Clarifying Ambiguous Keywords with Personal Word Embeddings for Personalized Search

Personalized search tailors document ranking lists for each individual user based on her interests and query intent to better satisfy the user’s information need. Many personalized search models have been proposed. They first build a user interest profile from the user’s search history, and then re-rank the documents based on the personalized matching scores between the created profile and candidate documents. In this article, we attempt to solve the personalized search problem from an alternative perspective of clarifying the user’s intention of the current query. We know that there are many ambiguous words in natural language such as “Apple.” People with different knowledge backgrounds and interests have personalized understandings of these words. Therefore, we propose a personalized search model with personal word embeddings for each individual user that mainly contain the word meanings that the user already knows and can reflect the user interests. To learn great personal word embeddings, we design a pre-training model that captures both the textual information of the query log and the information about user interests contained in the click-through data represented as a graph structure. With personal word embeddings, we obtain the personalized word and context-aware representations of the query and documents. Furthermore, we also employ the current session as the short-term search context to dynamically disambiguate the current query. Finally, we use a matching model to calculate the matching score between the personalized query and document representations for ranking. Experimental results on two large-scale query logs show that our designed model significantly outperforms state-of-the-art personalization models.

Automatic text summarization of konkani texts using pre-trained word embeddings and deep learning

<span lang="EN-US">Automatic text summarization has gained immense popularity in research. Previously, several methods have been explored for obtaining effective text summarization outcomes. However, most of the work pertains to the most popular languages spoken in the world. Through this paper, we explore the area of extractive automatic text summarization using deep learning approach and apply it to Konkani language, which is a low-resource language as there are limited resources, such as data, tools, speakers and/or experts in Konkani. In the proposed technique, Facebook’s fastText <br /> pre-trained word embeddings are used to get a vector representation for sentences. Thereafter, deep multi-layer perceptron technique is employed, as a supervised binary classification task for auto-generating summaries using the feature vectors. Using pre-trained fastText word embeddings eliminated the requirement of a large training set and reduced training time. The system generated summaries were evaluated against the ‘gold-standard’ human generated summaries with recall-oriented understudy for gisting evaluation (ROUGE) toolkit. The results thus obtained showed that performance of the proposed system matched closely to the performance of the human annotators in generating summaries.</span>

Classifying Mobile Applications Using Word Embeddings

Modern application stores enable developers to classify their apps by choosing from a set of generic categories, or genres, such as health, games, and music. These categories are typically static—new categories do not necessarily emerge over time to reflect innovations in the mobile software landscape. With thousands of apps classified under each category, locating apps that match a specific consumer interest can be a challenging task. To overcome this challenge, in this article, we propose an automated approach for classifying mobile apps into more focused categories of functionally related application domains. Our aim is to enhance apps visibility and discoverability. Specifically, we employ word embeddings to generate numeric semantic representations of app descriptions. These representations are then classified to generate more cohesive categories of apps. Our empirical investigation is conducted using a dataset of 600 apps, sampled from the Education, Health&Fitness, and Medical categories of the Apple App Store. The results show that our classification algorithms achieve their best performance when app descriptions are vectorized using GloVe, a count-based model of word embeddings. Our findings are further validated using a dataset of Sharing Economy apps and the results are evaluated by 12 human subjects. The results show that GloVe combined with Support Vector Machines can produce app classifications that are aligned to a large extent with human-generated classifications.

Upon Improving the Performance of Localized Healthcare Virtual Assistants

Virtual assistants are becoming popular in a variety of domains, responsible for automating repetitive tasks or allowing users to seamlessly access useful information. With the advances in Machine Learning and Natural Language Processing, there has been an increasing interest in applying such assistants in new areas and with new capabilities. In particular, their application in e-healthcare is becoming attractive and is driven by the need to access medically-related knowledge, as well as providing first-level assistance in an efficient manner. In such types of virtual assistants, localization is of utmost importance, since the general population (especially the aging population) is not familiar with the needed “healthcare vocabulary” to communicate facts properly; and state-of-practice proves relatively poor in performance when it comes to specialized virtual assistants for less frequently spoken languages. In this context, we present a Greek ML-based virtual assistant specifically designed to address some commonly occurring tasks in the healthcare domain, such as doctor’s appointments or distress (panic situations) management. We build on top of an existing open-source framework, discuss the necessary modifications needed to address the language-specific characteristics and evaluate various combinations of word embeddings and machine learning models to enhance the assistant’s behaviour. Results show that we are able to build an efficient Greek-speaking virtual assistant to support e-healthcare, while the NLP pipeline proposed can be applied in other (less frequently spoken) languages, without loss of generality.

