Open-domain Dialogue Research Articles

Anna: A Dapper Open-Domain Dialogue Agent Based on a Joint Attention Network

Anna: A Dapper Open-Domain Dialogue Agent Based on a Joint Attention Network

Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study.

Open-domain dialog generation, which is a crucial component of artificial intelligence, is an essential and challenging problem. In this article, we present a personalized dialog system, which leverages the advantages of multitask learning and reinforcement learning for personalized dialogue generation (MRPDG). Specifically, MRPDG consists of two subtasks: 1) an author profiling module that recognizes user characteristics from the input sentence (auxiliary task) and 2) a personalized dialog generation system that generates informative, grammatical, and coherent responses with reinforcement learning algorithms (primary task). Three kinds of rewards are proposed to generate high-quality conversations. We investigate the effectiveness of three widely used reinforcement learning methods [i.e., Q-learning, policy gradient, and actor-critic (AC) algorithm] in a personalized dialog generation system and demonstrate that the AC algorithm achieves the best results on the underlying framework. Comprehensive experiments are conducted to evaluate the performance of the proposed model on two real-life data sets. Experimental results illustrate that MRPDG is able to produce high-quality personalized dialogs for users with different characteristics. Quantitatively, the proposed model can achieve better performance than the compared methods across different evaluation metrics, such as the human evaluation, BiLingual Evaluation Understudy (BLEU), and perplexity.

PONE

Open-domain generative dialogue systems have attracted considerable attention over the past few years. Currently, how to automatically evaluate them is still a big challenge. As far as we know, there are three kinds of automatic evaluations for open-domain generative dialogue systems: (1) Word-overlap-based metrics; (2) Embedding-based metrics; (3) Learning-based metrics. Due to the lack of systematic comparison, it is not clear which kind of metrics is more effective. In this article, we first measure systematically all kinds of metrics to check which kind is best. Extensive experiments demonstrate that learning-based metrics are the most effective evaluation metrics for open-domain generative dialogue systems. Moreover, we observe that nearly all learning-based metrics depend on the negative sampling mechanism, which obtains extremely imbalanced and low-quality samples to train a score model. To address this issue, we propose a novel learning-based metric that significantly improves the correlation with human judgments by using augmented PO sitive samples and valuable NE gative samples, called PONE. Extensive experiments demonstrate that PONE significantly outperforms the state-of-the-art learning-based evaluation method. Besides, we have publicly released the codes of our proposed metric and state-of-the-art baselines. 1

KsponSpeech: Korean Spontaneous Speech Corpus for Automatic Speech Recognition

This paper introduces a large-scale spontaneous speech corpus of Korean, named KsponSpeech. This corpus contains 969 h of general open-domain dialog utterances, spoken by about 2000 native Korean speakers in a clean environment. All data were constructed by recording the dialogue of two people freely conversing on a variety of topics and manually transcribing the utterances. The transcription provides a dual transcription consisting of orthography and pronunciation, and disfluency tags for spontaneity of speech, such as filler words, repeated words, and word fragments. This paper also presents the baseline performance of an end-to-end speech recognition model trained with KsponSpeech. In addition, we investigated the performance of standard end-to-end architectures and the number of sub-word units suitable for Korean. We investigated issues that should be considered in spontaneous speech recognition in Korean. KsponSpeech is publicly available on an open data hub site of the Korea government.

Knowledge Augmented Dialogue Generation with Divergent Facts Selection

The end-to-end open-domain dialogue system is a challenging task since the existing neural models suffer from the issue of trivial responses. Employing background knowledge as a major solution, has been proven to be effective to improve the responses quality. However, less attention was paid to the selection of the appropriate knowledge in scenarios where the utterance subject drifts between two partners, which could prohibit the model from learning to access knowledge correctly. In this paper, we propose a novel Knowledge Augmented Dialogue Generation (KADG) model to facilitate both knowledge selection and incorporation in open-domain dialogue systems. The core components of KADG consist of Divergent Knowledge Selector (DKS) and Knowledge Aware Decoder (KAD). DKS performs a one-hop subject reasoning over knowledge by pre-optimizing each knowledge candidate with inferred drift clue. Drift clue implies the potential subjects association of the current conversation and is served to bridge the subject gap in the knowledge selection. Thereafter, KAD makes full use of this selected knowledge to generate responses contextual coherently as well as knowledgeably. Comprehensive experiments on a newly released knowledge-grounded conversation dataset Wizard-of-Wikipedia have verified the superiority of our model than previous baselines and shown that our method can refer to the knowledge properly and generate diverse and informative responses.

