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.
In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by combining these two types of representations. We argue that learning word-to-image interaction is more native in the sense of jointly modeling two modalities...
This paper presents a speech interface to extract domain-specific information from a tourism semantic website as a way to avoid complicated and unfriendly SPARQL queries. First, we present a user-oriented website with a semantic knowledge model of tourism. This model is also known as ontology, represents a common understanding of domain in which semantics of data is machine understandable. Second,...
One aspect that increases the accessibility of many blocks-based languages is their use of labels to tell users the meaning of the input-slots in the blocks. In this regard, every block is a little form. FreeCoffee is a blocks-based language whose editor goes well beyond terse slot labels and communicates the meaning of a block using complete grammatical sentences. These sentence-blocks still contain...
It is promising for service robots to be able to accomplish natural language tasks given by human automatically. In this paper, we propose a flexible framework, which is aimed at resolving Chinese service tasks into executable sequences of primitive actions. Firstly, we collect a number of service tasks described in free-form Chinese natural language. We then build the intelligent space corpus by...
Rich and dense human labeled datasets are among the main enabling factors for the recent advance on visionlanguage understanding. Many seemingly distant annotations (e.g., semantic segmentation and visual question answering (VQA)) are inherently connected in that they reveal different levels and perspectives of human understandings about the same visual scenes — and even the same set of images (e...
The ongoing trend towards distributed development activities causes a growing need for specification activities and techniques. Each component leads to a large number of specification documents being exchanged, change managed and committed. The quality of the specifications influences the timing, costs and success of the development task. However, the quality of such specifications is often far from...
Requirements are the keystone of complex systems development. In order to reduce inconsistencies, requirements analysis is an important issue of systems engineering. In this context, there is a need for conciliating views of several stakeholders from different domains and for tracing these requirements from specification to realization. The computerization of analysis, with the help of a clearly defined...
Natural language-based use cases remains the main means of requirements elicitation and specification, despite the well-known problems that accompany natural language specifications, namely their incompleteness, inconsistency and ambiguity. This paper presents a novel approach for tackling the textual description problems by using FrameNet frames, which are linguistics patterns for concept description...
The article presents the use of generative grammars in linguistic modeling. A description of sentence syntax modeling is used to automate the process of analysis and synthesis of natural language texts. The article reveals the features of synthesizing sentences of different languages with the use of generative grammars. The article examines influence of norms and rules of a language on the process...
This electronic document is a “live” template and already defines the components of your paper [title, text, heads, etc.] in its style sheet. The paper considers the possibility and necessity of using in modern control and training systems with a natural language interface methods and mechanisms, characteristic for knowledge processing systems. This symbiosis assumes the introduction of specialized...
A promising way to improve the programming process is increasing the declarativeness of programming, approximation to natural language on the base of accumulating and actively using knowledge. The essence of the proposed approach is representing the semantics of a program in the form of a set of concepts about actions, participants, resources and relations between them, accumulation and classification...
This article presents an approach to examining the similarity of the sentences. In our approach, Euler algorithm was used to generate a series of words based on tree and S⊘rensen-Dice coefficient was applied to determine the similarity between compared trees. The emphasis is on defining the similarity between the correct and incorrect answers from the Yahoo Question and Answer of the Non-Factual Data...
Web Services have become essential to the software industry as they provide reusable, remotely-accessible functionality and data, thus accelerating client application development and relieving users from maintaining the consumed services. Since Web Services-particularly their descriptions-must be discovered before being consumed, many discovery approaches based on classic Information Retrieval techniques,...
In this paper, we propose a method for extracting ICD-10 codes from the natural language description of a patient illness complaint. The proposed method is based on distributional semantics of terms that appeared in the two natural language expressions: a patient's complaint and an ICD-10 code description. In order to locate the relevant fragment of words within a given long and noisy patient's expression,...
We present a novel approach to enable a mobile service robot to understand questions about the history of tasks it has executed. We frame the problem of understanding such questions as grounding an input sentence to a query that can be executed on the logs recorded by the robot during its runs. We define a query as an operation followed by a set of filters. In order to ground sentence to a query we...
Today, there are many examples of humans and robots regularly interacting in a variety of domains, such as manufacturing, coordinated assembly, and rehabilitation. A resulting demand for more generally accessible communication interfaces has motivated several recent independent research efforts focused on providing robotic systems with a robust natural language interface. Natural language interfaces...
Stochastic natural language generation systems that are trained from labelled datasets are often domainspecific in their annotation and in their mapping from semantic input representations to lexical-syntactic outputs. As a result, learnt models fail to generalize across domains, heavily restricting their usability beyond single applications. In this article, we focus on the problem of domain adaptation...
In this work, we present a framework for handling multiple, simultaneous, natural language queries, in a resource constrained environment, using Quality of Information (QoI). Incoming queries are first parsed into response graphs, tree-like structures designed to formalize a system's understanding of user intent, via a pragmatics toolkit. The system then uses a combination of QoI-awareness, adaptive...
Understanding unfamiliar source code is inherently difficult for a software engineer, despite its importance. Thus, an experienced engineer prefers to guess the intended behavior, rather than to trace it line-by-line, by combining semantic chunks found in the source code. It is, however, still hard for a system to help in this activity, for lack of ways of both representing semantic chunks and of...
We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with images and their associated image-level captions, without any explicit region-to-phrase correspondence annotations. To this end, we introduce an end-to-end model...
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.