Search

Answer selection requires technology that effectively captures in-depth semantic information between the question and the corresponding answer. Most existing studies focus on using linear or pooling operations to directly classify the output representation, resulting in the absence of critical information and the emergence of single-label predictions. To address these issues, we propose a novel Multi-view Pre-trained Transformer with Hierarchical Capsule Network (MPT-HCN). Specifically, we propose a Hierarchical Capsule Network composed of three capsule networks to independently process high-dimensional sparse information of words, semantic information of similar expressions, and feature classification information so that multiple attributes can be fully considered and accurately clustered. Moreover, we consider the impact of the intermediate encoder layer output information on the overall sequence semantic representation and propose a Multi-view Information Fusion that obtains the final semantic representation information by weighted fusion of the output information of all encoder layers, thereby avoiding the appearance of a single prediction label. Extensive experiments on five typical representative datasets, especially on the WikiQA dataset, show that our model MPT-HCN (RL) achieves an excellent performance of 0.939 on MAP and 0.942 on MRR, which is a significant improvement of 3.9% and 2.7% respectively, compared to the state-of-the-art baseline model. [ABSTRACT FROM AUTHOR]

Answer selection is one of the most important tasks during natural language processing in the downstream tasks, such as question-answering systems, and search ranking. The most relevant answer can be selected to the given question from a candidate answer pool, which is usually regarded as a relevance ranking task. However, the current models of answer selection cannot discover the deep semantic relationships between questions and answers using the limited information in the text of the question-answer pairs. Fortunately, knowledge graph can be expected to serve as the background knowledge, in order to enhance the deep semantics of the answer selection model. It is still lacking on the multi-modal background knowledge support, because the answer selection models can rely solely on their own information. In this research, a multi-modal knowledge graph enhanced answer selection model was proposed, including the embedding layer, representation learning layer, knowledge graph enhancement layer, and output layer. Among them, the Glove model was used to obtain the word embeddings for the questionanswer texts in the embedding layer. Furthermore, a ComplEx-based method (complex embedding) was designed to learn the entity embeddings for the multi-modal knowledge graph. The image entity information was considered to extract the image feature representations using the Vision Transformer (VIT). Bi-directional long short-term memory (Bi-LSTM) was used for the representation learning of question-answer texts in the representation layer. The context-guided multi-modal knowledge graph question and answer vector representations were obtained using context-guided attention mechanism. In the knowledge graph enhancement layer, the interaction attention mechanism was used to fuse the semantic representation of the questionanswer texts with the background knowledge features that provided by the multi-modal knowledge graph, particularly for the feature representations of the multi-modal knowledge graph enhanced question and answer. The feature representations of the knowledge graph enhanced question and answer were concatenated with the additional semantic features in the output layer. The softmax function was used to predict the probability distribution of answer labels for a given question. Taking the grape planting as an example, the multi-modal entity linking was realized using the longest common subsequence algorithm. The entity recognition was also implemented to extract the knowledge using the Bert-LSTM-CRF framework and Bert pre-training model. The reference of knowledge graph was collected from the literature and experts. Finally, a multi-modal knowledge graph was constructed in the grape planting field. A grape planting question and answer dataset was also constructed using grape forums, smart agricultural platforms, agricultural managers, and agricultural benefit networks as data sources, followed by text cleaning and dataset expansion. Experimental results show that the better performance of the model was achieved to obtain more information using the multi-modal knowledge graphs. Specifically, the mean reciprocal rank and mean average precision reached 85.02% and 84.21%, respectively, in the grape question answering dataset. The mean reciprocal rank and mean average precision increased by 2.57 and 3.96 percentage points, respectively. The answer selection model with the knowledge of multi-modal knowledge graph can be expected to improve the better performance of answer selection model. The embedding representation with attention mechanism can be utilized to enhance the background knowledge from the multimodal knowledge graph. The finding can provide a technical basis for the downstream applications of multi-modal knowledge graphs, such as the search and question answering. [ABSTRACT FROM AUTHOR]

