Natural Language Question Answering Research Articles

Enhancing service excellence: analyzing natural language question answering with advanced cosine similarity

<span lang="EN-US">Information related to student services in higher education must be produced and disseminated in various forms. Covid-19 pandemic, student services with a remote model related to this question and answer become very important. To carry out this automation process, the advanced cosine similarity method is used to check the similarity of the questions to the database and statistics to calculate the similarity value of each word. The proposed paper proceeds with three phases. The first stage to solve this problem is the data processed in question; the professional next step is word insertion. It converts alphanumeric words to vector format. Each word is a vector that represents a point in space with a certain dimension. The recommended advanced cosine similarity data still must be analyzed into a statistical approach. We will measure accuracy to get results so that optimal results and answers are obtained, research procedures are carried out based on literature study, initial data collection and observation, system development, system testing, system analysis, and system evaluation. This research implemented in universities with student chat automation applications providing an accuracy 83.90% given by natural language question answering system (NLQAS) so that it can improve excellent service in universities.</span>

Around the GLOBE: Numerical Aggregation Question-answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks

One of the key AI tools for textual corpora exploration is natural language question-answering (QA). Unlike keyword-based search engines, QA algorithms receive and process natural language questions and produce precise answers to these questions, rather than long lists of documents that need to be manually scanned by the users. State-of-the-art QA algorithms based on DNNs were successfully employed in various domains. However, QA in the genealogical domain is still underexplored, and researchers in this field (and other fields in humanities and social sciences) can highly benefit from the ability to ask questions in natural language, receive concrete answers, and gain insights hidden within large corpora. While some research has been recently conducted for factual QA in the genealogical domain, to the best of our knowledge, there is no previous research on the more challenging task of numerical aggregation QA (i.e., answering questions combining aggregation functions, e.g., count, average, max). Numerical aggregation QA is critical for distant reading and analysis for researchers (and the general public) interested in investigating cultural heritage domains. Therefore, in this study, we present a new end-to-end methodology for numerical aggregation QA for genealogical trees that includes (1) an automatic method for training dataset generation, (2) a transformer-based table selection method, and (3) an optimized transformer-based numerical aggregation QA model. The findings indicate that the proposed architecture, GLOBE, outperforms the state-of-the-art models and pipelines by achieving 87% accuracy for this task compared to only 21% by current state-of-the-art models. This study may have practical implications for genealogical information centers and museums, making genealogical data research easy and scalable for experts as well as the general public.

KEBLM: Knowledge-Enhanced Biomedical Language Models

Pretrained language models (PLMs) have demonstrated strong performance on many natural language processing (NLP) tasks. Despite their great success, these PLMs are typically pretrained only on unstructured free texts without leveraging existing structured knowledge bases that are readily available for many domains, especially scientific domains. As a result, these PLMs may not achieve satisfactory performance on knowledge-intensive tasks such as biomedical NLP. Comprehending a complex biomedical document without domain-specific knowledge is challenging, even for humans. Inspired by this observation, we propose a general framework for incorporating various types of domain knowledge from multiple sources into biomedical PLMs.We encode domain knowledge using lightweight adapter modules, bottleneck feed-forward networks that are inserted into different locations of a backbone PLM. For each knowledge source of interest, we pretrain an adapter module to capture the knowledge in a self-supervised way. We design a wide range of self-supervised objectives to accommodate diverse types of knowledge, ranging from entity relations to description sentences.Once a set of pretrained adapters is available, we employ fusion layers to combine the knowledge encoded within these adapters for downstream tasks. Each fusion layer is a parameterized mixer of the available trained adapters that can identify and activate the most useful adapters for a given input. Our method diverges from prior work by including a knowledge consolidation phase, during which we teach the fusion layers to effectively combine knowledge from both the original PLM and newly-acquired external knowledge using a large collection of unannotated texts. After the consolidation phase, the complete knowledge-enhanced model can be fine-tuned for any downstream task of interest to achieve optimal performance.Extensive experiments on many biomedical NLP datasets show that our proposed framework consistently improves the performance of the underlying PLMs on various downstream tasks such as natural language inference, question answering, and entity linking. These results demonstrate the benefits of using multiple sources of external knowledge to enhance PLMs and the effectiveness of the framework for incorporating knowledge into PLMs. While primarily focused on the biomedical domain in this work, our framework is highly adaptable and can be easily applied to other domains, such as the bioenergy sector.

