Semantic Mapping between Natural Language Questions and SQL Queries via Syntactic Pairing

In this study, we proposed a method for automatically generating high-quality CLIP training data to enhance the performance of text-based image retrieval with CLIP. CLIP training utilizes two types of image-text pair data: compatible (correct) pairs and incompatible (incorrect) pairs. Correct pairs, where the image and text content match, are traditionally created by scraping or similar methods, while incorrect pairs are formed by recombining elements of correct pairs. CLIP is trained contrastively to increase the similarity within correct pairs and decrease it within incorrect pairs. However, when there are multiple images in the training data that are similar to each other, the text attached to them is also considered to be similar to each other, and although it is preferable to treat them as correct pairs, changed pairs are treated as incorrect pairs. Therefore, if two images taken from the training data are not similar, then the similarity between texts assigned to them should also be low, so that a highly reliable incorrect pair can be created by exchanging the assigned text with each other. We applied this idea to the results of clustering the images and texts in the training data, respectively, and used the similarity between the clusters to generate an incorrect pair, then learned to increase the negative effect as the similarity between images was lower. The results of an experiment using the Amazon review dataset, which is commonly used in this field, showed a 27.0% improvement in Rank@1 score compared to vanilla CLIP.

Building natural language interfaces to relational databases is an important and challenging problem in natural language processing (NLP), it requires a system that is able to understand natural language questions and generate corresponding SQL queries. In this paper, we present our idea of using type information and database content to better understand rare entities and numbers in natural language questions, in order to improve the model SyntaxSQLNet as the state of the art in Text-to-SQL task. We also present the global architecture and techniques that can be used in the implementation of our Neural Network (NN) model Text2SQLNet, with the integration of our idea that consists of using type information to better understand rare entities and numbers in natural language questions. We can also use the database content to better understand the user query if it is not well-formed. The implementation of this idea can further improve performance in the Text-to-SQL task.

Mapping natural language (NL) statements into SQL queries allows users to interact with systems through everyday language. Semantic parsing has seen a growing interest over the past decades. In this paper, we extend single hidden layer feedforward network (SLFN) by adding the Kullback-Liebler (KL) divergence parameter to its objective function. We refer to this algorithm as Sparse SLFN (S-SLFN) which can learn whether an SQL query answers a particular NL question. With Bag of Words (BoW) representing the questions and the queries, the algorithm, by enforcing sparsity, is meant to retain robust features representing informative relationships and structure of the data. Experimental results show that S-SLFN outperforms SLFN and other algorithms for the GeoQueries dataset by a respectable margin.KeywordsSingle-hidden Layer Feedforward Network (SLFN)SparsitySemantic Parsing

Relational databases are among the most widely used architectures to store massive amounts of data in the modern world. However, there is a barrier between these databases and the average user. The user often lacks the knowledge of a query language such as SQL required to interact with the database. The NL2SQL task aims at finding deep learning approaches to solve this problem by converting natural language questions into valid SQL queries. Given the sensitive nature of some databases and the growing need for data privacy, we have presented an approach with data privacy at its core. We have passed RoBERTa embeddings and data-agnostic knowledge vectors into LSTM based submodels to predict the final query. Although we have not achieved state of the art results, we have eliminated the need for the table data, right from the training of the model, and have achieved a test set execution accuracy of 76.7%. By eliminating the table data dependency while training we have created a model capable of zero shot learning based on the natural language question and table schema alone.

An empirical study of representing adjectives over knowledge bases: Approach, lexicon and application

Text-to-SQL parsing is the task of converting natural language questions into executable SQL queries, a significant branch of semantic parsing, which has gained increasing attention in recent years. This technology lowers the barrier for people to access databases, enhancing the convenience and availability of data. However, the primary challenge for text-to-SQL parsing lies in domain adaptation, which concerns whether the model can be applied to new databases and effectively align natural language questions with the corresponding tables or columns within the database. To address these issues, research has introduced SRSQL (Syntax and Relation-Augmented Query Generation), which incorporates syntax information and predefined relationships into the model, effectively utilizing syntactic dependencies and pattern linking to improve performance. Using a Transformer-based decoder, SRSQL generates SQL queries in the form of Abstract Syntax Trees (AST), significantly boosting prediction accuracy. Experimental results show that SRSQL outperforms comparative models, particularly on challenging benchmarks like Spider and Spider-SYN.