Evaluating Dialogue Generation Systems via Response Selection

Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation. We focus on evaluating response generation systems via response selection. To evaluate systems properly via response selection, we propose the method to construct response selection test sets with well-chosen false candidates. Specifically, we propose to construct test sets filtering out some types of false candidates: (i) those unrelated to the ground-truth response and (ii) those acceptable as appropriate responses. Through experiments, we demonstrate that evaluating systems via response selection with the test sets developed by our method correlates more strongly with human evaluation, compared with widely used automatic evaluation metrics such as BLEU.

Conversational Intelligence Challenge: Accelerating Research with Crowd Science and Open Source

Development of conversational systems is one of the most challenging tasks in natural language processing, and it is especially hard in the case of open‐domain dialogue. The main factors that hinder progress in this area are lack of training data and difficulty of automatic evaluation. Thus, to reliably evaluate the quality of such models, one needs to resort to time‐consuming and expensive human evaluation. We tackle these problems by organizing the Conversational Intelligence Challenge (ConvAI) — open competition of dialogue systems. Our goals are threefold: to work out a good design for human evaluation of open‐domain dialogue, to grow open‐source code base for conversational systems, and to harvest and publish new datasets. Over the course of ConvAI1 and ConvAI2 competitions, we developed a framework for evaluation of chatbots in messaging platforms and used it to evaluate over 30 dialogue systems in two conversational tasks — discussion of short text snippets from Wikipedia and personalized small talk. These large‐scale evaluation experiments were performed by recruiting volunteers as well as paid workers. As a result, we succeeded in collecting a dataset of around 5,000 long meaningful human‐to‐bot dialogues and got many insights into the organization of human evaluation. This dataset can be used to train an automatic evaluation model or to improve the quality of dialogue systems. Our analysis of ConvAI1 and ConvAI2 competitions shows that the future work in this area should be centered around the more active participation of volunteers in the assessment of dialogue systems. To achieve that, we plan to make the evaluation setup more engaging.

Challenges in Building Intelligent Open-domain Dialog Systems

There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI [33]. Unlike traditional task-oriented bots, an open-domain dialog system aims to establish long-term connections with users by satisfying the human need for communication, affection, and social belonging. This article reviews the recent work on neural approaches that are devoted to addressing three challenges in developing such systems: semantics , consistency , and interactiveness . Semantics requires a dialog system to not only understand the content of the dialog but also identify users’ emotional and social needs during the conversation. Consistency requires the system to demonstrate a consistent personality to win users’ trust and gain their long-term confidence. Interactiveness refers to the system’s ability to generate interpersonal responses to achieve particular social goals such as entertainment and conforming. The studies we select to present in this survey are based on our unique views and are by no means complete. Nevertheless, we hope that the discussion will inspire new research in developing more intelligent open-domain dialog systems.

Hierarchical Reinforcement Learning for Open-Domain Dialog

Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead to the generation of inappropriate, biased, or offensive text. Reinforcement Learning (RL) is a powerful framework that could potentially address these issues, for example by allowing a dialog model to optimize for reducing toxicity and repetitiveness. However, previous approaches which apply RL to open-domain dialog generation do so at the word level, making it difficult for the model to learn proper credit assignment for long-term conversational rewards. In this paper, we propose a novel approach to hierarchical reinforcement learning (HRL), VHRL, which uses policy gradients to tune the utterance-level embedding of a variational sequence model. This hierarchical approach provides greater flexibility for learning long-term, conversational rewards. We use self-play and RL to optimize for a set of human-centered conversation metrics, and show that our approach provides significant improvements – in terms of both human evaluation and automatic metrics – over state-of-the-art dialog models, including Transformers.

Improving Knowledge-Aware Dialogue Generation via Knowledge Base Question Answering

Neural network models usually suffer from the challenge of incorporating commonsense knowledge into the open-domain dialogue systems. In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation. In addition, we propose a response guiding attention and a multi-step decoding strategy to steer our model to focus on relevant features for response generation. Experiments on two benchmark datasets demonstrate that our model has robust superiority over compared methods in generating informative and fluent dialogues. Our code is available at https://github.com/siat-nlp/TransDG.

