Improving Subjective Bias Detection Using Bidirectional Encoder Representations from Transformers and Bidirectional Long Short-Term Memory

Detecting subjectively biased statements is a vital task. This is because this kind of bias, when present in the text or other forms of information dissemination media such as news, social media, scientific texts, and encyclopedias, can weaken trust in the information and stir conflicts amongst consumers. Subjective bias detection is also critical for many Natural Language Processing (NLP) tasks like sentiment analysis, opinion identification, and bias neutralization. Having a system that can adequately detect subjectivity in text will boost research in the above-mentioned areas significantly. It can also come in handy for platforms like Wikipedia, where the use of neutral language is of importance. The goal of this work is to identify the subjectively biased language in text on a sentence level. With machine learning, we can solve complex AI problems, making it a good fit for the problem of subjective bias detection. A key step in this approach is to train a classifier based on BERT (Bidirectional Encoder Representations from Transformers) as upstream model. BERT by itself can be used as a classifier; however, in this study, we use BERT as data preprocessor as well as an embedding generator for a Bi-LSTM (Bidirectional Long Short-Term Memory) network incorporated with attention mechanism. This approach produces a deeper and better classifier. We evaluate the effectiveness of our model using the Wiki Neutrality Corpus (WNC), which was compiled from Wikipedia edits that removed various biased instances from sentences as a benchmark dataset, with which we also compare our model to existing approaches. Experimental analysis indicates an improved performance, as our model achieved state-of-the-art accuracy in detecting subjective bias. This study focuses on the English language, but the model can be fine-tuned to accommodate other languages.

Analysis Model for the Relationship of Users, Products, and Stores on Online Marketplace Based on Distributed Representation

Recently, online marketplaces in the e-commerce industry, such as Rakuten and Alibaba, have become some of the most popular online marketplaces in Asia. In these shopping websites, consumers can select purchase products from a large number of stores. Additionally, consumers of the e-commerce site have to register their name, age, gender, and other information in advance, to access their registered account. Therefore, establishing a method for analyzing consumer preferences from both the store and the product side is required. This study uses the Doc2Vec method, which has been studied in the field of natural language processing. Doc2Vec has been used in many cases to analyze the extraction of semantic relationships between documents (represented as consumers) and words (represented as products) in the field of document classification. This concept is applicable to represent the relationship between users and items; however, the problem is that one more factor (i.e., shops) needs to be considered in Doc2Vec. More precisely, a method for analyzing the relationship between consumers, stores, and products is required. The purpose of our study is to combine the analysis of the Doc2vec model for users and shops, and for users and items in the same feature space. This method enables the calculation of similar shops and items for each user. In this study, we derive the real data analysis accumulated in the online marketplace and demonstrate the efficiency of the proposal.

Emotional Analysis for Text Search Queries on Internet

The goal of this study is to analyze if search queries carried out in search engines such as Google, can offer emotional information about the user that performs them. Knowing the emotional state in which the Internet user is located can be a key to achieve the maximum personalization of content and the detection of worrying behaviors. For this, two studies were carried out using tools with advanced natural language processing techniques. The first study determines if a query can be classified as positive, negative or neutral, while the second study extracts emotional content from words and applies the categorical and dimensional models for the representation of emotions. In addition, we use search queries in Spanish and English to establish similarities and differences between two languages. The results revealed that text search queries performed by users on the Internet can be classified emotionally. This allows us to better understand the emotional state of the user at the time of the search, which could involve adapting the technology and personalizing the responses to different emotional states.

Methodology for Developing an Intelligent Tutoring System Based on Marzano’s Taxonomy

The Mexican educational system faces diverse challenges related with the quality and coverage of education. The development of Intelligent Tutoring Systems (ITS) may help to solve some of them by helping teachers to customize their classes according to the performance of the students in online courses. In this work, we propose the adaptation of a functional ITS based on Bloom’s taxonomy called Sistema de Apoyo Generalizado para la Enseñanza Individualizada (SAGE), to measure student’s metacognition and their emotional response based on Marzano’s taxonomy. The students and the system will share the control over the advance in the course, so they can improve their metacognitive skills. The system will not allow students to get access to subjects not mastered yet. The interaction between the system and the student will be implemented through Natural Language Processing techniques, thus avoiding the use of sensors to evaluate student’s response. The teacher will evaluate student’s knowledge utilization, which is equivalent to the last cognitive level in Marzano’s taxonomy.

Adaption Model for Building Agile Pronunciation Dictionaries Using Phonemic Distance Measurements

Where human beings can easily learn and adopt pronunciation variations, machines need training before put into use. Also humans keep minimum vocabulary and their pronunciation variations are stored in front-end of their memory for ready reference, while machines keep the entire pronunciation dictionary for ready reference. Supervised methods are used for preparation of pronunciation dictionaries which take large amounts of manual effort, cost, time and are not suitable for real time use. This paper presents an unsupervised adaptation model for building agile and dynamic pronunciation dictionaries online. These methods mimic human approach in learning the new pronunciations in real time. A new algorithm for measuring sound distances called Dynamic Phone Warping is presented and tested. Performance of the system is measured using an adaptation model and the precision metrics is found to be better than 86 percent.