SParseQA: Sequential word reordering and parsing for answering complex natural language questions over knowledge graphs

Over the past decade, Knowledge Graphs (KG) have emerged as a prominent repository for storing facts about the world in a linked data architecture. Providing machines with the capability of exploring such Knowledge Graphs and answering natural language questions over them, has been an active area of research. The purpose of this work, is to delve further into the research of retrieving information stored in KGs, based on the natural language questions posed by the user. Knowledge Graph Question Answering (KGQA) aims to produce a concise answer to a user question, such that the user is exempt from using KG vocabulary and overheads of learning a formal query language. Existing KGQA systems have achieved excellent results over Simple Questions, where the information required is limited to a single triple and a single formal query pattern. Our motivation is to improve the performance of KGQA over Complex Questions, where formal query patterns significantly vary, and a single triple is not confining for all the required information. Complex KGQA provides several challenges such as understanding semantics and syntactic structure of questions, Entity Linking, Relation Linking and Answer Representation. Lack of suitable datasets for complex question answering further adds to research gaps. Hence, in this thesis, we focus the research objective of laying the foundations for the advancement of the state-of-the-art for Complex Question Answering over Knowledge Graphs, by providing techniques to solve various challenges and provide resources to fill the research gaps. First, we propose Normalized Query Structure (NQS), which is a linguistic analyzer module that helps the QA system to detect inputs and intents and the relation between them in the users' question. NQS acts like an intermediate language between natural language questions and formal expressions to ease the process of query formulation for complex questions. We then developed a framework named LC-QuAD to generate large scale question answering dataset by reversing the process of question answering, thereby translating natural language questions from the formal query using intermediate templates. Our goal is to use this framework for high variations in the query patterns and create a large size dataset with minimum human effort. The first version of the dataset consists of 5,000 complex questions. By extending the LC-QuAD framework to support Reified KGs and crowd-sourcing, we published the second version of the dataset as LC-QuAD 2.0, consisting of 30,000 questions with their paraphrases and has higher complexity and new variations in the questions. To overcome the problem of Entity Linking and Relation Linking in KGQA, we develop EARL, a module performing these two tasks as a single joint task for complex question answering. We develop approaches for this module, first by formalizing the task as an instance of the Generalized Traveling Salesman Problem (GTSP) and the second approach uses machine learning to exploit the connection density between nodes in the Knowledge Graph. Lastly, we create another large scale dataset to answer verbalization and provide results for multiple baseline system s on it. The Verbalization dataset is introduced to make the system's response more human-like. The NQS based KGQA system was next to the best system in terms of accuracy on the QALD-5 dataset. We empirically prove that NQS is robust to tackle paraphrases of the questions. EARL achieves the state of the art results in Entity Linking and Relation Linking for question answering on several KGQA datasets. The dataset curated in this thesis has helped the research community to move forward in the direction of improving the accuracy of complex question answering as a task as other researchers too developed several KGQA systems and modules around these published datasets. With the large-scale datasets, we have encouraged the use of large scale machine learning, deep learning and emergence of new techniques to advance the state-of-the-art in complex question answering over knowledge graphs. We further developed core components for the KGQA pipeline to overcome the challenges of Question Understanding, Entity-Relation Linking and Answer Verbalization and thus achieve our research objective. All the proposed approaches mentioned in this thesis and the published resources are available at https://github.com/AskNowQA and are released under the umbrella project AskNow.

Access to hospital data is commonly a difficult, costly and time-consuming process requiring extensive interaction with network administrators. This leads to possible delays in obtaining insights from data, such as diagnosis or other clinical outcomes. Healthcare administrators, medical practitioners, researchers and patients could benefit from a system that could extract relevant information from healthcare data in real-time. In this paper, we present a question answering system that allows health professionals to interact with a large-scale database by asking questions in natural language. This system is built upon the BERT and SQLOVA models, which translate a user's request into an SQL query, which is then passed to the data server to retrieve relevant information. We also propose a deep bilinear similarity model to improve the generated SQL queries by better matching terms in the user's query with the database schema and contents. This system was trained with only 75 real questions and 455 back-translated questions, and was evaluated over 75 additional real questions about a real health information database, achieving a retrieval accuracy of 78%.