SPARQL Generation with an NMT-based Approach

SPARQL is a powerful query language which has been widely used in various natural language question answering (QA) systems. As the advances of deep neural networks, Neural Machine Translation (NMT) models are employed to directly translate natural language questions to SPARQL queries in recent years. In this paper, we propose an NMT-based approach with Transformer model to generate SPARQL queries. Transformer model is chosen due to its relatively high efficiency and effectiveness. We design a format to encode a SPARQL query into a simple sequence with only RDF triples reserved. The main purpose of this step is to shorten the sequences and reduce the complexity of the target language. Moreover, we employ entity type tags to further resolve mistranslated problems. The proposed approach is evaluated against three open-domain question answering datasets (QALD-7, QALD-8, and LC-QuAD) on BLEU score and accuracy, and obtains outstanding results (83.49%, 90.13%, and 76.32% on BLEU score, respectively) which considerably outperform all known studies.

Towards combinational relation linking over knowledge graphs

Given a knowledge graph and a natural language phrase, relation linking aims to find relations (predicates or properties) from the underlying knowledge graph to match the phrase. It is very useful in many applications, such as natural language question answering, personalized recommendation and text summarization. However, the previous relation linking algorithms usually produce a single relation for the input phrase and pay little attention to the more general and challenging problem, i.e., combinational relation linking that extracts a subgraph pattern to match the compound phrase (e.g. father-in-law). In this paper, we focus on the task of combinational relation linking over knowledge graphs. To resolve the problem, we define several elementary meta patterns which can be used to build any combinational relation. Then we design a systematic method based on the data-driven relation assembly technique, which is performed under the guidance of meta patterns. To enhance the system’s understanding ability, we introduce external knowledge during the linking process. Finally, extensive experiments over the real knowledge graph confirm the effectiveness of the proposed method.

MKPM: Multi keyword-pair matching for natural language sentences

Sentence matching is widely used in various natural language tasks, such as natural language inference, paraphrase identification and question answering. For these tasks, we need to understand the logical and semantic relationship between two sentences. Most current methods use all information within a sentence to build a model and hence determine its relationship to another sentence. However, the information contained in some sentences may cause redundancy or introduce noise, impeding the performance of the model. Therefore, we propose a sentence matching method based on multi keyword-pair matching (MKPM), which uses keyword pairs in two sentences to represent the semantic relationship between them, avoiding the interference of redundancy and noise. Specifically, we first propose a sentence-pair-based attention mechanism sp-attention to select the most important word pair from the two sentences as a keyword pair, and then propose a Bi-task architecture to model the semantic information of these keyword pairs. The Bi-task architecture is as follows: 1. In order to understand the semantic relationship at the word level between two sentences, we design a word-pair task (WP-Task), which uses these keyword pairs to complete sentence matching independently. 2. We design a sentence-pair task (SP-Task) to understand the sentence level semantic relationship between the two sentences by sentence denoising. Through the integration of the two tasks, our model can understand sentences more accurately from the two granularities of word and sentence. Experimental results show that our model can achieve state-of-the-art performance in several tasks. Our source code is publicly available1.

Mining the web to discover acronym‐definitions based on sequence labeling and iterative query expansion model

SummaryFinding definitions associated with an acronym is a constructive task to many applications like web search, information retrieval, natural language processing, ontology mapping, and question answering. A large‐scale manually built acronym‐definition repositories are available online but updating is a difficult task. To address this problem, previous research works used either heuristics or a machine learning approach to automate the detection of acronym‐definition pairs. This article presents a heuristics approach based on a rule‐based sequence‐labeling model, for finding the list of definitions associated with an acronym from the Web. The organic search result of the web page includes website title, URL, Meta description, and site links. In the proposed work, web pages of the search engine are used as corpus and sequence‐labeling task is done through character and word level mapping schemes. In these schemes, the desirable properties of the definition are expressed by using rules. Each identified definition is validated through a collocation measure. Besides, the obtained results are assessed against a manually built acronym/definitions repository: Acronym Finder. The proposed model certainly improves the coverage of manual repositories maintaining high precision and recall.