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 % and 8.4 % higher than the previous non-pretraining-based models, and 3.4 % and 3.2 % higher than the pretraining-based models. [ABSTRACT FROM AUTHOR]

Answer selection, as a crucial method for intelligent medical service robots, has become more and more important in natural language processing (NLP). However, there are still some critical issues in the answer selection model. On the one hand, the model lacks semantic understanding of long questions because of noise information in a question–answer (QA) pair. On the other hand, some researchers combine two or more neural network models to improve the quality of answer selection. However, these models focus on the similarity between questions and answers without considering background information. To this end, this paper proposes a novel refined answer selection method, which uses an attentive bidirectional long short-term memory (Bi-LSTM) network and a self-attention mechanism to solve these issues. First of all, this paper constructs the required knowledge-based text as background information and converts the questions and answers from words to vectors, respectively. Furthermore, the self-attention mechanism is adopted to extract the global features from the vectors. Finally, an attentive Bi-LSTM network is designed to address long-distance dependent learning problems and calculate the similarity between the question and answer with consideration of the background knowledge information. To verify the effectiveness of the proposed method, this paper constructs a knowledge-based QA dataset including multiple medical QA pairs and conducts a series of experiments on it. The experimental results reveal that the proposed approach could achieve impressive performance on the answer selection task and reach an accuracy of 71.4%, MAP of 68.8%, and decrease the BLUE indicator to 3.10. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Question-answering understanding systems are of central importance to many natural language processing tasks. A successful question-answering system first needs to accurately mine the semantics of the problem text and then match the semantic similarity between the question and the answer. Most of the current pre-training language modes use joint coding of questions and answers, a pre-training language model to avoid the problem of feature extraction from multilevel text structure, it through unified advance training ignores text semantic expression in different particle size, different levels of semantic features, and to some extent avoiding the serious problem of semantic understanding. In this paper, we focus on the problem of multi-granularity and multi-level feature expression of text semantics in question and answer understanding, and design a question-answering understanding method for multi-granularity hierarchical features. First, we extract features from two aspects, the traditional language model and the deep matching model, and then fuse these features to construct the similarity matrix, and learn the similarity matrix by designing three different models. Finally, the similarity matrix is learned by three different models, and after sorting, the overall similarity is obtained from the similarity of multiple granularity features. Evaluated by testing on WikiQA public datasets, experiments show that the results of our method are improved by adding the multi-granularity hierarchical feature learning method compared with traditional deep learning methods. [ABSTRACT FROM AUTHOR]

Given a question and a set of candidate answers, answer selection is the task of identifying the best answer, which can be viewed as a kind of learning-to-rank tasks. Learning to rank arises in many information retrieval applications, where deep learning models can achieve inspiring results. Training a deep learning model often requires large scale annotated data that are expensive and time-consuming to obtain. Active learning presents a promising approach to this problem by selecting more informative training data to reduce the amount of labelling efforts required. Because traditional active learning methods cannot be directly used for deep learning, researchers have proposed multiple deep active learning methods. However, none of the previous research efforts on deep active learning algorithms presents a specific framework for learning-to-rank tasks. In this work, we introduce a novel deep active learning framework based on Deep Expected Loss Optimization (DELO) for the answer selection task. It adopts a data acquisition function based on model uncertainty with Bayesian deep learning and the expected loss optimization. Moreover, a two-step batch-mode procedure, combining DELO and other data acquisition strategies is proposed to further improve the performance of active learning. Experimental results verify the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

