Facebook AI Research（脸书人工智能研究院）；AI2 Incubator（AI2孵化器）
Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston
Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we show that other ingredients are important for a high-performing chatbot. Good conversation requires a number of skills that an expert conversationalist blends in a seamless way: providing engaging talking points and listening to their partners, and displaying knowledge, empathy and personality appropriately, while maintaining a consistent persona. We show that large scale models can learn these skills when given appropriate training data and choice of generation strategy. We build variants of these recipes with 90M, 2.7B and 9.4B parameter models, and make our models and code publicly available. Human evaluations show our best models are superior to existing approaches in multi-turn dialogue in terms of engagingness and humanness measurements. We then discuss the limitations of this work by analyzing failure cases of our models.
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…
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…
Visual representation of data like charts and tables can be challenging to understand for readers. Previous work showed that combining visualisations with text can improve the communication of insights in static contexts, but little is known about interactive ones. In this work we present an NLG chatbot that processes natural language queries and provides insights through a combination of charts and text. We apply it to nutrition, a domain communication quality is critical. Through crowd-sourced evaluation we compare the informativeness of our chatbot against traditional, static diet-apps. We …
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…
Jožef Stefan Institute（约泽夫·斯蒂芬研究所）；International Postgraduate School Jožef Stefan（约泽夫·斯蒂芬国际研究生院）
Although recipe data are very easy to come by nowadays, it is really hard to find a complete recipe dataset - with a list of ingredients, nutrient values per ingredient, and per recipe, allergens, etc. Recipe datasets are usually collected from social media websites where users post and publish recipes. Usually written with little to no structure, using both standardized and non-standardized units of measurement. We collect six different recipe datasets, publicly available, in different formats, and some including data in different languages. Bringing all of these datasets to the needed format…
Chatbot is a technology that is used to mimic human behavior using natural language. There are different types of Chatbot that can be used as conversational agent in various business domains in order to increase the customer service and satisfaction. For any business domain, it requires a knowledge base to be built for that domain and design an information retrieval based system that can respond the user with a piece of documentation or generated sentences. The core component of a Chatbot is Natural Language Understanding (NLU) which has been impressively improved by deep learning methods. But…
Viterbi School of Engineering, University of Southern California（南加州大学维特比工程学院）
One challenge for evaluating current sequence- or dialogue-level chatbots, such as Empathetic Open-domain Conversation Models, is to determine whether the chatbot performs in an emotionally consistent way. The most recent work only evaluates on the aspects of context coherence, language fluency, response diversity, or logical self-consistency between dialogues. This work proposes training an evaluator to determine the emotional consistency of chatbots.
In this paper, we introduce a methodology for predicting intent and slots of a query for a chatbot that answers career-related queries. We take a multi-staged approach where both the processes (intent-classification and slot-tagging) inform each other's decision-making in different stages. The model breaks down the problem into stages, solving one problem at a time and passing on relevant results of the current stage to the next, thereby reducing search space for subsequent stages, and eventually making classification and tagging more viable after each stage. We also observe that relaxing rule…
Artificial Intelligence Application Research Center, Huawei Technologies（华为技术有限公司人工智能应用研究中心）
In this paper, we describe a data enhancement method for developing Emily, an emotion-affective open-domain chatbot. The proposed method is based on explicitly modeling positively transitioned (PT) sentiment data from multi-turn dialogues. We construct a dialogue corpus with PT sentiment data and will release it for public use. By fine-tuning a pretrained dialogue model using the produced PT-enhanced dialogues, we are able to develop an emotion-affective open-domain chatbot exhibiting close-to-human performance in various emotion-affective metrics. We evaluate Emily against a few state-of-the-…
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 …
Artificial Intelligence Application Research Center, Huawei Technologies（华为技术有限公司人工智能应用研究中心）
