We propose a dialog system that creates responses based on a large-scale dialog corpus retrieved from Twitter and real-time crowd-sourcing. Instead of using complex dialog management, our system replies with the utterance from the database that is most similar to the user input. We also propose a real-time crowdsourcing framework for handling the case in which there is no adequate response in the database.

Dialog System Using Real-Time Crowdsourcing and Twitter Large-Scale Corpus

Recently emerged intelligent assistants on smartphones and home electronics (e.g., Siri and Alexa) can be seen as novel hybrids of domain-specific task-oriented spoken dialogue systems and open-domain non-task-oriented ones. To realize such hybrid dialogue systems, this paper investigates determining whether or not a user is going to have a chat with the system. To address the lack of benchmark datasets for this task, we construct a new dataset consisting of 15; 160 utterances collected from the real log data of a commercial intelligent assistant (and will release the dataset to facilitate future research activity). In addition, we investigate using tweets and Web search queries for handling open-domain user utterances, which characterize the task of chat detection. Experiments demonstrated that, while simple supervised methods are effective, the use of the tweets and search queries further improves the F1-score from 86.21 to 87.53.

Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems

This paper proposes an unsupervised spoken language understanding (SLU) framework for a multi-domain dialog system. Our unsupervised SLU framework applies a non-parametric Bayesian approach to dialog acts, intents and slot entities, which are the components of a semantic frame. The proposed approach reduces the human effort necessary to obtain a semantically annotated corpus for dialog system development. In this study, we analyze clustering results using various evaluation metrics for four dialog corpora. We also introduce a multi-domain dialog system that uses the unsupervised SLU framework. We argue that our unsupervised approach can help overcome the annotation acquisition bottleneck in developing dialog systems. To verify this claim, we report a dialog system evaluation, in which our method achieves competitive results in comparison with a system that uses a manually annotated corpus. In addition, we conducted several experiments to explore the effect of our approach on reducing development costs. The results show that our approach be helpful for the rapid development of a prototype system and reducing the overall development costs.

Unsupervised Spoken Language Understanding for a Multi-Domain Dialog System

This paper aims to find errors that lead to dialogue breakdowns in chat-oriented dialogue systems. We collected chat dialogue data, annotated them with dialogue breakdown labels, and collected comments describing the error that led to the breakdown. By mining the comments, we first identified error types. Then, we calculated the correlation between an error type and the degree of dialogue breakdown it incurred, quantifying its impact on dialogue breakdown. This is the first study to quantitatively analyze error types and their effect in chat-oriented dialogue systems.

/pdf/fatal-or-not-finding-errors-that-lead-to-dialogue-breakdowns-1znxr1bwgk.pdf

Fatal or not? Finding errors that lead to dialogue breakdowns in chat-oriented dialogue systems

Feedback on electricity usage for home energy management: A social experiment in a local village of cold region

Intelligent buildings are getting data-centric - they archive the historical records of motion detectors, power usages, HVAC statuses, weather, and any other information in order to improve their control strategies. The engineering cost of installation and maintenance of such systems should be minimized as the system owner has to operate them for several decades: i.e., the lifetime of the building. However, there are several design pitfalls that multiply such engineering costs, which make the operation heavy burden. This paper identifies those pitfalls and presents technical challenges that enable lightweight installation and maintenance. We, then, design facility information access protocol (FIAP) for data-centric building automation systems. We carried out FIAP-based system integration into a building of the University of Tokyo, and demonstrate that FIAP enables incremental installation for wide varieties of applications with small engineering costs.

/pdf/fiap-facility-information-access-protocol-for-data-centric-523pfk4eik.pdf

FIAP: Facility information access protocol for data-centric building automation systems

The current problem in building a conversational model from Twitter data is the scarcity of long conversations. According to our statistics, more than 90% of conversations in Twitter are composed of just two tweets. Previous work has utilized only conversations lasting longer than three tweets for dialogue modeling so that more than a single interaction can be successfully modeled. This paper verifies, by experiment, that two-tweet exchanges alone can lead to conversational models that are comparable to those made from longer-tweet conversations. This finding leverages the value of Twitter as a dialogue corpus and opens the possibility of better conversational modeling using Twitter data.

/pdf/building-a-conversational-model-from-two-tweets-41ilctmqou.pdf

Building a conversational model from two-tweets

Unsupervised clustering of utterances can be useful for the modeling of dialogue acts for dialogue applications. Previously, the Chinese restaurant process (CRP), a non-parametric Bayesian method, has been introduced and has shown promising results for the clustering of utterances in dialogue. This paper newly introduces the infinite HMM, which is also a nonparametric Bayesian method, and verifies its effectiveness. Experimental results in two dialogue domains show that the infinite HMM, which takes into account the sequence of utterances in its clustering process, significantly outperforms the CRP. Although the infinite HMM outperformed other methods, we also found that clustering complex dialogue data, such as humanhuman conversations, is still hard when compared to humanmachine dialogues. Index Terms: Unsupervised clustering, Nonparametric Bayesian methods, Chinese restaurant process, Infinite HMM

/pdf/unsupervised-clustering-of-utterances-using-non-parametric-3lvsx5wm6i.pdf

Hirohito Inagaki

Papers

FIAP: Facility information access protocol for data-centric building automation systems

Building a conversational model from two-tweets

Unsupervised Clustering of Utterances using Non-parametric Bayesian Methods