Predictive Engagement: An Efficient Metric for Automatic Evaluation of Open-Domain Dialogue Systems

User engagement is a critical metric for evaluating the quality of open-domain dialogue systems. Prior work has focused on conversation-level engagement by using heuristically constructed features such as the number of turns and the total time of the conversation. In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, predictive engagement, for automatic evaluation of open-domain dialogue systems. Our experiments demonstrate that (1) human annotators have high agreement on assessing utterance-level engagement scores; (2) conversation-level engagement scores can be predicted from properly aggregated utterance-level engagement scores. Furthermore, we show that the utterance-level engagement scores can be learned from data. These scores can be incorporated into automatic evaluation metrics for open-domain dialogue systems to improve the correlation with human judgements. This suggests that predictive engagement can be used as a real-time feedback for training better dialogue models.

A Dynamic Emotional Session Generation Model Based on Seq2Seq and a Dictionary-Based Attention Mechanism

With the development of deep learning, the method of large-scale dialogue generation based on deep learning has received extensive attention. The current research has aimed to solve the problem of the quality of generated dialogue content, but has failed to fully consider the emotional factors of generated dialogue content. In order to solve the problem of emotional response in the open domain dialogue system, we proposed a dynamic emotional session generation model (DESG). On the basis of the Seq2Seq (sequence-to-sequence) framework, the model abbreviation incorporates a dictionary-based attention mechanism that encourages the substitution of words in response with synonyms in emotion dictionaries. Meanwhile, in order to improve the model, internal emotion regulator and emotion classifier mechanisms are introduced in order to build a large-scale emotion-session generation model. Experimental results show that our DESG model can not only produce an appropriate output sequence in terms of content (related grammar) for a given post and emotion category, but can also express the expected emotional response explicitly or implicitly.

Insufficient Data Can Also Rock! Learning to Converse Using Smaller Data with Augmentation

Recent successes of open-domain dialogue generation mainly rely on the advances of deep neural networks. The effectiveness of deep neural network models depends on the amount of training data. As it is laboursome and expensive to acquire a huge amount of data in most scenarios, how to effectively utilize existing data is the crux of this issue. In this paper, we use data augmentation techniques to improve the performance of neural dialogue models on the condition of insufficient data. Specifically, we propose a novel generative model to augment existing data, where the conditional variational autoencoder (CVAE) is employed as the generator to output more training data with diversified expressions. To improve the correlation of each augmented training pair, we design a discriminator with adversarial training to supervise the augmentation process. Moreover, we thoroughly investigate various data augmentation schemes for neural dialogue system with generative models, both GAN and CVAE. Experimental results on two open corpora, Weibo and Twitter, demonstrate the superiority of our proposed data augmentation model.

RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems

Open-domain human-computer conversation has been attracting increasing attention over the past few years. However, there does not exist a standard automatic evaluation metric for open-domain dialog systems; researchers usually resort to human annotation for model evaluation, which is time- and labor-intensive. In this paper, we propose RUBER, a Referenced metric and Unreferenced metric Blended Evaluation Routine, which evaluates a reply by taking into consideration both a groundtruth reply and a query (previous user-issued utterance). Our metric is learnable, but its training does not require labels of human satisfaction. Hence, RUBER is flexible and extensible to different datasets and languages. Experiments on both retrieval and generative dialog systems show that RUBER has a high correlation with human annotation, and that RUBER has fair transferability over different datasets.

Open-Domain Neural Conversational Agents: The Step Towards Artificial General Intelligence

Development of conversational agents started half century ago and since then it has transformed into a technology that is accessible in various aspects in everyday life. This paper presents a survey current state-of-the-art in the open domain neural conversational agent research and future research directions towards Artificial General Intelligence (AGI) creation. In order to create a conversational agent which is able to pass the Turing Test, numerous research efforts are focused on open-domain dialogue system. This paper will present latest research in domain of Neural Network reasoning and logical association, sentiment analysis and real-time learning approaches applied to open domain neural conversational agents. As an effort to provide future research directions, current cuttingedge approaches applied to open domain neural conversational agents, current cutting-edge approaches in rationale generation and the state-of-the-art research directions in alternative training methods will be discussed in this paper.

Survey of evaluation methods for dialogue systems}{Survey of evaluation methods for dialogue systems

This paper introduces the history of dialogue systems and their evaluation methods. The evaluation methods are categorized as either task-oriented dialogue systems or open domain dialogue systems. This paper investigates and summarizes the different methods of evaluating dialogue systems, analyzes the pros and cons of the different methods, discusses the emphasis of each method, and presents the progress of recent research for the two categories. For task-oriented dialogue systems, this paper introduces the recent research results of Steve Young. In addition, this paper sums up several widely used evaluation approaches. The evaluation methods for open domain chatting systems are explored from two angles: objective index evaluation and simulated artificial scoring. The various indices and different research ideas are analyzed and introduced as well. Finally, through summarizing and analyzing classical evaluation methods of dialogue systems as well as the newer evaluation methods based on neural network models, this study aims to predict developmental trends in evaluation methods for dialogue systems.

