BERT for Conversational Question Answering Systems Using Semantic Similarity Estimation

Most of the questions from users lack the context needed to thoroughly understand the problemat hand,thus making the questions impossible to answer.Semantic Similarity Estimation is based on relating user’s questions to the context from previous Conversational Search Systems(CSS)to provide answers without requesting the user’s context.It imposes constraints on the time needed to produce an answer for the user.The proposed model enables the use of contextual data associated with previous Conversational Searches(CS).While receiving a question in a new conversational search,the model determines the question that refers tomore pastCS.Themodel then infers past contextual data related to the given question and predicts an answer based on the context inferred without engaging in multi-turn interactions or requesting additional data from the user for context.This model shows the ability to use the limited information in user queries for best context inferences based on Closed-Domain-based CS and Bidirectional Encoder Representations from Transformers for textual representations.

Context-Aware Collaborative Filtering Framework for Rating Prediction Based on Novel Similarity Estimation

Recommender systems are rapidly transforming the digital world into intelligent information hubs.The valuable context information associated with the users’prior transactions has played a vital role in determining the user preferences for items or rating prediction.It has been a hot research topic in collaborative filtering-based recommender systems for the last two decades.This paper presents a novel Context Based Rating Prediction(CBRP)model with a unique similarity scoring estimation method.The proposed algorithm computes a context score for each candidate user to construct a similarity pool for the given subject user-item pair and intuitively choose the highly influential users to forecast the item ratings.The context scoring strategy has an inherent capability to incorporate multiple conditional factors to filter down the most relevant recommendations.Compared with traditional similarity estimation methods,CBRP makes it possible for the full use of neighboring collaborators’choice on various conditions.We conduct experiments on three publicly available datasets to evaluate our proposed method with random user-item pairs and got considerable improvement in prediction accuracy over the standard evaluation measures.Also,we evaluate prediction accuracy for every user-item pair in the system and the results show that our proposed framework has outperformed existing methods.

Near-duplicate document detection with improved similarity measurement

To quickly find documents with high similarity in existing documentation sets, fingerprint group merging retrieval algorithm is proposed to address both sides of the problem:a given similarity threshold could not be too low and fewer fingerprints could lead to low accuracy. It can be proved that the efficiency of similarity retrieval is improved by fingerprint group merging retrieval algorithm with lower similarity threshold. Experiments with the lower similarity threshold r=0.7 and high fingerprint bits k=400 demonstrate that the CPU time-consuming cost decreases from 1 921 s to 273 s. Theoretical analysis and experimental results verify the effectiveness of this method.