Part of Speech Tagging Using Statistical Approach for Nepali Text

Part of Speech Tagging has always been a challenging task in the era of Natural Language Processing. This article presents POS tagging for Nepali text using Hidden Markov Model and Viterbi algorithm. From the Nepali text, annotated corpus training and testing data set are randomly separated. Both methods are employed on the data sets. Viterbi algorithm is found to be computationally faster and accurate as compared to HMM. The accuracy of 95.43% is achieved using Viterbi algorithm. Error analysis where the mismatches took place is elaborately discussed.

Role of Natural Language Processing in Information Retrieval; Challenges and Opportunities

This paper aims to analyze the role of natural language processing (NLP). The paper will discuss the role in the context of automated data retrieval, automated question answer, and text structuring. NLP techniques are gaining wider acceptance in real life applications and industrial concerns. There are various complexities involved in processing the text of natural language that could satisfy the need of decision makers. This paper begins with the description of the qualities of NLP practices. The paper then focuses on the challenges in natural language processing. The paper also discusses major techniques of NLP. The last section describes opportunities and challenges for future research.

A Thai to English Machine Translation System Using Thai LFG Tree Structure as Interlingua

Machine Translation (MT) between the Thai and English languages has been a challenging research topic in natural language processing. Most research has been done on English to Thai machine translation, but not the other way around. This paper presents a Thai to English Machine Translation System that translates a Thai sentence into interlingua of a Thai LFG tree using LFG grammar and a bottom up parser. The Thai LFG tree is then transformed into the corresponding English LFG tree by pattern matching and node transformation. Finally, an equivalent English sentence is created using structural information prescribed by the English LFG tree. Based on results of experiments designed to evaluate the performance of the proposed system, it can be stated that the system has been proven to be effective in providing a useful translation from Thai to English.

Greek Compounds: A Challenging Case for the Parsing Techniques of PC-KIMMO v.2

In this paper we describe the recognition process of Greek compound words using the PC-KIMMO software. We try to show certain limitations of the system with respect to the principles of compound formation in Greek. Moreover, we discuss the computational processing of phenomena such as stress and syllabification which are indispensable for the analysis of such constructions and we try to propose linguistically-acceptable solutions within the particular system.

Morpho-Phonological Modelling in Natural Language Processing

In this paper we propose a computational model for the representation and processing of morpho-phonological phenomena in a natural language, like Modern Greek. We aim at a unified treatment of inflection, compounding, and word-internal phonological changes, in a model that is used for both analysis and generation. After discussing certain difficulties cuase by well-known finitestate approaches, such as Koskenniemi-s two-level model [7] when applied to a computational treatment of compounding, we argue that a morphology-based model provides a more adequate account of word-internal phenomena. Contrary to the finite state approaches that cannot handle hierarchical word constituency in a satisfactory way, we propose a unification-based word grammar, as the nucleus of our strategy, which takes into consideration word representations that are based on affixation and [stem stem] or [stem word] compounds. In our formalism, feature-passing operations are formulated with the use of the unification device, and phonological rules modeling the correspondence between lexical and surface forms apply at morpheme boundaries. In the paper, examples from Modern Greek illustrate our approach. Morpheme structures, stress, and morphologically conditioned phoneme changes are analyzed and generated in a principled way.

PIELG: A Protein Interaction Extraction Systemusing a Link Grammar Parser from Biomedical Abstracts

Due to the ever growing amount of publications about protein-protein interactions, information extraction from text is increasingly recognized as one of crucial technologies in bioinformatics. This paper presents a Protein Interaction Extraction System using a Link Grammar Parser from biomedical abstracts (PIELG). PIELG uses linkage given by the Link Grammar Parser to start a case based analysis of contents of various syntactic roles as well as their linguistically significant and meaningful combinations. The system uses phrasal-prepositional verbs patterns to overcome preposition combinations problems. The recall and precision are 74.4% and 62.65%, respectively. Experimental evaluations with two other state-of-the-art extraction systems indicate that PIELG system achieves better performance. For further evaluation, the system is augmented with a graphical package (Cytoscape) for extracting protein interaction information from sequence databases. The result shows that the performance is remarkably promising.

Semi-Automatic Analyzer to Detect Authorial Intentions in Scientific Documents

Information Retrieval has the objective of studying models and the realization of systems allowing a user to find the relevant documents adapted to his need of information. The information search is a problem which remains difficult because the difficulty in the representing and to treat the natural languages such as polysemia. Intentional Structures promise to be a new paradigm to extend the existing documents structures and to enhance the different phases of documents process such as creation, editing, search and retrieval. The intention recognition of the author-s of texts can reduce the largeness of this problem. In this article, we present intentions recognition system is based on a semi-automatic method of extraction the intentional information starting from a corpus of text. This system is also able to update the ontology of intentions for the enrichment of the knowledge base containing all possible intentions of a domain. This approach uses the construction of a semi-formal ontology which considered as the conceptualization of the intentional information contained in a text. An experiments on scientific publications in the field of computer science was considered to validate this approach.