Answer selection is a key part of question answering system, and improving its accuracy is also one of the important contents of question answering. In recent years, answer selection task has achieved good results using deep learning techniques. But there are still some limitations. Among them, model’s low utilization of semantic information, lack of local semantic attention, and poor ability to perceive the interaction between sentences are particularly prominent. Regarding the issue above, this paper proposes an answer selection model NHITAS(New Hierarchical Interactive Transformer for Answer Selection) based on Transformer and dual attention fusion. First, this model extracts question categories and keywords for preliminary screening of answers in the information preprocessing part, and introduces external knowledge as additional semantic supplements for sentences; Second, using a hierarchical interactive transformer to model the semantic context of sentences, and proposing two structures to learn semantic features, respectively UP-Transformer(Untied Position-Transformer) and DA-Transformer(Decay Self-Attention-Transformer); Finally, Dual attention fusion layers not only filter sentence noise but also enhance semantic interaction between question and answer. this paper has tested the performance of NHITAS on the WikiQA and TrecQA datasets. The experimental results show that this model can effectively improve the effect of the answer selection task compared with other models. [ABSTRACT FROM AUTHOR]

In recent years, Community Question Answering (CQA) becomes increasingly prevalent, because it provides platforms for users to collect information and share knowledge. However, given a question in a CQA system, there are often many different paired answers. It is almost impossible for users to view them item by item and select the most relevant one. Hence, answer selection becomes an important task of CQA. In this paper, we propose a novel solution - BertHANK, which is a hierarchical attention networks with enhanced knowledge and pre-trained model for answer selection. Specifically, in the encoding stage, knowledge enhancement and pre-training model are used for questions and answers, respectively. Further, we adopt multi-attention mechanism, including the cross-attention on question-answer pairs, the inner attention on questions at word level, and the hierarchical inner attention on answers at both word and sentence level, to capture more subtle semantic features. In more details, the cross-attention focuses on capturing interactive information among encoded questions and answers. While the hierarchical inner attention assigns different weights to words in sentences, and sentences in answers, thereby obtaining both global and local information of question-answer pairs. The hierarchical inner attention contributes to select out best-matched answers for specific questions. Finally, we integrate attention-questions and attention-answers to make prediction. The results show that our model achieves state-of-the-art performance on two corpora, SemEval-2015 and SemEval-2017 CQA datasets, outperforming the advanced baselines by a large margin. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

This article introduces Xiao-Shih, the first intelligent question answering bot on Chinese-based massive open online courses (MOOCs). Question answering is critical for solving individual problems. However, instructors on MOOCs must respond to many questions, and learners must wait a long time for answers. To address this issue, Xiao-Shih integrates many novel natural language processing and machine learning approaches to achieve state-of-the-art performance. Furthermore, Xiao-Shih has a built-in self-enriched mechanism for expanding the knowledge base through open community-based question answering. This article proposes a novel approach, known as spreading question similarity (SQS), which iterates similar keywords on our keyword networks to find duplicate questions. Compared with BERT, an advanced neural language model, the results showed that SQS outperforms BERT on recall and accuracy above a prediction probability threshold of 0.8. After training, Xiao-Shih achieved a perfect correct rate. Furthermore, Xiao-Shih outperforms Jill Watson 1.0, which is a noted question answering bot, on answer rate with the self-enriched mechanism. [ABSTRACT FROM AUTHOR]

As a key problem in artificial intelligence, question answering (QA) has always been a topic of intensive research. Most existing methods cast question answering as an answer selection task. The size of the candidate answer pool is usually very large, so it is difficult to accurately select the correct answer. One of the solutions is to narrow the range of candidate answer pool based on the category labels of the answers. However, QA tasks in reality usually only provide the category label of the question but not the category label of the answer. Based on this observation, we propose an Answer Category-Aware Answer Selection system (ACAAS), which jointly leverage unlabelled answer data and labelled question category data to generate answer category pseudo-labels in a joint embedding space. Experimental results on two public QA datasets demonstrate the effectiveness of the proposed method.