Deep learning approach to text analysis for human emotion detection from big data

Emotional recognition has arisen as an essential field of study that can expose a variety of valuable inputs. Emotion can be articulated in several means that can be seen, like speech and facial expressions, written text, and gestures. Emotion recognition in a text document is fundamentally a content-based classification issue, including notions from natural language processing (NLP) and deep learning fields. Hence, in this study, deep learning assisted semantic text analysis (DLSTA) has been proposed for human emotion detection using big data. Emotion detection from textual sources can be done utilizing notions of Natural Language Processing. Word embeddings are extensively utilized for several NLP tasks, like machine translation, sentiment analysis, and question answering. NLP techniques improve the performance of learning-based methods by incorporating the semantic and syntactic features of the text. The numerical outcomes demonstrate that the suggested method achieves an expressively superior quality of human emotion detection rate of 97.22% and the classification accuracy rate of 98.02% with different state-of-the-art methods and can be enhanced by other emotional word embeddings.

An End-to-End Efficient Lucene-Based Framework of Document/Information Retrieval

In the context of big data and the 4.0 industrial revolution era, enhancing document/information retrieval frameworks efficiency to handle the ever‐growing volume of text data in an ever more digital world is a must. This article describes a double-stage system of document/information retrieval. First, a Lucene-based document retrieval tool is implemented, and a couple of query expansion techniques using a comparable corpus (Wikipedia) and word embeddings are proposed and tested. Second, a retention-fidelity summarization protocol is performed on top of the retrieved documents to create a short, accurate, and fluent extract of a longer retrieved single document (or a set of top retrieved documents). Obtained results show that using word embeddings is an excellent way to achieve higher precision rates and retrieve more accurate documents. Also, obtained summaries satisfy the retention and fidelity criteria of relevant summaries.

Natural language inference by deep learning method

Natural Language inference refers to the problem of determining the relationships between a premise and a hypothesis, it is an emerging area of natural language processing. The paper uses deep learning methods to complete natural language inference task. The dataset includes 3GPP dataset and SNLI dataset. Gensim library is used to get the word embeddings, there are 2 methods which are word2vec and doc2vec to map the sentence to array. 2 deep learning models DNNClassifier and Attention are implemented separately to classify the relationship between the proposals from the telecommunication area dataset. The highest accuracy of the experiment is 88% and we found that the quality of the dataset decided the upper bound of the accuracy.

Collocation ranking: frequency vs semantics

Collocations play a very important role in language description, especially in identifying meanings of words. Modern lexicography’s inevitable part of meaning deduction are lists of collocates ranked by some statistical measurement. In the paper, we present a comparison between two approaches to the ranking of collocates: (a) the logDice method, which is dominantly used and frequency-based, and (b) the fastText word embeddings method, which is new and semantic-based. The comparison was made on two Slovene datasets, one representing general language headwords and their collocates, and the other representing headwords and their collocates extracted from a language for special purposes corpus. In the experiment, two methods were used: for the quantitative part of the evaluation, we used supervised machine learning with the area-under-the-curve (AUC) ROC score and support-vector machines (SVMs) algorithm, and in the qualitative part the ranking results of the two methods were evaluated by lexicographers. The results were somewhat inconsistent; while the quantitative evaluation confirmed that the machine-learning-based approach produced better collocate ranking results than the frequency-based one, lexicographers in most cases considered the listings of collocates of both methods very similar.

Conspiracy theories on Twitter: emerging motifs and temporal dynamics during the COVID-19 pandemic

The COVID-19 pandemic resulted in an upsurge in the spread of diverse conspiracy theories (CTs) with real-life impact. However, the dynamics of user engagement remain under-researched. In the present study, we leverage Twitter data across 11 months in 2020 from the timelines of 109 CT posters and a comparison group (non-CT group) of equal size. Within this approach, we used word embeddings to distinguish non-CT content from CT-related content as well as analysed which element of CT content emerged in the pandemic. Subsequently, we applied time series analyses on the aggregate and individual level to investigate whether there is a difference between CT posters and non-CT posters in non-CT tweets as well as the temporal dynamics of CT tweets. In this regard, we provide a description of the aggregate and individual series, conducted a STL decomposition in trends, seasons, and errors, as well as an autocorrelation analysis, and applied generalised additive mixed models to analyse nonlinear trends and their differences across users. The narrative motifs, characterised by word embeddings, address pandemic-specific motifs alongside broader motifs and can be related to several psychological needs (epistemic, existential, or social). Overall, the comparison of the CT group and non-CT group showed a substantially higher level of overall COVID-19-related tweets in the non-CT group and higher level of random fluctuations. Focussing on conspiracy tweets, we found a slight positive trend but, more importantly, an increase in users in 2020. Moreover, the aggregate series of CT content revealed two breaks in 2020 and a significant albeit weak positive trend since June. On the individual level, the series showed strong differences in temporal dynamics and a high degree of randomness and day-specific sensitivity. The results stress the importance of Twitter as a means of communication during the pandemic and illustrate that these beliefs travel very fast and are quickly endorsed.