1,440 research outputs found
A Neural-based Architecture For Small Datasets Classification
No full textDigital Libraries benefit from the use of text classification strategies since they are enablers for performing many document management tasks like Information Retrieval. The effectiveness of such classification strategies depends on the amount of available data and the classifier used. The former leads to the design of data augmentation solutions where new samples are generated into small datasets based on the semantic similarity between existing samples and concepts defined within external linguistic resources. The latter relates to the capability of finding, which is the best learning principle to adopt for designing an effective classification strategy suitable for the problem. In this work, we propose a neural-based architecture thought for addressing the text classification problem on small datasets. Our architecture is based on BERT equipped with one further layer using the sigmoid function. The hypothesis we want to verify is that by using embeddings learned by a BERT-based architecture, one can perform effective classification on small datasets without the use of data augmentation strategies. We observed improvements up to 14% in the accuracy and up to in the f-score with respect to baseline classifiers exploiting data augmentation
Exploiting Propositions for Opinion Mining
No full textWith different social media and commercial platforms, users express their opinion about products in a textual form. Automatically extracting the polarity (i.e. whether the opinion is positive or negative) of a user can be useful for both actors: the online platform incorporating the feedback to improve their product as well as the client who might get recommendations according to his or her preferences. Different approaches for tackling the problem, have been suggested mainly using syntactic features. The “Challenge on Semantic Sentiment Analysis” aims to go beyond the word-level analysis by using semantic information. In this paper we propose a novel approach by employing the semantic information of grammatical unit called preposition. We try to drive the target of the review from the summary information, which serves as an input to identify the proposition in it. Our implementation relies on the hypothesis that the proposition expressing the target of the summary, usually containing the main polarity information
A semantic federated search engine for domain-specific document retrieval
No full textRetrieval of domain-specific documents became attractive for the Semantic Web community due to the possibility of integrating classic Information Retrieval (IR) techniques with semantic knowledge. Unfortunately, the gap between the construction of a full semantic search engine and the possibility of exploiting a repository of ontologies covering all possible domains is far from being filled. Recent solutions focused on the aggregation of different domain-specific repositories managed by third-parties. In this paper, we present a semantic federated search engine developed in the context of the EEXCESS EU project. Through the developed platform, users are able to perform federated queries over repositories in a transparent way, i.e. without knowing how their original queries are transformed before being actually submitted. The platform implements a facility for plugging new repositories and for creating, with the support of general purpose knowledge bases, knowledge graphs describing the content of each connected repository. Such knowledge graphs are then exploited for enriching queries performed by users
Removable template route to metallic nanowires and nanogaps
No full textA general method for the fabrication of nanowires with a thickness of ∼6 nm and width of 15–20 nm is presented. The approach is applicable to inorganic and organic materials and is demonstrated here for metallic systems. The wires are produced by ion-beam etching of a gold–palladium thin films covered by chemically modified vanadium–pentoxide nanowires as an etching mask. The two-probe room-temperature resistance of the wires is found to range between 7.8 and 18.1 kΩ. Nanogaps with a length on the order of 1 nm were created within the nanowires by breaking via electromigration
Opinion Mining with a Clause-Based Approach
No full textWith different social media and commercial platforms, users express their opinion about products in a textual form. Automatically extracting the polarity (i.e. whether the opinion is positive or negative) of a user can be useful for both actors: the online platform incorporating the feedback to improve their product as well as the client who might get recommendations according to his or her preferences. Different approaches for tackling the problem, have been suggested mainly using syntactic features. The “Challenge on Semantic Sentiment Analysis” aims to go beyond the word-level analysis by using semantic information. In this paper we propose a novel approach by employing the semantic information of grammatical unit called preposition. We try to derive the target of the review from the summary information, which serves as an input to identify the proposition in it. Our implementation relies on the hypothesis that the proposition expressing the target of the summary, usually containing the main polarity information
Polymer-electrolyte gated graphene transistors for analog and digital phase detection
No full textWe present an alternating current (ac) circuit based on a misoriented bilayer graphene device for analog and digital phase detection. We exploit the ambipolar nature of the transfer characteristics of a misoriented bilayer graphene transistor. The transistor action here is realized using an electrochemical gate integrated into a solid polymer electrolyte layer. This unique combination provides a voltage gain close to unity under ambient conditions, which is one order of magnitude higher than that attainable in back-gated devices. The achieved gain provides sufficient sensitivity to detect phase differences between pairs of analog or digital signals
A selective electrochemical approach to carbon nanotube field-effect transistors
No full textCommercial fabrication of field-effect transistors (FETs) using carbon
nanotubes has been hindered as all current production procedures yield
a mixture of metallic and semiconducting tubes. Herein, we present a
generic approach utilizing electrochemistry for selective covalent
modification of metallic nanotubes, resulting in exclusive electrical
transport through the unmodified semiconducting tubes. Toward this
goal, the semiconducting tubes are rendered nonconductive by
application of an appropriate gate voltage prior to the electrochemical
modification. The FETs fabricated in this manner display good hole
mobilities and a ratio approaching 10(6) between the current in the ON
and OFF state
The CLAUSY System at ESWC-2018 Challenge on Semantic Sentiment Analysis
No full textWith different social media and commercial platforms, users express their opinion about products in a textual form. Automatically extracting the polarity(i.e. whether the opinion is positive or negative) of a user can be useful for both actors: the online platform incorporating the feedback to improve their product as well as the client who might get recommendations according to his or her preferences. Different approaches for tackling the problem, have been suggested mainly using syntactic features. The “Challenge on Semantic Sentiment Analysis” aims to go beyond the word-level analysis by using semantic information. In this paper we propose a novel approach by employing the semantic information of grammatical unit called preposition. We try to derive the target of the review from the summary information, which serves as an input to identify the proposition in it. Our implementation relies on the hypothesis that the proposition expressing the target of the summary, usually containing the main polarity information
Polarity Classification for Target Phrases in Tweets: A Word2Vec Approach
No full textTwitter is one of the most popular micro-blogging services on the web. The service allows sharing, interaction and collaboration via short, informal and often unstructured messages called tweets. Polarity classification of tweets refers to the task of assigning a positive or a negative sentiment to an entire tweet. Quite similar is predicting the polarity of a specific target phrase, for instance @Microsoft or #Linux, which is contained in the tweet.
In this paper we present a Word2Vec approach to automatically predict the polarity of a target phrase in a tweet. In our classification setting, we thus do not have any polarity information but use only semantic information provided by a Word2Vec model trained on Twitter messages. To evaluate our feature representation approach, we apply well-established classification algorithms such as the Support Vector Machine and Naive Bayes. For the evaluation we used the Semeval 2016 Task #4 dataset. Our approach achieves F1-measures of up to ∼∼90 % for the positive class and ∼∼54 % for the negative class without using polarity information about single words
An Information Retrieval Based Approach for Multilingual Ontology Matching
No full textOntology matching in a multilingual environment consists of finding alignments between ontologies modeled by using more than one language. Such a research topic combines traditional ontology matching algorithms with the use of multilingual resources, services, and capabilities for easing multilingual matching. In this paper, we present a multilingual ontology matching approach based on Information Retrieval (IR) techniques: ontologies are indexed through an inverted index algorithm and candidate matches are found by querying such indexes. We also exploit the hierarchical structure of the ontologies by adopting the PageRank algorithm for our system. The approaches have been evaluated using a set of domain-specific ontologies belonging to the agricultural and medical domain. We compare our results with existing systems following an evaluation strategy closely resembling a recommendation scenario. The version of our system using PageRank showed an increase in performance in our evaluations
- …
