Answer Selection Research Articles

Cross-biased contrastive learning for answer selection with dual-tower structure

A large number of unanswered products-related questions appear in the E-commerce platforms, necessitating the deployment of question-answering models to automatically provide precise responses for the user. However, the substantial absence of ground truth presents challenges for implementing supervised learning, and existing unsupervised contrastive learning methods have not addressed this issue fundamentally, with limitations in integrating multi-level features. This paper presents a dual-tower cross-biased contrastive learning model for answer selection, named CCLM-AS. By taking questions and augmented product reviews as positive pairs for unsupervised contrastive learning and employing a dual-tower structure encoder, CCLM-AS learns sentence representations from unlabeled data effectively. Furthermore, the designed training objective realizes multi-level feature integration, including character, sentence and dialogue levels, which enhances the model's inference ability. The experimental results on AmazonQA dataset indicate that our proposed model outperforms existing contrastive learning-based sentence representation models and also achieves comparable performance to supervised answer selection models. This demonstrates that CCLM-AS can not only alleviate the data sparsity problem effectively but also retain the excellent performance.

Validation of the mental visualization effect on answer selection in closed questions in surveys

The selection of listed answers in surveys is influenced by numerous aspects. At the moment of decoding, the mental representation of the item can represent a bias if it is distorted by personal impressions. The present research aims to identify these influences at the moment of choice of items presented sequentially in a closed-ended question by a nominal scale. For this purpose, the answers of a survey were correlated with the results of psychometric experimental pretests on mental image formation by applying them to experimental groups. Although the item selection affects several aspects of linguistic elements, it seems that this no influences the choice. The comparison between the data of mental visualisation of item and item frequency showed a very high correlation unusually in social or psychosocial sciences. Wording can increase the item comprehensibility but not eliminate the visual imagery effects, therefore represents a permanent bias.

A Knowledge Graph Embedding Model for Answering Factoid Entity Questions

Factoid entity questions (FEQ), which seek answers in the form of a single entity from knowledge sources such as DBpedia and Wikidata, constitute a substantial portion of user queries in search engines. This paper introduces the Knowledge Graph Embedding model for Factoid Entity Question answering (KGE-FEQ). Leveraging a textual knowledge graph derived from extensive text collections, KGE-FEQ encodes textual relationships between entities. The model employs a two-step process: (1) Triple Retrieval, where relevant triples are retrieved from the textual knowledge graph based on semantic similarities to the question, and (2) Answer Selection, where a knowledge graph embedding approach is utilized for answering the question. This involves positioning the embedding for the answer entity close to the embedding of the question entity, incorporating a vector representing the question and textual relations between entities. Extensive experiments evaluate the performance of the proposed approach, comparing KGE-FEQ to state-of-the-art baselines in factoid entity question answering and the most advanced open-domain question answering techniques applied to FEQs. The results show that KGE-FEQ outperforms existing methods across different datasets. Ablation studies highlights the effectiveness of KGE-FEQ when both the question and textual relations between entities are considered for answering questions.

Improve Question Classification Genetic Algorithm Based Feature Selection and Convolution Neural Network

Natural Language Processing (NLP) approaches play a crucial role in classifying inquiries and comprehending human language in diverse applications. A Question Answering System (QAS) consists of three components are question processing, information retrieval, and answer selection. Question Answering Systems (QASs) are a distinct form of information retrieval. The most crucial aspect of QAS is deciding on the question type since it influences the other sections following. However, an important question-answering system requires a prominent question classification system. In the past, there are different methods to solve this problem, such as rule-based learning, and hybrid approaches. However, the problem with these methods is that the rules require a lot of effort to create and are very limited. In this study, the utilization of genetic algorithm and deep neural network techniques enhances the quality control problem-solving process. This research utilizes the UIUC dataset. This collection comprises 5452 questions designed for learning purposes and an additional 500 questions specifically intended for assessment. The suggested solution involves converting each query into a matrix, with each row representing the Word2vec of a word. Subsequently, a Genetic Algorithm (GA) is employed to identify the most optimal features. Ultimately, a Convolutional Neural Network is utilized for classification, yielding a remarkable accuracy of 98.2% in our experimentation with the question dataset.

