Development of Spoken Language User Interfaces: A Tool Kit Approach

Author(s):  
Hassan Alam ◽  
Ahmad Fuad ◽  
Rezaur Rahman ◽  
Timotius Tjahjadi ◽  
Hua Cheng ◽  
...  
Author(s):  
Hassan Alam ◽  
Ahmad Fuad Rezaur Rahman ◽  
Timotius Tjahjadi ◽  
Hua Cheng ◽  
Paul Llido ◽  
...  

1991 ◽  
Vol 1 (4) ◽  
pp. 351-363
Author(s):  
Octavio F. Torres-Chazaro ◽  
Robert J. Beaton ◽  
Michael P. Deisenroth

Mathematics ◽  
2020 ◽  
Vol 8 (11) ◽  
pp. 2075
Author(s):  
Óscar Apolinario-Arzube ◽  
José Antonio García-Díaz ◽  
José Medina-Moreira ◽  
Harry Luna-Aveiga ◽  
Rafael Valencia-García

Automatic satire identification can help to identify texts in which the intended meaning differs from the literal meaning, improving tasks such as sentiment analysis, fake news detection or natural-language user interfaces. Typically, satire identification is performed by training a supervised classifier for finding linguistic clues that can determine whether a text is satirical or not. For this, the state-of-the-art relies on neural networks fed with word embeddings that are capable of learning interesting characteristics regarding the way humans communicate. However, as far as our knowledge goes, there are no comprehensive studies that evaluate these techniques in Spanish in the satire identification domain. Consequently, in this work we evaluate several deep-learning architectures with Spanish pre-trained word-embeddings and compare the results with strong baselines based on term-counting features. This evaluation is performed with two datasets that contain satirical and non-satirical tweets written in two Spanish variants: European Spanish and Mexican Spanish. Our experimentation revealed that term-counting features achieved similar results to deep-learning approaches based on word-embeddings, both outperforming previous results based on linguistic features. Our results suggest that term-counting features and traditional machine learning models provide competitive results regarding automatic satire identification, slightly outperforming state-of-the-art models.


Informatics ◽  
2021 ◽  
Vol 18 (4) ◽  
pp. 40-52
Author(s):  
S. A. Hetsevich ◽  
Dz. A. Dzenisyk ◽  
Yu. S. Hetsevich ◽  
L. I. Kaigorodova ◽  
K. A. Nikalaenka

O b j e c t i v e s. The main goal of the work is a research of the natural language user interfaces and the developmentof a prototype of such an interface. The prototype is a bilingual Russian and Belarusian question-and-answer dialogue system. The research of the natural language interfaces was conducted in terms of the use of natural language for interaction between a user and a computer system. The main problems here are the ambiguity of natural language and the difficulties in the design of natural language interfaces that meet user expectations.M e t ho d s. The main principles of modelling the natural language user interfaces are considered. As an intelligent system, it consists of a database, knowledge machine and a user interface. Speech recognition and speech synthesis components make natural language interfaces more convenient from the point of view of usability.R e s u l t s. The description of the prototype of a natural language interface for a question-and-answer intelligent system is presented. The model of the prototype includes speech-to-text and text-to-speech Belarusian and Russian subsystems, generation of responses in the form of the natural language and formal text.An additional component is natural Belarusian and Russian voice input. Some of the data, required for human voice recognition, are stored as knowledge in the knowledge base or created on the basis of existing knowledge. Another important component is Belarusian and Russian voice output. This component is the top required for making the natural language interface more user-friendly.Co n c l u s i o n. The article presents the research of natural language user interfaces, the result of which provides the development and description of the prototype of the natural language interface for the intelligent question- and-answer system.


2022 ◽  
Author(s):  
Ross Gruetzemacher ◽  
David Paradice

AI is widely thought to be poised to transform business, yet current perceptions of the scope of this transformation may be myopic. Recent progress in natural language processing involving transformer language models (TLMs) offers a potential avenue for AI-driven business and societal transformation that is beyond the scope of what most currently foresee. We review this recent progress as well as recent literature utilizing text mining in top IS journals to develop an outline for how future IS research can benefit from these new techniques. Our review of existing IS literature reveals that suboptimal text mining techniques are prevalent and that the more advanced TLMs could be applied to enhance and increase IS research involving text data, and to enable new IS research topics, thus creating more value for the research community. This is possible because these techniques make it easier to develop very powerful custom systems and their performance is superior to existing methods for a wide range of tasks and applications. Further, multilingual language models make possible higher quality text analytics for research in multiple languages. We also identify new avenues for IS research, like language user interfaces, that may offer even greater potential for future IS research.


2002 ◽  
Author(s):  
Hassan Alam ◽  
Timotius Tjahjadi ◽  
Che Wilcox ◽  
Hua Cheng ◽  
Rachmat Hartono ◽  
...  

2016 ◽  
Vol 75 (1) ◽  
Author(s):  
Eleonora Massa

This paper develops a theoretical discussion about the definition of the unit of content in spoken language. The issue originates from the applicative field of corpus-based lexico-statistical surveys, which are traditionally and prevalently used to optimize and standardize the programs for the vocabulary didactics of foreign languages. The main critical limitation of lexico-statistical inquiries can be identified in their impossibility to determine a representative threshold of the basic content lexicon of a language or, put otherwise, the most important words referring to the concrete things that are spoken about. Beyond the threshold of the most recurring 1,000 lexemes, in fact, words virtually show low and irregular as well as semi-equivalent probabilities to recur in spoken texts. The lexico-statistical applications that have followed aim exactly at overcoming this limitation. Albeit through different methodologies, the various approaches conceive in fact the basic content lexicon as made up by the most frequent or used concrete substantives of a language. From time to time, either limited or particularly extensive series of concrete nouns have been compiled: however, these nouns are de facto subject to sporadic and irregular trends of recur-rence values in spoken texts and are likely to be encountered very rarely by the language user in actual spoken utterances. The discussion on basic spoken contents simply ends up in a theoretical flaw and in a mere representational paradox, because it investigates and describes exactly what is not constitutive of the examined phenomenon. The consideration of the very semiotic peculiarity of spoken language constitutes the premise of an alternative definition of its meaning unit. The things that are talked about are in fact expressed only sporadically, because they are embedded in the situational context wherein they are shared – and mostly reiterated – by the conversation partners. More than with a dis-crete lexical element, the unit of spoken content seems to be identifiable with the holistic con-versational practice that is instead regularly carried out by the speakers within likely ordinary frames of experience; consequently it seems to be closer to a basic unit in the “practice of meaning” than to an isolated meaning constituent. As the habitudinary modality of construct-ing, inhabiting and sharing our everyday form of life, the meaning unit in spoken language rather unveils as a narrative unit, for reasons that this paper explores in details. Such an alter-native theoretical vision is dealt with in the final part of the contribution, which also outlines further issues related to the possibilities of both its representation and its didactic usability.


Author(s):  
Richard Bale

Spoken language interpreting is a complex task involving comprehension of a source language message and subsequent production of this in the target language, all of which happens at a fast pace and often in front of an audience. Building on research conducted in language learning and drama-based pedagogies, this paper takes stock of recent technological developments in interpreter education, and proposes that a renewed focus on the interpreter as a language user and as a performer is necessary.1


Sign in / Sign up

Export Citation Format

Share Document