Multilingualism in India is widespread due to its long history of foreign acquaintances. This leads to the presence of an audience familiar with conversing using more than one language. Additionally, due to the social media boom, the usage of multiple languages to communicate has become extensive. Hence, the need for a translation system that can serve the novice and monolingual user is the need of the hour. Such translation systems can be developed by methods such as statistical machine translation and neural machine translation, where each approach has its advantages as well as disadvantages. In addition, the parallel corpus needed to build a translation system, with code-mixed data, is not readily available. In the present work, we present two translation frameworks that can leverage the individual advantages of these pre-existing approaches by building an ensemble model that takes a consensus of the final outputs of the preceding approaches and generates the target output. The developed models were used for translating English-Bengali code-mixed data (written in Roman script) into their equivalent monolingual Bengali instances. A code-mixed to monolingual parallel corpus was also developed to train the preceding systems. Empirical results show improved BLEU and TER scores of 17.23 and 53.18 and 19.12 and 51.29, respectively, for the developed frameworks.

Abstract A system which is transparent and has less decision rules is an efficient, user‐convincing system and moreover convenient and manageable to fields like banking, business, and medical. Decision Tree (DT) is a data mining technique which is transparent and produces a set of production rules for decision‐making. However sometimes it creates some unnecessary and redundant rules which diminish its comprehensibility. Thus a system named Transparent Expert System of Rules (TESR) is proposed in this paper to efficiently improve comprehensibility of the DT by reducing the number of rules drastically without compromising accuracy. The proposed system adopts a Sequential Hill Climbing method with a flexible heuristic function to prune the insignificant rules from decision rules generated by DT. Finally, the proposed TESR system produces a transparent and comprehensible rule set for a decision. The proposed TESR performance is evaluated using 10 datasets and is compared with simple DT (ID3, C4.5, and Classification and Regression Trees) and also two of the existing transparent systems with respect to comprehensibility, accuracy, precision, recall, and F‐measures.

Summary The mathematical formula is one of the most vital components in a scientific document, which can explicitly describe various complex concepts and ideas. In addition to numerical calculations, they are also used to clarify definitions and disambiguate explanations transcribed in natural language. Nevertheless, the formulas have a noteworthy impact in the scientific documents, the existing information retrieval systems have limited access to scientific documents based on formulas‐based queries. To accomplish this, in this research, we have studied and implemented the formula embedding approach, which encodes the formula into the embedded vector. For encoding the formula, we have used pretrained sentence bidirectional encoder representations from transformers model. The proposed embedding model takes the latex formula as input and generates an upshot as a fixed dimensional embedding representation. In addition to this, the Siamese network is used to reform the semantic meaning of the formulas. Furthermore, the embedding of the formulas and the queried formula are compared, and cosine similarity is estimated. The performance of the suggested methodology is verified using a math stack exchange corpus of ARQMath 2020, and obtained results have shown a remarkable contribution in the task of formula retrieval.

Abstract Automatic segmentation and classification of breast tumours in ultrasound images using deep learning approaches can help early detect breast cancer. Such predictive modelling can potentially significantly improve the survival chances of the involved patients. Most of the typical deep convolutional neural network (CNN) based approaches consider segmentation and classification tasks separately. But this loses important supervisory information to help achieve better model training. This work proposes the integrated learning of both of these tasks in an end‐to‐end manner, using a multi‐task learning based approach. More specifically, a convolutional encoder‐decoder based architecture is coupled with a residual CNN for performing segmentation and classification together. The level‐wise feature maps from both the encoder and decoder parts of the segmentation network are utilized for classification in the proposed approach. From experimental analysis on a publicly available breast ultrasound image (BUSI) dataset, it has been observed that the proposed approach can achieve impressive performances, both with respect to tumour segmentation and classification. A mean test set AUC of 0.97 and a mean dice score of 0.74 is achieved, establishing a new state‐of‐the‐art performance on the BUSI dataset. From the impressive experimental observations, it can be concluded that learning to perform both segmentation and classification simultaneously can have a very high positive impact on the overall quality of the predictive model. Such observations suggest that the proposed approach can be beneficial in providing real‐time decision support to the involved diagnostic radiologists, which can help improve the survival chances of the corresponding patients.