Evaluating LLMs on document-based QA: Exact answer selection and numerical extraction using CogTale dataset

Document-based Question-Answering (QA) tasks are crucial for precise information retrieval. While some existing work focus on evaluating large language model’s (LLMs) performance on retrieving and answering questions from documents, assessing the LLMs performance on QA types that require exact answer selection from predefined options and numerical extraction is yet to be fully assessed. In this paper, we specifically focus on this underexplored context and conduct empirical analysis of LLMs (GPT-4 and GPT-3.5) on question types, including single-choice, yes–no, multiple-choice, and number extraction questions from documents. We use the CogTale dataset for evaluation, which provide human expert-tagged responses, offering a robust benchmark for precision and factual grounding. We found that LLMs, particularly GPT-4, can precisely answer many single-choice and yes–no questions given relevant context, demonstrating their efficacy in information retrieval tasks. However, their performance diminishes when confronted with multiple-choice and number extraction formats, lowering the overall performance of the models on this task, indicating that these models may not yet be sufficiently reliable for the task. This limits the applications of LLMs on applications demanding precise information extraction and inference from documents, such as meta-analysis tasks. Our work offers a framework for ongoing dataset evaluation, ensuring that LLM applications for information retrieval and document analysis continue to meet evolving standards.

Medical education and artificial intelligence: Question answering for medical questions based on intelligent interaction

SummaryComputer assisted medical diagnosis technology is widely used in the field of medical assistance to assist doctors in making diagnostic decisions. But as the number of patients increases, the diagnostic pressure on doctors gradually increases, and more efficient computer‐aided medical diagnosis technology is needed to improve the accuracy of doctors' diagnosis. Today's computer‐based medically assisted diagnostic technologies suffer from the inability to fully simulate physical attributes and environmental factors, the large computational resources required for high‐precision models, the need for professional training for user operation, and the limited intuition for innovative design. For improving diagnostic efficiency, this study designs a medical Question answering intelligent interaction system in view of artificial intelligence algorithms. The system is constructed with an active interactive intelligent Q&A model consisting of a medical reasoning module and a medical examination recommendation module. Then, it uses local Bayesian network algorithm as the foundation to establish an intelligent strategy optimization network. And it puts forward the answer selection model of medical Question answering in view of hierarchical interaction for natural language processing tasks in the medical context. The performance test results show that when the diagnostic end threshold of the medical reasoning module is 0.8, the shortest diagnostic path is 3.33. When the diagnostic threshold is 0.85, the maximum length of the diagnostic path is 4.66, and the maximum difference between the diagnostic paths is 1.33, which is basically not affected by the diagnostic end threshold. The local Bayesian network algorithm can reduce the impact of noise features and extract more valuable information. The accuracy of the multilevel interactive answer selection model on the Stanford Natural Language Inference dataset without using external resources reached 89.2%. The ablation test results show that the overall accuracy of the model is 89.64%. The visualization results of the attention weight distribution test between interaction layers show that under different levels of interaction, the attention distribution will undergo significant changes.

Is Fibular Fixation Necessary with Increasing Proximity in Ankle Fractures: A Survey of OTA and AOFAS Surgeons

Introduction/Purpose: Ankle fractures are one of the most common fractures encountered in orthopedics. The Maisonneuve fracture pattern is described as a pronation, external rotation injury involving the medial ankle structures, the syndesmosis, and the proximal third of the fibula. However, the actual distance from the proximal fibula has not been defined in what distinguishes a Maisonneuve fracture. With Weber C fractures, most surgeons tend to provide fixation to the fibula and reassess the syndesmosis afterwards. When dealing with the proximal fibula “Maisonneuve” fracture pattern, most surgeons would tend to ignore the fibula fracture and focus on syndesmotic reduction. Orthopaedic Trauma Association and American Orthopaedic Foot & Ankle Society provided their opinion via survey in treating increasing proximity of fibula fractures associated with unstable ankle fracture patterns. Methods: A survey was provided to eight OTA and AOFAS orthopedic surgeons. A powerpoint was provided to the surgeons that contained non-weightbearing injury films of eighteen patients. A questionnaire was provided giving two answer choices, address the fibular or syndesmosis primarily. The eighteen ankle fractures were selected based on increasing proximity of the fibula fracture, which ranged from 4.5cm to 32.3cm. The ankle fractures were grouped into four categories to include the Maisonneuve variant based on distance. These fracture radiographs were randomized in order to not influence the surgeon’s opinion during the study. The four groups were as follows: 1. 4.5cm – 7.4cm to include six ankle fracture radiographs 2. 8cm – 10.4cm to include four ankle fracture radiographs 3. 14.6cm to 23.3cm to include five ankle fracture radiographs 4. 30.7cm to 32.3 cm to include three Maisonneuve variant ankle fracture radiographs Results: Regarding section 1, the majority of surgeons responded with open reduction, internal fixation of the fibula as their initial reduction. Section 2, the responses remained consistent with a majority of surgeons choosing to address fibular fixation followed by syndesmotic evaluation. The total number of responses in this section scored 43 answer A selections to 5 answer B selections. Section 3 (14.6-23.3cm) provided the most variability in the responses provided. With 60 possible answer choices, the polled surgeons responded with answer choice A seventeen times and answer choice B 43 times. Section 4 (30.7-32.2cm) or the Maisonneuve produced a steady response of answer choice B. Syndesmotic reduction was performed 34 times compared to only two fibular fixation choices – or answer choice A. Conclusion: The purpose of this study was to evaluate expert opinion on differing treatment as the proximity of the fibular fracture increased in connection with an unstable ankle fracture pattern. General consensus under 10,4cm was to address fibular fixation. However, once the fibular fracture exceeded 14cm, significant variability was noted. These results prove that further biomechanical studies are needed to determine the effect fibular stability in increasing proximity has on the syndesmosis. Chart 1 shows answer selections across the four categories. Chart 2 shows answer selections across the highest variability group 3.

