Knowledge-based Question Answering System Research Articles

Knowledge-Based Reasoning Network for Relation Detection.

With the rapid growth of large-scale knowledge bases (KBs), knowledge base question answering (KBQA) has attracted increasing attention recently. Relation detection plays an important role in the KBQA system, which finds a compatible answer by analyzing the semantics of questions and querying and reasoning with multiple KB triples. Significant progress has been made by deep neural networks. However, existing methods often concern on detecting single-hop relation without path reasoning, and a few of these methods exploit the multihop relation reasoning, which involves the answer reasoning from the noisy and abundant relational paths in the KB. Meanwhile, the relatedness between question and answer candidates has received little attention and remains unsolved. This article proposes a novel knowledge-based reasoning network (KRN) for relation detection, including both single-hop relation and multihop relation. To address the semantic gap problem in question-answer interaction, we first learn attentive question representations according to the influence of answer aspects. Then, we learn the single-hop relation sequence through different levels of abstraction and adopt the KB entity and structure information to denoise the multihop relation detection task. Finally, we adopt a Siamese network to measure the similarity between question representation and relation representation for both single-hop and multihop relation KBQA tasks. We conduct experiments on two well-known benchmarks, SimpleQuestions and WebQSP, and the results show the superiority of our approach over the state-of-the-art models for both single-hop and multihop relation detection. Our model also achieves a significant improvement over existing methods on KBQA end task. Further analysis demonstrates the robustness and the applicability of the proposed approach.

Domain Knowledge Graph Question Answering Based on Semantic Analysis and Data Augmentation

Information retrieval-based question answering (IRQA) and knowledge-based question answering (KBQA) are the main forms of question answering (QA) systems. The answer generated by the IRQA system is extracted from the relevant text but has a certain degree of randomness, while the KBQA system retrieves the answer from structured data, and its accuracy is relatively high. In the field of policy and regulations such as household registration, the QA system requires precise and rigorous answers. Therefore, we design a QA system based on the household registration knowledge graph, aiming to provide rigorous and accurate answers for relevant household registration inquiries. The QA system uses a semantic analysis-based approach to simplify one question into a simple problem consisting of a single event entity and a single intention relationship, and quickly generates accurate answers by searching in the household registration knowledge graph. Due to the scarcity and imbalance of QA corpus data in the field of household registration, we use GPT3.5 to augment the collected questions dataset and explore the impact of data augmentation on the QA system. The experiment results show that the accuracy rate of the QA system using the augmented dataset reaches 93%, which is 6% higher than before.

Question Decomposition Tree for Answering Complex Questions over Knowledge Bases

Knowledge base question answering (KBQA) has attracted a lot of interest in recent years, especially for complex questions which require multiple facts to answer. Question decomposition is a promising way to answer complex questions. Existing decomposition methods split the question into sub-questions according to a single compositionality type, which is not sufficient for questions involving multiple compositionality types. In this paper, we propose Question Decomposition Tree (QDT) to represent the structure of complex questions. Inspired by recent advances in natural language generation (NLG), we present a two-staged method called Clue-Decipher to generate QDT. It can leverage the strong ability of NLG model and simultaneously preserve the original questions. To verify that QDT can enhance KBQA task, we design a decomposition-based KBQA system called QDTQA. Extensive experiments show that QDTQA outperforms previous state-of-the-art methods on ComplexWebQuestions dataset. Besides, our decomposition method improves an existing KBQA system by 12% and sets a new state-of-the-art on LC-QuAD 1.0.

Knowledge base question answering via path matching

Knowledge base question answering (KBQA) refers to combining the information in the knowledge base to obtain an answer for an objective question. However, most of the existing methods tend to add a large number of hand-crafted features or constraints to improve the performance of the model. This makes the KBQA system more and more complex, but the improvement is limited. In this work, we try a novel method without any hand-crafted features or constraints, which transforms this problem into a text matching problem. In this method, a question and a series of edges in knowledge bases (KBs) are treated as two pieces of text that need to be matched. The network to match the two texts called Path Matching Model (PMM). On the WebQuestions benchmark, our method has 3% improvement compared to the state-of-the-art method.