Recent research in Text-to-SQL translation has primarily adopted in-context learning methods leveraging large language models (LLMs), achieving significant progress. However, these methods face challenges in adapting to natural language questions of varying difficulty and the relevance of the few-shot examples provided. In this paper, we propose an adaptive in-context learning approach with difficulty-aware instruction and retrieval-augmented generation to enhance the performance of Text-to-SQL translation (AID-SQL). First, we introduce adaptive instructions for LLMs, which employ precise difficulty classification to apply difficulty-adaptive generative guidelines and chain of thought (CoT) templates for varying difficulty levels. We automatically incorporate few-shot examples retrieved through the knowledge base into the CoT template to construct CoT-enhanced examples, which improves the capability of LLMs with retrieval-augmented generation (RAG). Furthermore, considering that current RAG methods struggle to effectively measure the contribution of retrieved examples in solving the specific task of Text-to-SQL translation, we train a ranking model that can better bridge the semantic and structural gap between NL questions and SQL queries. This approach can better understand semantic information and allows for retrieving examples that are more beneficial to the final problem-solving. We evaluate our method on five benchmarks. Our method achieves competitive performance compared with existing methods.

Aiming at open domain question answering system evaluation task in the fourth CCF Natural Language Processing and Chinese Computing Conference NLPCC2015, a solution of automatic question answering which can answer natural language questions is proposed. Firstly, SPE Subject Predicate Extraction algorithm is presented to find answers from the knowledge base, and then WKE Web Knowledge Extraction algorithm is used to extract answers from search engine query result. Experimental data provided in the evaluation task includes the knowledge base and questions in natural language. The evaluation result shows that MRR is 0.5670, accuracy is 0.5700, and average F1 is 0.5240, and indicates the proposed method is feasible in open domain question answering system.

The rapid development in the field of information science and the increase in the usage of information retrieval strategies have empowered users to retrieve more accurate information. The availability of information in a different format and across different has presented colossal difficulties for information retrieval using information retrieval techniques. In this paper, an attempt is made at highlighting the question and answering (QA) systems that provide users the platform to express their question using the Natural Language and also retrieve the response from such systems in Natural Language. The four important modules of any QA system are the Natural Language Question (NLQ) processing, document processing, passage processing, and answer processing. Fundamentally, most QA systems combined several techniques from other fields such as information retrieval, knowledge representation, and natural language processing to process NLQ and present the most insightful response based on the stored document. This paper gives a thorough review of the various survey on the QA systems frameworks, their methodologies, types, approaches, and challenges of QA systems.

With the recent and intensive research in the biomedical area, the knowledge accumulated is disseminated through various knowledge bases. Links between these knowledge bases are needed in order to use them jointly. Linked Data, SPARQL language, and interfaces in Natural Language question-answering provide interesting solutions for querying such knowledge bases. We propose a method for translating natural language questions in SPARQL queries. We use Natural Language Processing tools, semantic resources, and the RDF triples description. The method is designed on 50 questions over 3 biomedical knowledge bases, and evaluated on 27 questions. It achieves 0.78 F-measure on the test set. The method for translating natural language questions into SPARQL queries is implemented as Perl module available at http://search.cpan.org/ thhamon/RDF-NLP-SPARQLQuery

A building information model often provides the functional and physical data of an electrical facility for the downstream construction, operation and maintenance of the built power grid infrastructure. Therefore, the rapid and convenient query of the required information from the design model is crucial for all the project participants. However, the query of the design data from a BIM model is frequently burdensome and tedious. Moreover, the Grid Information Modeling (GIM) schema, developed by the China State Grid for describing electrical equipment with more engineering details, exaggerates the difficulty of querying the design model. This study applies the Natural Language Interface to Database (NLIDB) approach for querying data from the Neo4j graph database that fuses both IFC data for architectural or structural design and GIM data for electrical equipment. Meanwhile, this study also develops a tool to automatically convert the natural language questions into Cypher queries. In addition, a knowledge graph is also developed for linking the semantic elements extracted from the natural language questions with the IFC semantics stored in the Neo4j database.

In this paper, we address the problem of answering complex questions formulated by users in natural language. Since traditional information retrieval systems are not suitable for complex questions, these questions are usually run over knowledge bases, such as Wikidata or DBpedia. We propose a semi-automatic approach for transforming a natural language question into a SPARQL query that can be easily processed over a knowledge base. The approach applies classification techniques to associate a natural language question with a proper query template from a set of predefined templates. The nature of our approach is semi-automatic as the query templates are manually written by human assessors, who are the experts of the knowledge bases, whereas the classification and query processing steps are completely automatic. Our experiments on the large-scale CSQA dataset for question-answering corroborate the effectiveness of our approach.