Educating for uncertainty in what is certainly an uncertain world

While uncertainty is an unavoidable companion in our world, it is hard to grasp and even harder to embrace in educational contexts. In this special issue of Teachers and Teaching: Theory and Practice, researchers who have done extensive research on uncertainty in various fields of education share their insights into this phenomenon. In what follows, we highlight some of the most pressing uncertainty-related questions being considered in this special issue and refer to an abbreviated selection of answers that the authors expand on in their articles. Despite different foci, all authors contend that the certainty of uncertainty requires educators to consider its role as a lever of and for new and promising possibilities of teaching and learning.

Students' Ability to Understand Statistics Subjects: An Analytical Review

This research aims to assess the comprehension skills of students in the statistics course at the Management Study Program, Universitas Islam Kadiri, Kediri. A survey method was employed to gather diverse information from 30 students in Semester III class A5 enrolled in the statistics course during the academic year 2022/2023. The research was conducted from July to November 2023, utilizing purposive sampling. Data collection involved a test comprising 10 multiple-choice questions, focusing on stages such as reading comprehension, understanding, transformation, process skills, and selecting the correct answers. Qualitative descriptive analysis was applied during and after data collection. The research findings indicate that students' comprehension skills in the statistics course fall into the high category, with 62% of students answering correctly. Common errors occurred in stages such as reading comprehension, understanding, transformation, process skills, and answer selection. Suggestions are given to students to study more diligently, actively participate in learning activities, and overcome difficulties by finding ways to make statistics materials more comprehensible. The Management Study Program is advised to pay special attention to challenging statistics topics to optimize students' learning outcomes.

A Local Self-Attention Sentence Model for Answer Selection Task in CQA Systems

Current evidence indicates that the semantic representation of question and answer sentences is better generated by deep neural network-based sentence models than traditional methods in community answer selection tasks. In particular, as a widely recognized language model, the self-attention model computes the similarity between the specific word and the whole sets of words in the same sentence and generates new semantic representation through the similarity-weighted summation of semantic representations of the whole words. However, the self-attention operation entirely considers all the signals with a weighted sum operation, which disperses the distribution of attention, which may result in overlooking the relation of neighboring signals. This issue becomes serious when applying the self-attention model to online community question answering platforms because of the varied length of the user-generated questions and answers. To address this problem, we introduce an attention mechanism enhanced local self-attention (LSA), which restricts the range of original self-attention by a local window mechanism, thereby scaling linearly when increasing the sequence length. Furthermore, we propose stacking multiple LSA layers to model the relationship of multiscale <inline-formula> <tex-math notation="LaTeX">$n$</tex-math> </inline-formula>-gram features. It captures the word-to-word relationship in the first layer and then captures the chunk-to-chunk (such as lexical <inline-formula> <tex-math notation="LaTeX">$n$</tex-math> </inline-formula>-gram phrases) relationship in its deeper layers. We also test the effectiveness of the proposed model by applying the learned representation through the LSA model to a Siamese and a classification network in community question answer selection tasks. Experiments on the public datasets show that the proposed LSA achieves a good performance.