Automatic Summarization of Open-Domain Multiparty Dialogues in Diverse Genres

Automatic summarization of open-domain spoken dialogues is a relatively new research area. This article introduces the task and the challenges involved and motivates and presents an approach for obtaining automatic-extract summaries for human transcripts of multiparty dialogues of four different genres, without any restriction on domain. We address the following issues, which are intrinsic to spoken-dialogue summarization and typically can be ignored when summarizing written text such as news wire data: (1) detection and removal of speech disfluencies; (2) detection and insertion of sentence boundaries; and (3) detection and linking of cross-speaker information units (question-answer pairs). A system evaluation is performed using a corpus of 23 dialogue excerpts with an average duration of about 10 minutes, comprising 80 topical segments and about 47,000 words total. The corpus was manually annotated for relevant text spans by six human annotators. The global evaluation shows that for the two more informal genres, our summarization system using dialogue-specific components significantly outperforms two baselines: (1) a maximum-marginal-relevance ranking algorithm using TF*IDF term weighting, and (2) a LEAD baseline that extracts the first n words from a text.

Introduction to the Special Issue on Summarization

generation based on rhetorical structure extraction. In Proceedings of the International Conference on Computational Linguistics, Kyoto, Japan, pages 344–348. Otterbacher, Jahna, Dragomir R. Radev, and Airong Luo. 2002. Revisions that improve cohesion in multi-document summaries: A preliminary study. In ACL Workshop on Text Summarization, Philadelphia. Papineni, K., S. Roukos, T. Ward, and W-J. Zhu. 2001. BLEU: A method for automatic evaluation of machine translation. Research Report RC22176, IBM. Radev, Dragomir, Simone Teufel, Horacio Saggion, Wai Lam, John Blitzer, Arda Celebi, Hong Qi, Elliott Drabek, and Danyu Liu. 2002. Evaluation of text summarization in a cross-lingual information retrieval framework. Technical Report, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, June. Radev, Dragomir R., Hongyan Jing, and Malgorzata Budzikowska. 2000. Centroid-based summarization of multiple documents: Sentence extraction, utility-based evaluation, and user studies. In ANLP/NAACL Workshop on Summarization, Seattle, April. Radev, Dragomir R. and Kathleen R. McKeown. 1998. Generating natural language summaries from multiple on-line sources. Computational Linguistics, 24(3):469–500. Rau, Lisa and Paul Jacobs. 1991. Creating segmented databases from free text for text retrieval. In Proceedings of the 14th Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, New York, pages 337–346. Saggion, Horacio and Guy Lapalme. 2002. Generating indicative-informative summaries with SumUM. Computational Linguistics, 28(4), 497–526. Salton, G., A. Singhal, M. Mitra, and C. Buckley. 1997. Automatic text structuring and summarization. Information Processing & Management, 33(2):193–207. Silber, H. Gregory and Kathleen McCoy. 2002. Efficiently computed lexical chains as an intermediate representation for automatic text summarization. Computational Linguistics, 28(4), 487–496. Sparck Jones, Karen. 1999. Automatic summarizing: Factors and directions. In I. Mani and M. T. Maybury, editors, Advances in Automatic Text Summarization. MIT Press, Cambridge, pages 1–13. Strzalkowski, Tomek, Gees Stein, J. Wang, and Bowden Wise. 1999. A robust practical text summarizer. In I. Mani and M. T. Maybury, editors, Advances in Automatic Text Summarization. MIT Press, Cambridge, pages 137–154. Teufel, Simone and Marc Moens. 2002. Summarizing scientific articles: Experiments with relevance and rhetorical status. Computational Linguistics, 28(4), 409–445. White, Michael and Claire Cardie. 2002. Selecting sentences for multidocument summaries using randomized local search. In Proceedings of the Workshop on Automatic Summarization (including DUC 2002), Philadelphia, July. Association for Computational Linguistics, New Brunswick, NJ, pages 9–18. Witbrock, Michael and Vibhu Mittal. 1999. Ultra-summarization: A statistical approach to generating highly condensed non-extractive summaries. In Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Berkeley, pages 315–316. Zechner, Klaus. 2002. Automatic summarization of open-domain multiparty dialogues in diverse genres. Computational Linguistics, 28(4), 447–485.