Representing Semantics of Text by Acquiring its Canonical Form

Taiye, Mohammed Ahmed; Kamaruddin, Siti Sakira; Ahmad, Farzana Kabir

doi:10.18517/ijaseit.7.3.2395

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For these reasons, it is necessary to adopt automated tools to perform topics analysis favoring their understanding and the support to the decision making [1]. Digitalized sources have several characteristics such as heterogeneity and inconsistency in texts, which pose serious limits when trying to extract the meaning from sentences [2]- [4].…”

Section: Introductionmentioning

confidence: 99%

Analysing and Visualizing Tweets for U.S. President Popularity

Luca

Fallucchi

Giuliano

et al. 2019

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

In our society we are continually invested by a stream of information (opinions, preferences, comments, etc.). This shows how Twitter users react to news or events that they attend or take part in real time and with interest. In this context it becomes essential to have the appropriate tools in order to be able to analyze and extract data and information hidden in their large number of tweets. Social networks are a source of information with no rivals in terms of amount and variety of information that can be extracted from them. We propose an approach to analyze, with the help of automated tools, comments and opinions taken from social media in a real time environment. We developed a software system in R based on the Bayesian approach for text categorization. We aim of identifying sentiments expressed by the tweets posted on the Twitter social platform. The analysis of sentiment spread on social networks allows to identify the free thoughts, expressed authentically. In particular, we analyze the sentiments related to U.S President popularity by also visualizing tweets on a map. This allows to make an additional analysis of the real time reactions of people by associating the reaction of the single person who posted the tweet to his real time position in Unites States. In particular, we provide a visualization based on the geographical analysis of the sentiments of the users who posted the tweets.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysing and Visualizing Tweets for U.S. President Popularity

Luca

Fallucchi

Giuliano

et al. 2019

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…Despite the complexity, models that use continuous input variables tend to show better performance. For example, vector representations of words significantly improve many NLP applications such as text syntactic and semantic analyses [2] [3] Named Entity Disambiguation (NED) [4], ontology population [5] and information retrieval [6]. These representations can be shared across languages [7] to overcome language-specific problems such as Arabic entity detection issues [8].…”

Section: Introductionmentioning

confidence: 99%

Building Compact Entity Embeddings Using Wikidata

Lubani

Noah

2018

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Representing natural language sentences has always been a challenge in statistical language modeling. Atomic discrete representations of words make it difficult to represent semantically related sentences. Other sentence components such as phrases and named-entities should be recognized and given representations as units instead of individual words. Different entity senses should be assigned different representations even though they share identical words. In this paper, we focus on building the vector representations (embedding) of named-entities from their contexts to facilitate the task of ontology population where named-entities need to be recognized and disambiguated in natural language text. Given a list of target named-entities, Wikidata is used to compensate for the lack of a labeled corpus to build the contexts of all target named-entities as well as all their senses. Description text and semantic relations with other named-entities are considered when building the contexts from Wikidata. To avoid noisy and uninformative features in the embedding generated from artificially built contexts, we propose a method to build compact entity representations to sharpen entity embedding by removing irrelevant features and emphasizing the most detailed ones. An extended version of the Continuous Bag-of-Words model (CBOW) is used to build the joint vector representations of words and named-entities using Wikidata contexts. Each entity context is then represented by a subset of elements that maximizes the chances of keeping the most descriptive features about the target entity. The final entity representations are built by compressing the embedding of the chosen subset using a deep stacked auto encoders model. Cosine similarity and t-SNE visualization technique are used to evaluate the final entity vectors. Results show that semantically related entities are clustered near each other in the vector space. Entities that appear in similar contexts are assigned similar compact vector representations based on their contexts.

show abstract

Representing Semantics of Text by Acquiring its Canonical Form

Cited by 2 publications

References 17 publications

Analysing and Visualizing Tweets for U.S. President Popularity

Analysing and Visualizing Tweets for U.S. President Popularity

Building Compact Entity Embeddings Using Wikidata

Contact Info

Product

Resources

About