Natural language question answering over knowledge graph: the marriage of SPARQL query and keyword search

Natural language question answering over knowledge graph has received widespread attention. However, the existing methods always aim to improve every phase of natural language question answering and neglect the defects; namely, not all query intentions can be identified and mapped to the correct SPARQL statement. In contrast, keyword search relies on the links among multiple keywords regardless of the exact logic relations in question. Therefore, we propose a framework (abbreviated as NLQSK for title of this paper) that introduces keyword search into natural language question answering to compensate for the defects mentioned above. First, we translate a natural language question into top-k SPARQL statements by using the existing methods. Second, we transform the valuable information that cannot be identified and mapped into keywords, and then, return the neighboring information in a knowledge graph by keyword index. Third, we combine the SPARQL block (i.e., the SPARQL statement and its result) and keyword search to produce the answer to the natural language question. Finally, the experiments on the benchmark dataset confirm that keyword search can compensate for the defects of natural language question answering and that NLQSK can answer more questions than the existing state-of-the-art question answering systems.

Better Modeling the Hierarchical Structure of Language for Sentence Semantic Matching

Sentence semantic matching requires understanding the semantic relationship between two sentences, which is widely used in various natural language tasks such as paraphrase identification, natural language inference and question answering. Usually, the underlying structure of sentence is not strictly sequential, this structure is hierarchical. This paper studies how to better model the hierarchical structure of sentence for semantic matching. Recent research suggests that BERT implicitly captures classical, tree-like structures. Based on this, this paper proposes to further enhance the strength of modeling hierarchical structure of language with an advanced variant of LSTM – Ordered Neurons LSTM(ON-LSTM), which introduces a syntax-oriented inductive bias to perform the composition of classical tree structure. Experimental results demonstrate that the proposed approach, which enhances hierarchical structure of language, significantly improves the performance of sentence semantic matching.

Combining Local and Global Features Into a Siamese Network for Sentence Similarity

Sentence similarity is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. However, a variety of linguistic expressions and ambiguities of words in sentences make it difficult to measure sentence similarity. Many studies show that using local features or global features of a sentence will produce satisfactory sentence representations that can be utilized to measure sentence similarity. Local features reflect the relationships of adjacent words for each sentence and the sequence information of a sentence are usually expressed by global features. However, local features lack abilities to capture sequence information while a small amount of extracted global features is not enough to produce sentence representations with good qualities. In this paper, we propose A Hybrid Model combining Local and Global features into a Siamese Network (HM-LGSN) for sentence similarity calculation. We first propose a new convolution neural network architecture called group convolution neural network to extract the most representative local features (or word semantic features). Then we combine these new features with pre-trained embeddings of words as input to the Bidirectional Gated Recurrent Units to extract global features of sentences. Finally, we select the global features to form sentence representations and calculate sentence similarity through Manhattan distance. The experimental results on SICK, MSRVID, STS-B datasets show that the accuracy of our proposed model is significantly improved by combining local features and global features.

QUASE: AN Ontology-Based Domain Specific Natural Language Question Answering System

Since early days Question Answering (QA) has been an intuitive way of understanding the concept by humans. Considering its inevitable importance it has been introduced to children from very early age and they are promoted to ask more and more questions. With the progress in Machine Learning & Ontological semantics, Natural Language Question Answering (NLQA) has gained more popularity in recent years. In this paper QUASE (QUestion Answering System for Education) question answering system for answering natural language questions has been proposed which help to find answer for any given question in a closed domain containing finite set of documents. The QA system mainly focuses on factoid questions. QUASE has used Question Taxonomy for Question Classification. Several Natural Language Processing techniques like Part of Speech (POS) tagging, Lemmatization, Sentence Tokenization have been applied for document processing to make search better and faster. DBPedia ontology has been used to validate the candidate answers. By application of this system the learners can gain knowledge on their own by getting precise answers to their questions asked in natural language instead of getting back merely a list of documents. The precision, recall and F measure metrics have been taken into account to evaluate the performance of answer type evaluation. The metric Mean Reciprocal Rank has been considered to evaluate the performance of QA system. Our experiment has shown significant improvement in classifying the questions in to correct answer types over other methods with approximately 91% accuracy and also providing better performance as a QA system in closed domain search.