Chinese Named Entity Recognition Based on Knowledge Based Question Answering System

The KBQA (Knowledge-Based Question Answering) system is an essential part of the smart customer service system. KBQA is a type of QA (Question Answering) system based on KB (Knowledge Base). It aims to automatically answer natural language questions by retrieving structured data stored in the knowledge base. Generally, when a KBQA system receives the user’s query, it first needs to recognize topic entities of the query, such as name, location, organization, etc. This process is the NER (Named Entity Recognition). In this paper, we use the Bidirectional Long Short-Term Memory-Conditional Random Field (Bi-LSTM-CRF) model and introduce the SoftLexicon method for a Chinese NER task. At the same time, according to the analysis of the characteristics of application scenario, we propose a fuzzy matching module based on the combination of multiple methods. This module can efficiently modify the error recognition results, which can further improve the performance of entity recognition. We combine the NER model and the fuzzy matching module into an NER system. To explore the availability of the system in some specific fields, such as a power grid field, we utilize the power grid-related original data collected by the Hebei Electric Power Company to improve our system according to the characteristics of data in the power grid field. We innovatively make the dataset and high-frequency word lexicon in the power grid field, which makes our proposed NER system perform better in recognizing entities in the field of power grid. We used the cross-validation method for validation. The experimental results show that the F1-score of the improved NER model on the power grid dataset reaches 92.43%. After processing the recognition results by using the fuzzy matching module, about 99% of the entities in the test set can be correctly recognized. It proves that the proposed NER system can achieve excellent performance in the application scenario of a power grid. The results of this work will also fill the gap in the research of intelligent customer-service-related technologies in the power grid field in China.

Intelligent question and answer analysis model of power ICT based on BI-LSTM-CRF

With the deepening of the country’s digital transformation and the development of big data artificial intelligence software definition and other technologies, customers’ demand for IT services is constantly increasing. In the electric power industry, the front-end knowledge base for traditional customer service lacks self-learning ability, the accumulated customer service data in the middle cannot be analyzed and utilized effectively, the back-end quality inspection was not fully covered and lacked emotion recognition, etc. Apply artificial intelligence, information and communication technology and big data technology to power ICT customer service. It is proposed to construct a network model by combining conditional random airport with the long- and short-term memory neural network, and to realize the intelligent customer service model combined with human–computer interaction by constructing an intelligent knowledge base and the information system fault association analysis model, so as to improve the extraction performance of context information and establish a knowledge base question answering system in the field of power service. Through the comparative analysis of experimental data, the proposed model has achieved good results and can be effectively applied to the power industry to improve customer service satisfaction.

A Semantic Parsing and Reasoning-Based Approach to Knowledge Base Question Answering

Knowledge Base Question Answering (KBQA) is a task where existing techniques have faced significant challenges, such as the need for complex question understanding, reasoning, and large training datasets. In this work, we demonstrate Deep Thinking Question Answering (DTQA), a semantic parsing and reasoning-based KBQA system. DTQA (1) integrates multiple, reusable modules that are trained specifically for their individual tasks (e.g. semantic parsing, entity linking, and relationship linking), eliminating the need for end-to-end KBQA training data; (2) leverages semantic parsing and a reasoner for improved question understanding. DTQA is a system of systems that achieves state-of-the-art performance on two popular KBQA datasets.

A Global–Local Attentive Relation Detection Model for Knowledge-Based Question Answering

Knowledge-based question answering (KBQA) is an essential but challenging task for artificial intelligence and natural language processing. A key challenge pertains to the design of effective algorithms for relation detection. Conventional methods model questions and candidate relations separately through the knowledge bases (KBs) without considering the rich word-level interactions between them. This approach may result in local optimal results. This article presents a global–local attentive relation detection model (GLAR) that utilizes the local module to learn the features of word-level interactions and employs the global module to acquire nonlinear relationships between questions and their candidate relations located in KBs. This article also reports on the application of an end-to-end retrieval-based KBQA system incorporating the proposed relation detection model. Experimental results obtained on two datasets demonstrated GLAR's remarkable performance in the relation detection task. Furthermore, the functioning of end-to-end KBQA systems was significantly improved through the relation detection model, whose results on both datasets outperformed even state-of-the-art methods. Impact Statement —Knowledge-based question answering (KBQA) aims at answering user questions posed over the knowledge bases (KBs). KBQA helps users access knowledge in the KBs more easily, and it works on two subtasks: entity mention detection and relation detection. While existing relation detection algorithms perform well on the global representation of questions and relations sequences, they ignore some local semantic information on interaction cases between them. The technology proposed in this article takes both global and local interactions into account. With superior improvement on two relation detection tasks and two KBQA end tasks, the technology provides more precise answers. It could be used in more applications, including intelligent customer service, intelligent finance, and others.

DAM: Transformer-based relation detection for Question Answering over Knowledge Base

Relation Detection is a core component of Knowledge Base Question Answering (KBQA). In this paper, we propose a Transformer-based deep attentive semantic matching model (DAM), to identify the KB relations corresponding to the questions. The DAM is completely based on the attention mechanism and applies the fine-grained word-level attention to enhance the matching of questions and relations. On the basis of the DAM, we build a three-stage KBQA pipeline system. The experimental results on multiple benchmarks demonstrate that our DAM model outperforms previous methods on relation detection. In addition, our DAM-based KBQA system also achieves state-of-the-art results on multiple datasets.

