The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Using speech or text to predict articulatory movements can have potential benefits for speech related applications. Many approaches have been proposed to solve the acoustic-to-articulatory inversion problem, which is much more than the exploration for predicting articulatory movements from text. In this paper, we investigate the feasibility of using deep neural network (DNN) for articulartory movement...
This research paper describes the application of linguistic analysis through scaled co-occurrence networks to create visual representations of systematic literature reviews. This approach uses currently available and free tools in this new application. Co-occurrence networks are a method for visualizing relationships between concepts within written material. The results of a co-occurrence analysis...
The goal of the study is to predict acoustic features of expressive speech from semantic vector space representations. Though a lot of successful work was invested in expressiveness analysis and prediction, the results often involve manual labeling, or indirect prediction evaluation such as speech synthesis. The proposed analysis aims at direct acoustic feature prediction and comparison to original...
Thanks to a remarkably great ability to show amusement and engagement, laughter is one of the most important social markers in human interactions. Laughing together can actually help to set up a positive atmosphere and favors the creation of new relationships. This paper presents a data collection of social interaction dialogs involving humor between a human participant and a robot. In this work,...
This paper describes the development of parser algorithm which is used for Hindi-English machine translation (MT). Machine translation requires analysis, transfer and generation steps to produce target language output from a source language input. Structural representation of Hindi sentences codes the information of Hindi sentences and a transfer module can be designed to generate English sentences...
The concept of bipolar linguistic summaries of data, introduced by Dziedzic, Zadrożny and Kacprzyk [1], is further developed. These summaries are meant as an extension of the “classical” linguistic summarization [2], [3], a human-consistent data mining technique, making it possible to express more complex patterns present in data. The focus of the paper is to provide a deeper insight into the very...
Skyline queries are a popular and powerful paradigm for extracting interesting objects from a d-dimensional dataset. They rely on Pareto dominance principle to identify the skyline objects, i.e., the set of incomparable objects which are not dominated by any other object from the dataset. Two main problems may be faced when using skyline queries: (i) a small number of returned objects which could...
We consider the important problem of comprehensiveness of linguistic data summaries equated with linguistically quantified propositions in Zadeh's sense. Motivated by Michal-ski's [29] seminal approach to the comprehensiveness of data mining and machine learning results, with a clear emphasis on natural language, we advocate the use of linguistic summaries which provide a new quality and an exceptional...
The quality measures for bipolar linguistic summaries of data, as proposed in our previous work [1], are further developed. The summaries introduced in [2] are assumed to be an extension of the “classical” linguistic summarization (cf. [3], [4]), a human-consistent data mining technique revealing complex patterns present in data. This extension consists in using the “and possibly” to build a summary...
If NLP systems could better simulate how people would evaluate various states of the world in contexts of interest, this would make it easier to accurately extract embedded sentiments and avoid being led astray by solely linguistic cues. If this knowledge could then be combined with 'fullsemantics' linguistic processing capable of modeling the interplay between lexical and syntactic semantics and...
This paper describes an HMM-based speech synthesis that allows dimensional description of emotion as inputs. A spontaneous dialogue speech corpus that was designed for studying paralinguistic phenomena in expressive social interactions was used to train the models, utilizing its emotional state description as additional contextual factors. In the perceptual experiment, a very high correlation was...
In this paper we present a system that combines the cognitive and socio-cultural paradigms existent in the field of discourse analysis in order to analyze both narrations and conversations. The novelty of our approach is that existing applications are oriented on analyzing only one of these two types, an adaptation being necessary for the analysis of the other type.
We study the possibility to extend the concept of linguistic data summaries employing the notion of bipolarity. Yager's linguistic summaries may be derived using a fuzzy linguistic querying interface. We look for a similar analogy between bipolar queries and the extended form of linguistic summaries. The general concept of bipolar query, and its special interpretation are recalled, which turns out...
The main challenge of question answering is that the lack of task structure prohibits the use of simplified assumptions as in task-oriented dialogue systems. This problem was tackled by integrating a dialogue management environment into a question answering system. Firstly, Wizard of Oz studies were conducted to discover how users describe their music information needs in contextual situations as...
In this paper, we describe an approach to database preference queries based on the notion of fuzzy outranking, suited to the case where partial preferences are incommensurable. This model constitutes an alternative to the use of Pareto order. Even though outranking does not define an order in the strict sense of the term, we describe a technique which yields a complete pre-order, based on a global...
Mining information from very large databases poses numerous challenges. In fact, systems that can mine such voluminous databases are increasingly desirable. In this context, we propose a generic approach of database summarization that takes into account the user's interest topic. Innovation in our work consists in the generation of a set of database summaries having different levels of granularity...
For the majority college students in Taiwan, learning and using terminologies of a specific domain between Chinese and English interchangeably are quite a challenge. Most of the students seek for assistances from library resources or search for answers on web. Unfortunately, the students would not be able to identify the correctness of their findings, or the worse, the students cannot choose the right...
Tacit knowledge in requirements documents can lead to miscommunication between software engineers and other stakeholders. One way in which the presence of tacit knowledge is signalled in text is by linguistic presuppositions. In this paper, we present a brief introduction to tacit knowledge, presuppositions and the links between them. Our aim is to build a theoretically grounded system which is able...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.