In this paper, we describe approaches for developing Emily, an emotion-affective open-domain chatbot. Emily can perceive a user's negative emotion state and offer supports by positively converting the user's emotion states. This is done by finetuning a pretrained dialogue model upon data capturing dialogue contexts and desirable emotion states transition across turns. Emily can differentiate a general open-domain dialogue utterance with questions relating to personal information. By leveraging a question-answering approach based on knowledge graphs to handle personal information, Emily maintai…
Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant
Czech Technical University in Prague（布拉格捷克技术大学）；National Institute of Mental Health in Prague（布拉格国家精神卫生研究所）；The University of Hong Kong（香港大学）；Shenzhen Mental Health Centre（深圳市精神卫生中心）
To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning. There are two stages involved in the learning process. In the first stage, a coarse-grained generation model is trained to learn response generation under the simplified framework of one-to-one mapping. In the second stage, a fine-grained generative model augmented with latent variables and an evaluation model are further trained to generate diverse responses and to select the best response, respectively. PLATO-2 was trained on both Chinese and English data, whose effect…
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…
Popular conversational agents frameworks such as Alexa Skills Kit (ASK) and Google Actions (gActions) offer unprecedented opportunities for facilitating the development and deployment of voice-enabled AI solutions in various verticals. Nevertheless, understanding user utterances with high accuracy remains a challenging task with these frameworks. Particularly, when building chatbots with large volume of domain-specific entities. In this paper, we describe the challenges and lessons learned from building a large scale virtual assistant for understanding and responding to equipment-related compl…
Text classification problem is a very broad field of study in the field of natural language processing. In short, the text classification problem is to determine which of the previously determined classes the given text belongs to. Successful studies have been carried out in this field in the past studies. In the study, Bidirectional Encoder Representations for Transformers (BERT), which is a frequently preferred method for solving the classification problem in the field of natural language processing, is used. By solving classification problems through a single model to be used in a chatbot a…
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…
We apply sequence-to-sequence model to mitigate the impact of speech recognition errors on open domain end-to-end dialog generation. We cast the task as a domain adaptation problem where ASR transcriptions and original text are in two different domains. In this paper, our proposed model includes two individual encoders for each domain data and make their hidden states similar to ensure the decoder predict the same dialog text. The method shows that the sequence-to-sequence model can learn the ASR transcriptions and original text pair having the same meaning and eliminate the speech recognition…
In recent years, there has been an increase in the number of devices with virtual assistants (e.g: Siri, Google Home, Alexa) in our living rooms and kitchens. As a result of this, these devices receive several queries about recipes. All these queries will contain terms relating to a "recipe-domain" i.e: they will contain dish-names, ingredients, cooking times, dietary preferences etc. Extracting these recipe-relevant aspects from the query thus becomes important when it comes to addressing the user's information need. Our project focuses on extracting ingredients from such plain-text user utte…
Large end-to-end neural open-domain chatbots are becoming increasingly popular. However, research on building such chatbots has typically assumed that the user input is written in nature and it is not clear whether these chatbots would seamlessly integrate with automatic speech recognition (ASR) models to serve the speech modality. We aim to bring attention to this important question by empirically studying the effects of various types of synthetic and actual ASR hypotheses in the dialog history on TransferTransfo, a state-of-the-art Generative Pre-trained Transformer (GPT) based neural open-d…
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））
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-…
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）；Swisscom AG（瑞士电信公司）
Goal-Oriented (GO) Dialogue Systems, colloquially known as goal oriented chatbots, help users achieve a predefined goal (e.g. book a movie ticket) within a closed domain. A first step is to understand the user's goal by using natural language understanding techniques. Once the goal is known, the bot must manage a dialogue to achieve that goal, which is conducted with respect to a learnt policy. The success of the dialogue system depends on the quality of the policy, which is in turn reliant on the availability of high-quality training data for the policy learning method, for instance Deep Rein…
