Search results for "NLP"

Attention-based Model for Evaluating the Complexity of Sentences in English Language

2020

The automation of text complexity evaluation (ATCE) is an emerging problem which has been tackled by means of different methodologies. We present an effective deep learning- based solution which leverages both Recurrent Neural and the Attention mechanism. The developed system is capable of classifying sentences written in the English language by analysing their syntactical and lexical complexity. An accurate test phase has been carried out, and the system has been compared with a baseline tool based on the Support Vector Machine. This paper represents an extension of a previous deep learning model, which allows showing the suitability of Neural Networks to evaluate sentence complexity in tw…

Personīgo zināšanu pārvaldības iespējas ar mobilā telefona lietotnes palīdzību

2018

Pasaule ir ļoti sarežģīti aptverama un izzināma vieta. Ikdienā cilvēki uztver ļoti daudz informācijas, kas netiek organizēta. Personīgo zināšānu pārvaldība palīdz saprast, kas ir svarīgs, pārvietot informāciju un organizēt to, lai tiktu galā ar problēmām, kas izveidojas, prasot risinājumu. Darbā tiek apskatītas esošās pieejas – modeļi, sistēmas. Lai risinātu šo problēmu, tiek apskatīts veids, kā izstrādāt Android telefonu lietotni, kas izmantojot personības testu, nosaka ar personību saistītos atslēgvārdus, lai iegūt datus no kāda avota un izmanto NLP metodes, lai pakārtotu informāciju, kas palīdzētu iegūt konkrētam indivīdam būtisku informāciju.

Software Architectures for Human-Machine Interaction Using Natural Language

Il linguaggio naturale rappresenta un sistema di comunicazione a carattere inferenziale in opposizione ai sistemi di comunicazione a codice che non prevedono una forma di ragionamento intelligente da parte del ricevente, ma si basano sul riconoscimento di patterns dell'informazione. In un sistema di comunicazione di tipo inferenziale, infatti, si parte dal presupposto che il ricevente abbia una certa "intelligenza" e sia, quindi, capace di comprendere, elaborare ed inferire il contenuto informativo di una comunicazione attraverso ragionamenti su un background di conoscenze (come modelli di mondo e di linguaggio) condivisi sia dalla sorgente che dal destinatario. L'attività di ricerca, svolt…

Enhancing Attention’s Explanation Using Interpretable Tsetlin Machine

2022

Explainability is one of the key factors in Natural Language Processing (NLP) specially for legal documents, medical diagnosis, and clinical text. Attention mechanism has been a popular choice for such explainability recently by estimating the relative importance of input units. Recent research has revealed, however, that such processes tend to misidentify irrelevant input units when explaining them. This is due to the fact that language representation layers are initialized by pre-trained word embedding that is not context-dependent. Such a lack of context-dependent knowledge in the initial layer makes it difficult for the model to concentrate on the important aspects of input. Usually, th…

Semantic technologies for industry: From knowledge modeling and integration to intelligent applications

2013

Artificial Intelligence technologies are growingly used within several software systems ranging from Web services to mobile applications. It is by no doubt true that the more AI algorithms and methods are used the more they tend to depart from a pure "AI" spirit and end to refer to the sphere of standard software. In a sense, AI seems strongly connected with ideas, methods and tools that are not (yet) used by the general public. On the contrary, a more realistic view of it would be a rich and pervading set of successful paradigms and approaches. Industry is currently perceiving semantic technologies as a key contribution of AI to innovation. In this paper a survey of current industrial expe…

Pēc loģikas līdzīgu teikumu meklēšana, izmantojot mašīnmācīšanās metodes

2018

Mūsdienās ļoti strauji pieaug mašīnmācīšanās popularitāte, kas rezultējas ar dažādu metožu izveidi valodas apstrādes jomā, bet lielākā daļa no šīm metodēm tiek izstrādātas priekš angļu valodas. Darbā tika izvirzīts mērķis aplūkot un salīdzināt populārākās metodes, kas ļauj salīdzināt teikumus pēc to loģikas un pārbaudīt tās uz latviešu valoda, lai gūtu priekšstatu par to, kuras no tām ir efektīvākas. Darba ietvaros tika pētītas mašīnmācīšanās dabiskās valodas apstrādes (NLP) metodes, kas ļauj iemācīt datoram saprast teikumu loģiku. Tika sagatavota apmācāmo datu kopa, kas satur teikumus latviešu valodā. Daļa no aplūkotajiem risinājumi tika izmēģināti, izmantojot sagatavoto apmācāmo datu kopu…

A recurrent deep neural network model to measure sentence complexity for the Italian Language

2019

Text simplification (TS) is a natural language processing task devoted to the modification of a text in such a way that the grammar and structure of the phrases is greatly simplified, preserving the underlying meaning and information contents. In this paper we give a contribution to the TS field presenting a deep neural network model able to detect the complexity of italian sentences. In particular, the system gives a score to an input text that identifies the confidence level during the decision making process and that could be interpreted as a measure of the sentence complexity. Experiments have been carried out on one public corpus of Italian texts created specifically for the task of TS…

A Lite Romanian BERT: ALR-BERT

2022

Large-scale pre-trained language representation and its promising performance in various downstream applications have become an area of interest in the field of natural language processing (NLP). There has been huge interest in further increasing the model’s size in order to outperform the best previously obtained performances. However, at some point, increasing the model’s parameters may lead to reaching its saturation point due to the limited capacity of GPU/TPU. In addition to this, such models are mostly available in English or a shared multilingual structure. Hence, in this paper, we propose a lite BERT trained on a large corpus solely in the Romanian language, which we cal…

AI for Resource Allocation and Resource Allocation for AI: a two-fold paradigm at the network edge

2022

5G-and-beyond and Internet of Things (IoT) technologies are pushing a shift from the classic cloud-centric view of the network to a new edge-centric vision. In such a perspective, the computation, communication and storage resources are moved closer to the user, to the benefit of network responsiveness/latency, and of an improved context-awareness, that is, the ability to tailor the network services to the live user's experience. However, these improvements do not come for free: edge networks are highly constrained, and do not match the resource abundance of their cloud counterparts. In such a perspective, the proper management of the few available resources is of crucial importance to impr…

A Social Spider Optimisation Algorithm for 3D Unmanned Aerial Base Stations Placement

2020

International audience; In recent years, the use of drones as aerial base stations (ABS) has attracted the attention of both scientific and industrial communities as a promising solution to enhance the network coverage. However, their deployment brings out many challenges and restrictions. In this work, we model a realistic, constrained scenario where unmanned aerial vehicles (UAVs) are used as ABSs along with traditional ground base stations (GBSs) to extend their coverage. We propose a scalable and efficient social spider optimization (SSO) algorithm that determines the placement of UAVs and their association with both user equipments (UEs) and GBSs. Extensive computational experiments we…