Artificial Intelligence provides accurate predictions for critical applications (e.g., healthcare, finance), but lacks the ability to explain its internal mechanism in most applications which require high interaction with humans. Even if many studies analyze machine learning models and their learning behaviour and eventually provide an interpretation of the inner mechanics of these models, these studies often entail a simpler surrogate model generate explanations by producing a piece of interpretable information such as feature scores. The crucial caveat against these studies is the lack of human involvement in the design and evaluation of explanations, consequently giving rise to trust issues and lack of acceptance and understanding. To this end, we address this limitation by involving humans in the counterfactual explanation generation process which is enriched with user feedback and thus enhancing the automated explanations which are better aligned with user expectations. In this paper, we propose a user feedback based counterfactual explanation approach for explainable Artificial Intelligence. In our work, we utilize feedback in two ways: first, feedback to customize the explanations locally that helps in providing the neighbourhood to discern the feasible explanations; and second, to evaluate the generated explanations.INDEX TERMS Counterfactual explanations, Explainable AI, Human-in-the-loop, Interactive machine learning, User feedback.
Dictionaries not only are the source of getting meanings of the word but also serve the purpose of comprehending the context in which the words are used. For such purpose, we see a small sentence as an example for the very word in comprehensive book-dictionaries and more recently in online dictionaries. The lexicographers perform a very meticulous activity for the elicitation of Good Dictionary EXamples (GDEX)—a sentence that is best fit in a dictionary for the word’s definition. The rules for the elicitation of GDEX are very strenuous and require a lot of time for committing the manual process. In this regard, this paper focuses on two major tasks, i.e., the development of labelled corpora for top 3K English words through the usage of distant supervision approach and devising a state-of-the-art artificial intelligence-based automated procedure for discriminating Good Dictionary EXamples from the bad ones. The proposed methodology involves a suite of five machine learning (ML) and five word embedding-based deep learning (DL) architectures. A thorough analysis of the results shows that GDEX elicitation can be done by both ML and DL models; however, DL-based models show a trivial improvement of 3.5% over the conventional ML models. We find that the random forests with parts-of-speech information and word2vec-based bidirectional LSTM are the most optimal ML and DL combinations for automated GDEX elicitation; on the test set, these models, respectively, secured a balanced accuracy of 73% and 77%.
The Evidence-Based Medicine (EBM) is emerged as the helpful practice for medical practitioners to make decisions with available shreds of evidence along with their professional expertise. In EBM, the medical practitioners suggest the medication on the basis of underlying information of patients descriptions and medical records (mostly available in textual form). This paper presents a novel and efficient method for predicting the correct disease. Since these type of tasks are generally accounted as the multi-class classifying problem, therefore, a large number of records are needed, so a large number of records will be entertained in higher n-dimensional space. Our system, as proposed in this paper, will utilise the key-phrases extraction techniques to scoop out the meaningful information to reduce the size of textual dimension, and, the suite of machine learning algorithms for classifying the diseases efficiently. We have tested the proposed approach on 6 different diseases i.e. Asthma, Hypertension, Diabetes, Fever, Abdominal issues, and Heart problems over the dataset of 690 patients. With key-phrases tested in the range [3,7] features, SVM has shown the highest (93.34%, 95%) F1-score and accuracy.
The semantic coexistence is the reason to adopt the language spoken by other people. In such human habitats, different languages share words typically known as loan words which appears not only as of the principal medium of enriching language vocabulary but also for creating influence upon each other for building stronger relationships and forming multilingualism. In this context, the spoken words are usually common but their writing scripts vary or the language may have become a digraphia. In this paper, we presented the similarities and relatedness between Hindi and Urdu (that are mutually intelligible and major languages of Indian sub-continent). In general, the method modifies edit-distance; and works in the fashion that instead of using alphabets from the words it uses articulatory features from the International Phonetic Alphabets (IPA) to get the phonetic edit distance. This paper also shows the results for the languages consonant under the method which quantifies the evidence that the Urdu and Hindi languages are 67.8% similar on average despite the script differences.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.