Creating chatbots to behave like real people is important in terms of believability. Errors in general chatbots and chatbots that follow a rough persona have been studied, but those in chatbots that behave like real people have not been thoroughly investigated. We collected a large amount of user interactions of a generation-based chatbot trained from large-scale dialogue data of a specific character, i.e., target person, and analyzed errors related to that person. We found that person-specific errors can be divided into two types: errors in attributes and those in relations, each of which can be divided into two levels: self and other. The correspondence with an existing taxonomy of errors was also investigated, and person-specific errors that should be addressed in the future were clarified.
With the increase in the number of published academic papers, growing expectations have been placed on research related to supporting the writing process of scientific papers. Recently, research has been conducted on various tasks such as citation worthiness (judging whether a sentence requires citation), citation recommendation, and citation-text generation. However, since each task has been studied and evaluated using data that has been independently developed, it is currently impossible to verify whether such tasks can be successfully pipelined to effective use in scientific-document writing. In this paper, we first define a series of tasks related to scientific-document writing that can be pipelined. Then, we create a dataset of academic papers that can be used for the evaluation of each task as well as a series of these tasks. Finally, using the dataset, we evaluate the tasks of citation worthiness and citation recommendation as well as both of these tasks integrated. The results of our evaluations show that the proposed approach is promising.
This paper proposes a taxonomy of errors in chat-oriented dialogue systems. Previously, two taxonomies were proposed; one is theory-driven and the other data-driven. The former suffers from the fact that dialogue theories for human conversation are often not appropriate for categorizing errors made by chat-oriented dialogue systems. The latter has limitations in that it can only cope with errors of systems for which we have data. This paper integrates these two taxonomies to create a comprehensive taxonomy of errors in chat-oriented dialogue systems. We found that, with our integrated taxonomy, errors can be reliably annotated with a higher Fleiss’ kappa compared with the previously proposed taxonomies.
Endowing a task-oriented dialogue system with adaptiveness to user personality can greatly help improve the performance of a dialogue task. However, such a dialogue system can be practically challenging to implement, because it is unclear how user personality influences dialogue task performance. To explore the relationship between user personality and dialogue task performance, we enrolled participants via crowdsourcing to first answer specified personality questionnaires and then chat with a dialogue system to accomplish assigned tasks. A rule-based dialogue system on the prevalent Multi-Domain Wizard-of-Oz (MultiWOZ) task was used. A total of 211 participants’ personalities and their 633 dialogues were collected and analyzed. The results revealed that sociable and extroverted people tended to fail the task, whereas neurotic people were more likely to succeed. We extracted features related to user dialogue behaviors and performed further analysis to determine which kind of behavior influences task performance. As a result, we identified that average utterance length and slots per utterance are the key features of dialogue behavior that are highly correlated with both task performance and user personality.
We are studying a cooperation style where multiple speakers can provide both advanced dialogue services and operator education. We focus on a style in which two operators interact with a user by pretending to be a single operator. For two operators to effectively act as one, each must adjust his/her conversational content and timing to the other. In the process, we expect each operator to experience the conversational content of his/her partner as if it were his/her own, creating efficient and effective learning of the other’s skill. We analyzed this educational effect and examined whether dialogue services can be successfully provided by collecting travel guidance dialogue data from operators who give travel information to users. In this paper, we report our preliminary results on dialogue content and user satisfaction of operators and users.
This paper concerns the problem of realizing consistent personalities in neural conversational modeling by using user generated question-answer pairs as training data. Using the framework of role play-based question answering, we collected single-turn question-answer pairs for particular characters from online users. Meta information was also collected such as emotion and intimacy related to question-answer pairs. We verified the quality of the collected data and, by subjective evaluation, we also verified their usefulness in training neural conversational models for generating utterances reflecting the meta information, especially emotion.
To provide a better discussion experience in current argumentative dialogue systems, it is necessary for the user to feel motivated to participate, even if the system already responds appropriately. In this paper, we propose a method that can smoothly introduce argumentative dialogue by inserting an initial discourse, consisting of question-answer pairs concerning personality. The system can induce interest of the users prior to agreement or disagreement during the main discourse. By disclosing their interests, the users will feel familiarity and motivation to further engage in the argumentative dialogue and understand the system’s intent. To verify the effectiveness of a question-answer dialogue inserted before the argument, a subjective experiment was conducted using a text chat interface. The results suggest that inserting the question-answer dialogue enhances familiarity and naturalness. Notably, the results suggest that women more than men regard the dialogue as more natural and the argument as deepened, following an exchange concerning personality.
This paper proposes a fully neural network based dialogue-context online end-of-turn detection method that can utilize long-range interactive information extracted from both speaker’s utterances and collocutor’s utterances. The proposed method combines multiple time-asynchronous long short-term memory recurrent neural networks, which can capture speaker’s and collocutor’s multiple sequential features, and their interactions. On the assumption of applying the proposed method to spoken dialogue systems, we introduce speaker’s acoustic sequential features and collocutor’s linguistic sequential features, each of which can be extracted in an online manner. Our evaluation confirms the effectiveness of taking dialogue context formed by the speaker’s utterances and collocutor’s utterances into consideration.