In this paper, we consider mimicking fictional characters as a promising direction for building engaging conversation models. To this end, we present a new practical task where only a few utterances of each fictional character are available to generate responses mimicking them. Furthermore, we propose a new method named Pseudo Dialog Prompting (PDP) that generates responses by leveraging the power of large-scale language models with prompts containing the target character's utterances. To better reflect the style of the character, PDP builds the prompts in the form of dialog that includes the …
Despite the multi-turn open-domain dialogue systems have attracted more and more attention and made great progress, the existing dialogue systems are still very boring. Nearly all the existing dialogue models only provide a response when the user's utterance is accepted. But during daily conversations, humans always decide whether to continue to utter an utterance based on the context. Intuitively, a dialogue model that can control the timing of talking autonomously based on the conversation context can chat with humans more naturally. In this paper, we explore the dialogue system that automat…
Johns Hopkins University（约翰霍普金斯大学）；New York University（纽约大学）
Non-task-oriented dialog models suffer from poor quality and non-diverse responses. To overcome limited conversational data, we apply Simulated Multiple Reference Training (SMRT; Khayrallah et al., 2020), and use a paraphraser to simulate multiple responses per training prompt. We find SMRT improves over a strong Transformer baseline as measured by human and automatic quality scores and lexical diversity. We also find SMRT is comparable to pretraining in human evaluation quality, and outperforms pretraining on automatic quality and lexical diversity, without requiring related-domain dialog dat…
FPT Technology Research Institute（FPT技术研究院）；FPT University（FPT大学）；Vietnam National University（越南国家大学）
This work investigates the task-oriented dialogue problem in mixed-domain settings. We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems. We first show that a specialized state tracking component in multiple domains plays an important role and gives better results than an end-to-end task-oriented dialogue system. We then propose a hybrid system which is able to improve the belief tracking accuracy of about 28% of average absolute point on a standard multi-domain dialogue dataset. These experimental resul…
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）；Swisscom AG（瑞士电信股份公司）
Spoken language understanding (SLU) systems, such as goal-oriented chatbots or personal assistants, rely on an initial natural language understanding (NLU) module to determine the intent and to extract the relevant information from the user queries they take as input. SLU systems usually help users to solve problems in relatively narrow domains and require a large amount of in-domain training data. This leads to significant data availability issues that inhibit the development of successful systems. To alleviate this problem, we propose a technique of data selection in the low-data regime that…
Automatic Speech Recognition (ASR) robustness toward slot entities are critical in e-commerce voice assistants that involve monetary transactions and purchases. Along with effective domain adaptation, it is intuitive that cross utterance contextual cues play an important role in disambiguating domain specific content words from speech. In this paper, we investigate various techniques to improve contextualization, content word robustness and domain adaptation of a Transformer-XL neural language model (NLM) to rescore ASR N-best hypotheses. To improve contextualization, we utilize turn level dia…
General translation models often still struggle to generate accurate translations in specialized domains. To guide machine translation practitioners and characterize the effectiveness of domain adaptation methods under different data availability scenarios, we conduct an in-depth empirical exploration of monolingual and parallel data approaches to domain adaptation of pre-trained, third-party, NMT models in settings where architecture change is impractical. We compare data centric adaptation methods in isolation and combination. We study method effectiveness in very low resource (8k parallel e…
On the Reliability of Large Language Models to Misinformed and Demographically-Informed Prompts
Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；CIMNE（国际数值方法工程中心）；University of Lleida（莱里达大学）；Dalhousie University（达尔豪斯大学）；University of Toronto（多伦多大学）；University of Ottawa（渥太华大学）
EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education
East China Normal University（华东师范大学）；Institute of AI for Education, ECNU（华东师范大学教育人工智能研究院）；Fudan University（复旦大学）；ZhuQingTing Data Technology (Zhejiang) Co., Ltd.（竹蜻蜓数据科技（浙江）有限公司）
We describe and validate a metric for estimating multi-class classifier performance based on cross-validation and adapted for improvement of small, unbalanced natural-language datasets used in chatbot design. Our experiences draw upon building recruitment chatbots that mediate communication between job-seekers and recruiters by exposing the ML/NLP dataset to the recruiting team. Evaluation approaches must be understandable to various stakeholders, and useful for improving chatbot performance. The metric, nex-cv, uses negative examples in the evaluation of text classification, and fulfils three…