Abstract Prediction of breast tumour malignancy using ultrasound imaging, is an important step for early detection of breast cancer. An efficient prediction system can be a great help to improve the survival chances of the involved patients. In this work, a machine learning (ML)—radiomics based classification pipeline is proposed, to perform this predictive modelling task, in a much more efficient manner. Multiple different types of image features of the region of interests are considered in this work, followed by a recursive feature elimination based feature selection step. Furthermore, a synthetic minority oversampling technique based step is also included in the pipeline, to deal with the class imbalance problem, that is often present in medical imaging datasets. Various ML models are considered in the subsequent model training phase, on a publicly available breast ultrasound image dataset (BUSI). From experimental analysis it has been observed that, shape, texture and histogram oriented gradients related features are the most informative, with respect to the predictive modelling task. Furthermore, it was observed that ensemble learners such as random forest, gradient boosting and AdaBoost classifiers are able to achieve significant results with respect to multiple evaluation metrics. The proposed approach achieved the state‐of‐the‐art accuracy, area under the curve, F1‐score and Mathews correlation coefficient values of 0.974, 0.97, 0.94 and 0.959, respectively, on the BUSI dataset. Such kind of impressive results suggest that the proposed approach can have a very high practical utility, in real medical diagnostic settings.

The field of speech recognition has seen tremendous advances in the recent past owing to the development of powerful deep learning architectures. However, the closely related fields of speech segmentation and di-arization are still primarily dominated by sophisticated variants of hierarchical clustering algorithms. We propose a powerful adaptation of the state-of-the-art Speech Recognition models for these tasks and demonstrate the effectiveness of our techniques on standard datasets. Our architectures are a combination of Bidirectional Long Short Term Memory (LSTM) Networks, Convolutional Networks, and Fully Connected Networks, trained by Gradient Descent to minimize the Cross Entropy and the Connectionist Temporal Classification (CTC) losses. We adapt the Libri Speech corpus for the task of segmentation and diarization. We obtained comparable results with respect to state-of-the-art in both tasks.

Information extraction in the medical domain is laborious and time-consuming due to the insufficient number of domainspecific lexicons and lack of involvement of domain experts such as doctors and medical practitioners.Thus, in the present work, we are motivated to design a new lexicon, WME 3.0 (WordNet of Medical Events), which contains over 10,000 medical concepts along with their part of speech, gloss (descriptive explanations), polarity score, sentiment, similar sentiment words, category, affinity score and gravity score features.In addition, the manual annotators help to validate the overall as well as individual category level of medical concepts of WME 3.0 using Cohen's Kappa agreement metric.The agreement score indicates almost correct identification of medical concepts and their assigned features in WME 3.0.

Music information retrieval has emerged as a mainstream research area in the past two decades. Experiments on music mood classification have been performed mainly on Western music based on audio, lyrics and a combination of both. Unfortunately, due to the scarcity of digitalized resources, Indian music fares poorly in music mood retrieval research. In this paper, we identified the mood taxonomy and prepared multimodal mood annotated datasets for Hindi and Western songs. We identified important audio and lyric features using correlation based feature selection technique. Finally, we developed mood classification systems using Support Vector Machines and Feed Forward Neural Networks based on the features collected from audio, lyrics, and a combination of both. The best performing multimodal systems achieved F-measures of 75.1 and 83.5 for classifying the moods of the Hindi and Western songs respectively using Feed Forward Neural Networks. A comparative analysis indicates that the selected features work well for mood classification of the Western songs and produces better results as compared to the mood classification systems for Hindi songs.

In order to overcome the lack of medical corpora, we have developed a WordNet for Medical Events (WME) for identifying medical terms and their sense related information using a seed list.The initial WME resource contains 1654 medical terms or concepts.In the present research, we have reported the enhancement of WME with 6415 number of medical concepts along with their conceptual features viz.Parts-of-Speech (POS), gloss, semantics, polarity, sense and affinity.Several polarity lexicons viz.SentiWordNet, SenticNet, Bing Liu's subjectivity list and Taboda's adjective list were introduced with WordNet synonyms and hyponyms for expansion.The semantics feature guided us to build a semantic co-reference relation based network between the related medical concepts.These features help to prepare a medical concept network for better sense relation based visualization.Finally, we evaluated with respect to Adaptive Lesk Algorithm and conducted an agreement analysis for validating the expanded WME resource.

The paper presents an approach to identify the emotions of the bloggers on different topics provided in the Bengali blog documents. The rule based identification of emotion holders and topics along with their corresponding emotional expressions forms the baseline system. A Support Vector Machine (SVM) based supervised framework is also employed to identify the three components from the blog sentences and it outperforms the baseline system. As the topic of a document is not always conveyed at the sentence level, the similarity between a document's overall topic and sentential topic is measured through semantic clustering approach. Two different approaches are adopted to identify the many to many relationships among the holders and topics on Ekman's six emotions. One is based from the perspectives of the holders and other is with respect to topics. The two way evaluation of Ekman's six emotions achieves precision, recall and F-Score of 65.02%, 76.23% and 70.18% for 10 bloggers and 71.02%, 78.47% and 74.55% for 8 different topics on 512 test sentences respectively.