Adversarial Training Improved Multi-Path Multi-Scale Relation Detector for Knowledge Base Question Answering

Knowledge Base Question Answering (KBQA) is a promising approach for users to access substantial knowledge and has become a research focus in recent years. Our paper focuses on relation detection, a subtask of KBQA and proposes an adversarial training improved multi-path multi-scale relation detector (AdvT-MMRD) to improve the performance of a common KBQA system. To solve the problem of matching the casual form of a question with the logical form of a predicate, we use question pattern-relation matching, in which an attention-based bidirectional recurrent neural network with gated recurrent units (Bi-GRUs) is used to match semantic similarity and a convolutional neural network (CNN) is used to learn literal similarity between question and relation. We also explore two ways to measure the relevance of entity type-relation pairs through several level representations. Additionally, an adversarial training strategy is conducted to enhance our model. The experimental results demonstrate that our approach not only achieves a state-of-the-art accuracy of 93.8% on relation detection task, but contributes our KBQA system to reaching an outstanding accuracy of 79.0% on the SimpleQuestions benchmark.

Development and statistical validation of an ontology-based question answering system

Question answering systems in general use external knowledge sources for extracting answers. Domain specific question answering systems require pre-constructed knowledge sources like domain ontology. A major challenge in knowledge-based question answering system development is building a huge knowledge base with the objective and correct factual knowledge in the preferred domain. The process of collecting useful knowledge from various sources and maintaining in a knowledge repository is a useful process for providing required answer on demand with greater accuracy and efficiency. In this paper an experimental framework has been proposed for concept-relational ontology-based question answering process. The question answering framework proposed in this paper includes two subsystems: 1) a dynamic concept relational ontology construction module, is capable to extract new concepts from the web and incorporate the extracted knowledge into the concept relational ontology knowledge base; 2) the answer extraction module formulates the query string from the natural language question according to the expected answer and retrieves the information from the ontology for answer formation. Furthermore, a novel statistical validation framework for evaluating the prototype implementation of the proposed question answering system is introduced.

A Novel Approach of Collaborative KBQA System using Ontology

The objective of the research is to provide relevant answers for the questions posted by the learners using Collaborative Knowledge Based Question Answering System (CKBQA) of Knowledge Extraction which provide the most suitable answers by sharing the ideas of various learners, when the user needs information. In the modern era numerous information available in the World Wide Web which is too difficult to get the required information. CKBQA system aims at retrieving precise information from a large collection of documents. It provides the most relevant answers rather than the irrelevant information by applying Latent Semantic Analysis. In collaborative learning the users benefit when the learner exposed to diverse viewpoints from the other learners with varied backgrounds and provides the best interactive teaching learning method where the interaction taken place between the learners and also the learners with the exports. The CKBQA system consists of four phases such as Question Preprocessing, Answer Evaluation, Concept Mapping of question with their answer and voting. Ontology plays the vital role for checking the semantic nature of the question and the answer. Sample of 100 questions with their Answers were taken and tested for their various question types and also checked with resoner which gave 89% of correctness.

Question answering based on pervasive agent ontology and Semantic Web

Semantic Web technologies bring new benefits to knowledge-based question answering system. Especially, ontology is becoming the pivotal methodology to represent domain-specific conceptual knowledge in order to promote the semantic capability of a QA system. In this paper we present a QA system in which the domain knowledge is represented by means of ontology. In addition, personalized services are enabled through modeling users’ profiles in the form of pervasive agent ontology, and a Chinese Natural Language human–machine interface is implemented mainly through a NL parser in this system. An initial evaluation result shows the feasibility to build such a semantic QA system based on pervasive agent ontology, the effectivity of personalized semantic QA, the extensibility of pervasive agent ontology and knowledge base, and the possibility of self-produced knowledge-based on semantic relations in the pervasive agent ontology.

A knowledge-based question answering system for B2C eCommerce

The evolution of Business-to-Consumer (B2C) eCommerce has been formed through various generations. Last models of B2C eCommerce are comparative shopping systems that connect to multiple vendors’ databases and collect the information requested by the user. The comparative result obtained is then displayed in a tabular format in the user’s browser. Although this scenario is much better than the multiple manual site comparisons, user still needs to face inconsistent user interfaces when he is linked from the comparison site to the actual purchasing site for shopping. Therefore, user has to learn logics of each site’s user interface. In this paper, we propose a question answering system based on natural language processing techniques for retail (B2C) in eCommerce. This system gets a question in natural language formats, decomposes it to keywords, and extracts constraints automatically. Corresponding answers are then retrieved from the vendors’ Web sites by exploiting the question constraints.