Intelligent Interaction with Virtual Geographical Environments Based on Geographic Knowledge Graph

The core of intelligent virtual geographical environments (VGEs) is the formal expression of geographic knowledge. Its purpose is to transform the data, information, and scenes of a virtual geographic environment into “knowledge” that can be recognized by computer, so that the computer can understand the virtual geographic environment more easily. A geographic knowledge graph (GeoKG) is a large-scale semantic web that stores geographical knowledge in a structured form. Based on a geographic knowledge base and a geospatial database, intelligent interactions with virtual geographical environments can be realized by natural language question answering, entity links, and so on. In this paper, a knowledge-enhanced Virtual geographical environments service framework is proposed. We construct a multi-level semantic parsing model and an enhanced GeoKG for structured geographic information data, such as digital maps, 3D virtual scenes, and unstructured information data. Based on the GeoKG, we propose a bilateral LSTM-CRF (long short-term memory- conditional random field) model to achieve natural language question answering for VGEs and conduct experiments on the method. The results prove that the method of intelligent interaction based on the knowledge graph can bridge the distance between people and virtual environments.

Semantic Sentence Matching with Densely-Connected Recurrent and Co-Attentive Information

Sentence matching is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. For these tasks, understanding logical and semantic relationship between two sentences is required but it is yet challenging. Although attention mechanism is useful to capture the semantic relationship and to properly align the elements of two sentences, previous methods of attention mechanism simply use a summation operation which does not retain original features enough. Inspired by DenseNet, a densely connected convolutional network, we propose a densely-connected co-attentive recurrent neural network, each layer of which uses concatenated information of attentive features as well as hidden features of all the preceding recurrent layers. It enables preserving the original and the co-attentive feature information from the bottommost word embedding layer to the uppermost recurrent layer. To alleviate the problem of an ever-increasing size of feature vectors due to dense concatenation operations, we also propose to use an autoencoder after dense concatenation. We evaluate our proposed architecture on highly competitive benchmark datasets related to sentence matching. Experimental results show that our architecture, which retains recurrent and attentive features, achieves state-of-the-art performances for most of the tasks.

A Review of the Analytics Techniques for an Efficient Management of Online Forums: An Architecture Proposal

E-learning is a response to the new educational needs of society and an important development in information and communication technologies because it represents the future of the teaching and learning processes. However, this trend presents many challenges, such as the processing of online forums which generate a huge number of messages with an unordered structure and a great variety of topics. These forums provide an excellent platform for learning and connecting students of a subject but the difficulty of following and searching the vast volume of information that they generate may be counterproductive. The main goal of this paper is to review the approaches and techniques related to online courses in order to present a set of learning analytics techniques and a general architecture that solve the main challenges found in the state of the art by managing them in a more efficient way: 1) efficient tracking and monitoring of forums generated; 2) design of effective search mechanisms for questions and answers in the forums; and 3) extraction of relevant key performance indicators with the objective of carrying out an efficient management of online forums. In our proposal, natural language processing, clustering, information retrieval, question answering, and data mining techniques will be used.

Querying biomedical Linked Data with natural language questions

Recent and intensive research in the biomedical area enabled to accumulate and disseminate biomedical knowledge through various knowledge bases increasingly available on the Web. The exploitation of this knowledge requires to create links between these bases and to use them jointly. Linked Data, the SPARQL language and interfaces in natural language question answering provide interesting solutions for querying such knowledge bases. However, while using biomedical Linked Data is crucial, life-science researchers may have difficulties using the SPARQL language. Interfaces based on natural language question answering are recognized to be suitable for querying knowledge bases. In this paper, we propose a method for translating natural language questions into SPARQL queries. We use Natural Language Processing tools, semantic resources and RDF triple descriptions. We designed a four-step method which allows to linguistically and semantically annotate questions, to perform an abstraction of these questions, then to build a representation of the SPARQL queries, and finally to generate the queries. The method is designed on 50 questions over three biomedical knowledge bases used in the task 2 of the QALD-4 challenge framework and evaluated on 27 new questions. It achieves good performance with 0.78 F-measure on the test set. The method for translating questions into SPARQL queries is implemented as a Perl module and is available at http://search.cpan.org/~thhamon/ RDF-NLP-SPARQLQuery/.