TopicAns: Topic-Informed Architecture for Answer Recommendation on Technical Q&amp;A Site

Technical Q&amp;A sites, such as Stack Overflow and Ask Ubuntu, have been widely utilized by software engineers to seek support for development challenges. However, not all the raised questions get instant feedback and the retrieved answers can vary in quality. The users can hardly avoid spending much time before solving their problems. Prior studies propose approaches to automatically recommend answers for the question posts on technical Q&amp;A sites. However, the lengthiness and the lack of background knowledge issues limit the performance of answer recommendation on these sites. The irrelevant sentences in the posts may introduce noise to the semantics learning and prevent neural models from capturing the gist of texts. The lexical gap between question and answer posts further mislead current models to make failure recommendations. From this end, we propose a novel neural network named TopicAns for answer selection on technical Q&amp;A sites. TopicAns aims at learning high-quality representations for the posts in Q&amp;A sites with a neural topic model and a pre-trained model. This involves three main steps: (1) generating topic-aware representations of Q&amp;A posts with the neural topic model, (2) incorporating the corpus-level knowledge from the neural topic model to enhance the deep representations generated by the pre-trained language model, and (3) determining the most suitable answer for a given query based on the topic-aware representation and the deep representation. Moreover, we propose a two-stage training technique to improve the stability of our model. We conduct comprehensive experiments on four benchmark datasets to verify our proposed TopicAns’s effectiveness. Experiment results suggest that TopicAns consistently outperforms state-of-the-art techniques by over 30% in terms of Precision@1.

Content-Driven Answer Selection in Community Question Answering Using Clustering and Fuzzy Ranking

Content-Driven Answer Selection in Community Question Answering Using Clustering and Fuzzy Ranking

OpenViVQA: Task, dataset, and multimodal fusion models for visual question answering in Vietnamese

In recent years, visual question answering (VQA) has attracted attention from the research community because of its highly potential applications (such as virtual assistance on intelligent cars, assistant devices for blind people, or information retrieval from document images using natural language as queries) and challenge. The VQA task requires methods that have the ability to fuse the information from questions and images to produce appropriate answers. Neural visual question answering models have achieved tremendous growth on large-scale datasets which are mostly for resource-rich languages such as English. However, available datasets narrow the VQA task as the answers selection task or answer classification task. We argue that this form of VQA is far from human ability and eliminates the challenge of the answering aspect in the VQA task by just selecting answers rather than generating them. In this paper, we introduce the OpenViVQA (Open-domain Vietnamese Visual Question Answering) dataset, the first large-scale dataset for VQA with open-ended answers in Vietnamese, consists of 11,000+ images associated with 37,000+ question–answer pairs (QAs). Moreover, we proposed FST, QuMLAG, and MLPAG which fuse information from images and questions, then use these fused features to construct answers as humans iteratively. Our proposed methods achieve results that are competitive with SOTA models such as SAAA, MCAN, LORA, and M4C. The dataset11https://github.com/hieunghia-pat/OpenViVQA-dataset. is available to encourage the research community to develop more generalized algorithms including transformers for low-resource languages such as Vietnamese.

Memory-Aware Attentive Control for Community Question Answering With Knowledge-Based Dual Refinement

The question answering system in open domain enables a machine to automatically select and generate the answer for questions posed by humans in a natural language form on the website. Previous approaches seek effective ways of extracting the semantic features between question and answer, but the contextual information effects in semantic matching are still limited by short-term memory. As an alternative, we propose an internal knowledge-based end-to-end model, enhanced by an attentive memory network for both answer selection and answer generation tasks by considering the full advantages of the semantics and multifacts (i.e., timescales, topics, and context). In detail, we design a long-term memory to learn the top- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$</tex-math> </inline-formula> fine-grained similarity representations, where two memory-aware mechanisms aggregate the series of semantic word-level and sentence-level similarities to support the coarse contextual information. Furthermore, we propose a novel memory refinement mechanism with the two-dimensional of writing heads that offer an efficient approach to multiview selection of the salient word pairs. In the training stage, we adopt the transformer-based transfer learning skill to effectively pretrain the model. Experimentally, we compare the state-of-the-art approaches on four public datasets, the experimental results show that the proposed model achieves competitive performance.

