages. Dialogs between the users and the chatbot are collected. Findings indicate that the dialogs between the huma…
Recent work building open-domain chatbots has demonstrated that increasing model size improves performance. On the other hand, latency and connectivity considerations dictate the move of digital assistants on the device. Giving a digital assistant like Siri, Alexa, or Google Assistant the ability to discuss just about anything leads to the need for reducing the chatbot model size such that it fits on the user's device. We demonstrate that low parameter models can simultaneously retain their general knowledge conversational abilities while improving in a specific domain. Additionally, we propos…
This paper describes the development of Microsoft XiaoIce, the most popular social chatbot in the world. XiaoIce is uniquely designed as an AI companion with an emotional connection to satisfy the human need for communication, affection, and social belonging. We take into account both intelligent quotient (IQ) and emotional quotient (EQ) in system design, cast human-machine social chat as decision-making over Markov Decision Processes (MDPs), and optimize XiaoIce for long-term user engagement, measured in expected Conversation-turns Per Session (CPS). We detail the system architecture and key …
Zurich University of Applied Sciences (ZHAW)（苏黎世应用科技大学）；University of the Basque Country (UPV/EHU)（巴斯克地区大学）；National Distance Education University (UNED)（国家远程教育大学）；Synapse Développement（Synapse Développement（Synapse 发展公司））
The lack of time-efficient and reliable evaluation methods hamper the development of conversational dialogue systems (chatbots). Evaluations requiring humans to converse with chatbots are time and cost-intensive, put high cognitive demands on the human judges, and yield low-quality results. In this work, we introduce \emph{Spot The Bot}, a cost-efficient and robust evaluation framework that replaces human-bot conversations with conversations between bots. Human judges then only annotate for each entity in a conversation whether they think it is human or not (assuming there are humans participa…
Aalto University（阿尔托大学）；University of Helsinki（赫尔辛基大学）
Creating open-domain chatbots requires large amounts of conversational data and related benchmark tasks to evaluate them. Standardized evaluation tasks are crucial for creating automatic evaluation metrics for model development; otherwise, comparing the models would require resource-expensive human evaluation. While chatbot challenges have recently managed to provide a plethora of such resources for English, resources in other languages are not yet available. In this work, we provide a starting point for Finnish open-domain chatbot research. We describe our collection efforts to create the Fin…
Norwegian University of Science and Technology（挪威科技大学）
Innovation is a key component in trying new solutions for the students to learn efficiently and in ways that correspond to their own experience, where chatbots are one of these new solutions. One of the main problem that chatbots face today is to mimic human language, where they try to find the best answer to an input, which is not how a human conversation usually works, rather taking into account the previous messages and building onto them. Extreme programming methodology was chosen to use integrate ChatterBot, Pyside2, web scraping and Tampermonkey into Blackboard as a test case. Problems o…
Supporting Student Decisions on Learning Recommendations: An LLM-Based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoring
Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI. The traditional approach of information-sharing topic handlers is balanced with a focus on opinion-oriented exchanges that Emora delivers, and new conversational abilities are developed that support dialogues that consist of a collaborative understanding and learning process of the partner's life experiences. We present a curated dialogue system t…
Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted biases. We investigate a variety of methods to mitigate these issues in the context of open-domain generative dialogue models. We introduce a new human-and-model-in-the-loop framework for both training safer models and for evaluating them, as well as a novel method to distill safety considerations inside generative models without the use of an external classifier at deployment time. We conduct experiments comparing the…
East China Normal University（华东师范大学）；Shanghai Jiao Tong University（上海交通大学）
Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching …
Characterizing Delusional Spirals through Human-LLM Chat Logs
Stanford University（斯坦福大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Chicago（芝加哥大学）；Independent Researcher（独立研究者）；Harvard Belfer Center（哈佛贝尔弗中心）；University of Minnesota（明尼苏达大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
University of Notre Dame（圣母大学）；University of California, Irvine（加州大学欧文分校）；Georgia Institute of Technology（佐治亚理工学院）；Rensselaer Polytechnic Institute（伦斯勒理工学院）；University of Washington（华盛顿大学）；IBM Research（IBM研究院）
Despite its benefits for children's skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions. While recent advances made AI generation of questions from stories possible, the fully-automated approach excludes parent involvement, disregards educational goals, and underoptimizes for child engagement. Informed by need-finding interviews and participatory design (PD) results, we developed StoryBuddy, an AI-enabled syste…
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心）；Hong Kong University of Science and Technology（香港科技大学）
Politically sensitive topics are still a challenge for open-domain chatbots. However, dealing with politically sensitive content in a responsible, non-partisan, and safe behavior way is integral for these chatbots. Currently, the main approach to handling political sensitivity is by simply changing such a topic when it is detected. This is safe but evasive and results in a chatbot that is less engaging. In this work, as a first step towards a politically safe chatbot, we propose a group of metrics for assessing their political prudence. We then conduct political prudence analysis of various ch…