ON USAGE OF MACHINE LEARNING FOR NATURAL LANGUAGE PROCESSING TASKS AS ILLUSTRATED BY EDUCATIONAL CONTENT MINING

In this paper, we review most popular approaches to a variety of natural language processing (NLP) tasks, primarily those, which involve machine learning: from classics to state-of-the-art technologies. Most modern approaches can be separated into three rough categories: ones based on distributional hypothesis, those extracting information from graph-like structures (such as ontologies) and the ones that look for lexico-syntactic patterns in text documents. We focus mainly on the former of the three. Before the analysis can even begin, one of the important steps in preparation stage of NLP is the task of representing words and documents as numeric vectors. There exists a variety of approaches from the most simplistic Bag-of-Words to sophisticated machine learning methods, such as word embedding. Today, in the task of information retrieval the best quality for both English and Russian languages is achieved by approaches based on word embedding algorithms, trained on carefully picked text corpora in conjunction with deep syntactic and semantic analysis using various deep neural networks. A big variety of different machine learning algorithms is being applied for NLP tasks such as Part-of-Speech-tagging, text summarization, named entity recognition, document classification, topic and relation extraction and natural language question answering. We also review possibilities of applying these approaches and methods to educational content analysis, and propose the novel approach to utilizing NLP and machine learning capabilities in analyzing and synthesizing educational content in a form of a decision support systems.

Framework for Improved Question Answering System

Background/Objectives: The proposed frame work uses statistical based similarity measure for QAS, which gives short and exact answer to user query. The entire frame work is focusing similarity computation between question and answer pair. Methods/Statistical Analysis: The involvement of similarity computation between question and answer pair should be investigated in this work QAS. Statistical based similarity measure is an important issue as compared to similarity computation in many fields such as, Natural Language Processing, Information Retrieval, Ontology Mapping, Knowledge Acquisition and Question Answering System. Semantic web has been used to present the structure knowledge representation between questions and answer keywords. Ontology can be used as important proposal to enable semantic similarity between keywords present in the question and answer pairs. Findings: The proposed frame work investigate, how the statistical based similarity measure used in these system helps to improve the performance of the QA system for all Wh-questions. We find the keywords having most similar meaning will return the answer as the final answer. The best performance is achieved by extracting the relevant snippets information form Google search engine. The performance of the system will change as the retrieval of the document is increases beyond 15; this could indicate that restriction in the retrieval of document is helps to optimize the performance of the system. Application/Improvements: This frame work is applicable to all type of search engines which helps to finds most relevant answer to user questions. In future, we implement our frame work for questions having more than five keywords.

Building a Business Knowledge Base by a Supervised Learning and Rule-Based Method

Natural Language Question Answering (NLQA) and Prescriptive Analytics (PA) have been identified as innovative, emerging technologies in 2015 by the Gartner group. These technologies require knowledge bases that consist of data that has been extracted from unstructured texts. Every business requires a knowledge base for business analytics as it can enhance companies’ competitiveness in their industry. Most intelligent or analytic services depend a lot upon on knowledge bases. However, building a qualified knowledge base is very time consuming and requires a considerable amount of effort, especially if it is to be manually created. Another problem that occurs when creating a knowledge base is that it will be outdated by the time it is completed and will require constant updating even when it is ready in use. For these reason, it is more advisable to create a computerized knowledge base. This research focuses on building a computerized knowledge base for business using a supervised learning and rule-based method. The method proposed in this paper is based on information extraction, but it has been specialized and modified to extract information related only to a business. The business knowledge base created by our system can also be used for advanced functions such as presenting the hierarchy of technologies and products, and the relations between technologies and products. Using our method, these relations can be expanded and customized according to business requirements.

A Survey of Natural Language Question Answering System

In Question answering (QA) system retrieves the precise information from large documents according to user query. This survey paper describe the different methods of natural language question answering system (NLQA) for general languages.QA System automatically retrieve correct responses to the question asked by the human in natural languages.

Natural Language Access to Enterprise Data

This paper describes USI Answers — a natural language question answering system for enterprise data. We report on the progress towards the goal of offering easy access to enterprise data to a large number of business users, most of whom are not familiar with the specific syntax or semantics of the underlying data sources. Additional complications come from the nature of the data, which comes both as structured and unstructured. The proposed solution allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation. The application is in use by more than 1500 users from Siemens Energy. We evaluate our approach on a data set consisting of fleet data.