Having consistent personalities is important for chatbots if we want them to be believable. Typically, many question-answer pairs are prepared by hand for achieving consistent responses; however, the creation of such pairs is costly. In this study, our goal is to collect a large number of question-answer pairs for a particular character by using role play-based question-answering in which multiple users play the roles of certain characters and respond to questions by online users. Focusing on two famous characters, we conducted a large-scale experiment to collect question-answer pairs by using real users. We evaluated the effectiveness of role play-based question-answering and found that, by using our proposed method, the collected pairs lead to good-quality chatbots that exhibit consistent personalities.
This paper proposes an adversarial training method for the multi-task and multi-lingual joint modeling needed for utterance intent classification. In joint modeling, common knowledge can be efficiently utilized among multiple tasks or multiple languages. This is achieved by introducing both language-specific networks shared among different tasks and task-specific networks shared among different languages. However, the shared networks are often specialized in majority tasks or languages, so performance degradation must be expected for some minor data sets. In order to improve the invariance of shared networks, the proposed method introduces both language-specific task adversarial networks and task-specific language adversarial networks; both are leveraged for purging the task or language dependencies of the shared networks. The effectiveness of the adversarial training proposal is demonstrated using Japanese and English data sets for three different utterance intent classification tasks.
This paper is an initial study on multi-task and multi-lingual joint learning for lexical utterance classification. A major problem in constructing lexical utterance classification modules for spoken dialogue systems is that individual data resources are often limited or unbalanced among tasks and/or languages. Various studies have examined joint learning using neural-network based shared modeling; however, previous joint learning studies focused on either cross-task or cross-lingual knowledge transfer. In order to simultaneously support both multi-task and multi-lingual joint learning, our idea is to explicitly divide state-of-the-art neural lexical utterance classification into language-specific components that can be shared between different tasks and task-specific components that can be shared between different languages. In addition, in order to effectively transfer knowledge between different task data sets and different language data sets, this paper proposes a partially-shared modeling method that possesses both shared components and components specific to individual data sets. We demonstrate the effectiveness of proposed method using Japanese and English data sets with three different lexical utterance classification tasks.
This paper presents an initial study on hyperspherical query likelihood models (QLMs) for information retrieval (IR). Our motivation is to naturally utilize pre-trained word embeddings for probabilistic IR. To this end, key idea is to directly leverage the word embeddings as random variables for directional probabilistic models based on von Mises-Fisher distributions which are familiar to cosine distances. The proposed method enables us to theoretically take semantic similarities between document and target queries into consideration without introducing heuristic expansion techniques. In addition, this paper reveals relationships between hyperspherical QLMs and conventional QLMs. Experiments show document retrieval evaluation results in which a hyperspherical QLM is compared to conventional QLMs and document distance metrics using word or document embeddings.
In dialogue systems, conveying understanding results of user utterances is important because it enables users to feel understood by the system. However, it is not clear what types of understanding results should be conveyed to users; some utterances may be offensive and some may be too commonsensical. In this paper, we explored the effect of conveying understanding results of user utterances in a chat-oriented dialogue system by an experiment using human subjects. As a result, we found that only certain types of understanding results, such as those related to a user’s permanent state, are effective to improve user satisfaction. This paper clarifies the types of understanding results that can be safely uttered by a system.
This paper describes a hierarchical neural network we propose for sentence classification to extract product information from product documents. The network classifies each sentence in a document into attribute and condition classes on the basis of word sequences and sentence sequences in the document. Experimental results showed the method using the proposed network significantly outperformed baseline methods by taking semantic representation of word and sentence sequential data into account. We also evaluated the network with two different product domains (insurance and tourism domains) and found that it was effective for both the domains.
Dialogue breakdown detection is a promising technique in dialogue systems. To promote the research and development of such a technique, we organized a dialogue breakdown detection challenge where the task is to detect a system’s inappropriate utterances that lead to dialogue breakdowns in chat. This paper describes the design, datasets, and evaluation metrics for the challenge as well as the methods and results of the submitted runs of the participants.
This paper proposes a method for extracting Daily Changing Words (DCWs), words that indicate which questions are real-time dependent. Our approach is based on two types of template matching using time and named entity slots from large size corpora and adding simple filtering methods from news corpora. Extracted DCWs are utilized for detecting and sorting real-time dependent questions. Experiments confirm that our DCW method achieves higher accuracy in detecting real-time dependent questions than existing word classes and a simple supervised machine learning approach.
This paper describes a dialogue data collection experiment and resulting corpus for dialogues between a senior mobile journalist and a junior cub reporter back at the office. The purpose of the dialogue is for the mobile journalist to collect background information in preparation for an interview or on-the-site coverage of a breaking story. The cub reporter has access to text archives that contain such background information. A unique aspect of these dialogues is that they capture information-seeking behavior for an open-ended task against a large unstructured data source. Initial analyses of the corpus show that the experimental design leads to real-time, mixedinitiative, highly interactive dialogues with many interesting properties.