A New Method of Teaching ‘Software Operation’ by a Knowledge Sharing Oriented to Practice Teaching Approach

The practice teaching of software operation emphasizes operation practice and practical experience, and it lays special attention on the interactions among students and teachers and teaching in accordance with aptitude. As a typical knowledge sharing platform, question-and-answer (Q&amp;A) community is developing fast and can be taken as an assistant teaching method for the practice teaching of software operation to facilitate the teaching knowledge sharing between teachers and students. Most existing studies consider the attention mechanism of the correlation between questions and answers based on the similarity of word vectors, which has resulted in unsatisfactory accuracy and interpretability of the answers given by the model, in view of this matter, this paper studied a new method of teaching knowledge sharing oriented to the practice teaching of software operation. At first, this paper elaborated on the idea of knowledge sharing, and proposed a knowledge answer selection model for practice teaching of software operation based on the aggregation of features and attention to solve the problem with conventional studies which generally focus on the weighting of attention of a single sentence. Comparing the word granularity of sentence sequences to be matched and aggregating the comparison results have solved the problem with conventional methods in ignoring the interaction between the sentence sequences to be matched. At last, experimental results verified the effectiveness of the proposed method.

Context-aware Answer Selection in Community Question Answering Exploiting Spatial Temporal Bidirectional Long Short-Term Memory

Community Question Answering (CQA) sites provide knowledge sharing facility as the users can post questions and other users can share their answers. The selection of top-quality answers from the set of answers in a thread is a significant and challenging task in Natural Language Processing (NLP). To address this issue, we propose a deep learning based spatial temporal Bidirectional Long Short-Term Memory (Bi-LSTM) algorithm. The existing studies mainly focus only computing semantic similarity between questions and answers using votes given by the users. The proposed hybrid approach, based on both forward and backward, consider question to answer and answer to answer similarity. The forward LSTM captures the spatial impact of the answer to estimate the relevancy, whereas the backward LSTM learns temporal features with the answer to predict the best quality answer. Moreover, spatial Bi-LSTM captures past and future dependencies for a better understanding of context and to improve the effectiveness of answer selection. For extracting meaningful information from noisy text data, data is preprocessed following standard steps such as tokenization, parsing, lemmatization, stop words removal, part of speech tagging and entities extraction. Word embeddings-based Paragraph to vector (par2vec) has additional input nodes to represent paragraph information in vector for context understanding. The empirical analysis carried out on the SemEval CQA dataset shows that the proposed model outperforms state-of-art answer selection approaches.

Task-based attentional and default mode connectivity associated with science and math anxiety profiles among university physics students

PurposeAttentional control theory (ACT) posits that elevated anxiety increases the probability of re-allocating cognitive resources needed to complete a task to processing anxiety-related stimuli. This process impairs processing efficiency and can lead to reduced performance effectiveness. Science, technology, engineering, and math (STEM) students frequently experience anxiety about their coursework, which can interfere with learning and performance and negatively impact student retention and graduation rates. The objective of this study was to extend the ACT framework to investigate the neurobiological associations between science and math anxiety and cognitive performance among 123 physics undergraduate students. ProceduresLatent profile analysis (LPA) identified four profiles of science and math anxiety among STEM students, including two profiles that represented the majority of the sample (Low Science and Math Anxiety; 59.3% and High Math Anxiety; 21.9%) and two additional profiles that were not well represented (High Science and Math Anxiety; 6.5% and High Science Anxiety; 4.1%). Students underwent a functional magnetic resonance imaging (fMRI) session in which they performed two tasks involving physics cognition: the Force Concept Inventory (FCI) task and the Physics Knowledge (PK) task. FindingsNo significant differences were observed in FCI or PK task performance between High Math Anxiety and Low Science and Math Anxiety students. During the three phases of the FCI task, we found no significant brain connectivity differences during scenario and question presentation, yet we observed significant differences during answer selection within and between the dorsal attention network (DAN), ventral attention network (VAN), and default mode network (DMN). Further, we found significant group differences during the PK task were limited to the DAN, including DAN-VAN and within-DAN connectivity. ConclusionsThese results highlight the different cognitive processes required for physics conceptual reasoning compared to physics knowledge retrieval, provide new insight into the underlying brain dynamics associated with anxiety and physics cognition, and confirm the relevance of ACT theory for science and math anxiety.

Quantifying the Impact of Dysmenorrhea Symptoms on Quality-of-Life and Access to Oral Contraceptives by Income.

Dysmenorrhea, or painful menstrual periods, is one of the most common gynecological complaints. Most reports of uterine contractions range between moderate to severe pain, and patients often elect to cope with their discomfort without assistance from a physician. In the process, women experiencing dysmenorrhea are more likely to report absenteeism from work and school. This study measures the reported impact of dysmenorrhea on patients' lives and elucidates a relationship between income and access to oral contraceptives. Two hundred women completed a survey about their symptoms, level of pain, treatments, and the extent to which dysmenorrhea affected day-to-day obligations. Most questions were multiple-choice while others permitted several answer selections or were free response. The data was analyzed using JMP statistical software. Eighty-four percent of respondents reported moderate to severe pain during menstruation. This discomfort has caused 65.5% of the cohort to miss work and 68% to avoid participating in social gatherings. Pain relief medications are most often used as treatment - 143 respondents took ibuprofen, 93 took acetaminophen, and 51 took naproxen. 29.5% of respondents are prescribed birth control for cramps and blood flow. Income (p = 0.049), age (p = 0.002), and education (p = 0.002) were significant predictors for oral contraceptive pill (OCP) use. The lowest income groups were found to use OCPs at less than half the rate as the highest income respondents. Dysmenorrhea affected most participants in the cohort with an impact that extends beyond professional obligations. Income was found to be positively correlated with increased OCP use, whereas education level was inversely correlated. Clinicians should consider how patients' backgrounds influence their access to OCP options. An improvement on this study's findings would be to establish a causal relationship between these demographic factors and access to OCPs.

Enhancing Answer Selection via Ad-Hoc Knowledge Extraction from Unstructured Web Texts

Answer selection aims to identify the most relevant answers to a given question from a set of candidates. It is the fundamental component of intelligent question answering system. To improve performance, it gradually becomes an effective strategy to integrate external structured knowledge bases (KBs) into the answer selection model. Due to expensive cost of construction and maintenance of such KBs, these models are suffering from domain barriers and information incompleteness. In this paper, we propose a two-stage extraction–comprehension answer selection model, which can extract ad-hoc knowledge from unstructured web texts to enhance the performance of answer selection. For the extraction, two types of snippets are extracted from unstructured web pages and utilized as the source of ad-hoc knowledge. For the comprehension, a selective attention mechanism is employed to extract and integrate ad-hoc knowledge from multiple text snippets obtained in the first stage, which can enrich the representation of question–answer pairs and more accurately identify the correct answers. By incorporating ad-hoc knowledge extracted from both types of snippets, the proposed model achieves state-of-the-art results on two public available benchmark datasets. In particular, on WikiQA, in terms of the two evaluation metrics (mean average precision and mean reciprocal rank), it achieves 9.9[Formula: see text] and 8.4[Formula: see text] higher than the previous non-pretraining-based models, and 3.4[Formula: see text] and 3.2[Formula: see text] higher than the pretraining-based models.

Text Matching in Insurance Question-Answering Community Based on an Integrated BiLSTM-TextCNN Model Fusing Multi-Feature

Along with the explosion of ChatGPT, the artificial intelligence question-answering system has been pushed to a climax. Intelligent question-answering enables computers to simulate people's behavior habits of understanding a corpus through machine learning, so as to answer questions in professional fields. How to obtain more accurate answers to personalized questions in professional fields is the core content of intelligent question-answering research. As one of the key technologies of intelligent question-answering, the accuracy of text matching is related to the development of the intelligent question-answering community. Aiming to solve the problem of polysemy of text, the Enhanced Representation through Knowledge Integration (ERNIE) model is used to obtain the word vector representation of text, which makes up for the lack of prior knowledge in the traditional word vector representation model. Additionally, there are also problems of homophones and polyphones in Chinese, so this paper introduces the phonetic character sequence of the text to distinguish them. In addition, aiming at the problem that there are many proper nouns in the insurance field that are difficult to identify, after conventional part-of-speech tagging, proper nouns are distinguished by especially defining their parts of speech. After the above three types of text-based semantic feature extensions, this paper also uses the Bi-directional Long Short-Term Memory (BiLSTM) and TextCNN models to extract the global features and local features of the text, respectively. It can obtain the feature representation of the text more comprehensively. Thus, the text matching model integrating BiLSTM and TextCNN fusing Multi-Feature (namely MFBT) is proposed for the insurance question-answering community. The MFBT model aims to solve the problems that affect the answer selection in the insurance question-answering community, such as proper nouns, nonstandard sentences and sparse features. Taking the question-and-answer data of the insurance library as the sample, the MFBT text-matching model is compared and evaluated with other models. The experimental results show that the MFBT text-matching model has higher evaluation index values, including accuracy, recall and F1, than other models. The model trained by historical search data can better help users in the insurance question-and-answer community obtain the answers they need and improve their satisfaction.