With the rapid increase of text information on the Internet, intelligent question answering has attracted considerable attention in many different domains. Many studies use intelligent question answering as an answer selection task and use local or global features to encode sentence representation, which has been proven to be very effective. However, due to the different characteristics of the corpora in different domains or languages, these methods usually suffer a great reduction in performance and cannot produce a sentence representation with good qualities. In this paper, we introduce Hybrid Model combining Local Composite features and Global features into a Siamese network (HM-LCGS) to alleviate the issue. The framework consists of a novel convolution neural network like architecture called local composite features convolution neural network to extract sufficient semantic information of the text from different granularity, shortcut connection to combine local composite features into pre-trained embeddings, alignment layer to mine the correlation between question and answer and bidirectional Long Short-Term Memory to encode the final sentence representation. The experimental results on InsuranceQA and cMedQA datasets show that with suitable granularity selection and embedding method, our proposed model can achieve competitive performance compared with other state-of-the-art models.

Answer selection, which is involved in many natural language processing applications, such as dialog systems and question answering (QA), is an important yet challenging task in practice, since conventional methods typically suffer from the issues of ignoring diverse real-world background knowledge. In this article, we extensively investigate approaches to enhancing the answer selection model with external knowledge from knowledge graph (KG). First, we present a context-knowledge interaction learning framework, Knowledge-aware Neural Network, which learns the QA sentence representations by considering a tight interaction with the external knowledge from KG and the textual information. Then, we develop two kinds of knowledge-aware attention mechanism to summarize both the context-based and knowledge-based interactions between questions and answers. To handle the diversity and complexity of KG information, we further propose a Contextualized Knowledge-aware Attentive Neural Network, which improves the knowledge representation learning with structure information via a customized Graph Convolutional Network and comprehensively learns context-based and knowledge-based sentence representation via the multi-view knowledge-aware attention mechanism. We evaluate our method on four widely used benchmark QA datasets, including WikiQA, TREC QA, InsuranceQA, and Yahoo QA. Results verify the benefits of incorporating external knowledge from KG and show the robust superiority and extensive applicability of our method. [ABSTRACT FROM AUTHOR]

Answer selection, as a crucial method for intelligent medical service robots, has become more and more important in natural language processing (NLP). However, there are still some critical issues in the answer selection model. On the one hand, the model lacks semantic understanding of long questions because of noise information in a question–answer (QA) pair. On the other hand, some researchers combine two or more neural network models to improve the quality of answer selection. However, these models focus on the similarity between questions and answers without considering background information. To this end, this paper proposes a novel refined answer selection method, which uses an attentive bidirectional long short-term memory (Bi-LSTM) network and a self-attention mechanism to solve these issues. First of all, this paper constructs the required knowledge-based text as background information and converts the questions and answers from words to vectors, respectively. Furthermore, the self-attention mechanism is adopted to extract the global features from the vectors. Finally, an attentive Bi-LSTM network is designed to address long-distance dependent learning problems and calculate the similarity between the question and answer with consideration of the background knowledge information. To verify the effectiveness of the proposed method, this paper constructs a knowledge-based QA dataset including multiple medical QA pairs and conducts a series of experiments on it. The experimental results reveal that the proposed approach could achieve impressive performance on the answer selection task and reach an accuracy of 71.4%, MAP of 68.8%, and decrease the BLUE indicator to 3.10.

Chinese selection is one of the most important subtasks in Chinese medical question-answer system. To obtain the representations of question and answer, an attractive method is to use the attentive pooling based deep neural network. However, this method suffers from the over-pooling problem. It generates attentive information by only using the related medical keywords, and neglects the local semantic information of sentences. In this paper, a novel co-attention fusion based deep neural network method is proposed. Our method solves the over-pooling problem by fusing local semantic information with attentive information. Because of the usage of the fusion mechanism, the proposed method tends to obtain more useful information for pooling and produce better representations for question and answer. For comparison, we create a new Chinese medical answer selection dataset in the epilepsy theme (i.e., cEpilepsyQA), and our method performs much better than the state-of-the-art methods. Also, the proposed method gets competitive results on the public Chinese medical answer selection datasets: cMedQA v1.0 and v2.0. [ABSTRACT FROM AUTHOR]

Answer selection (AS) aims to select correct answers for a question from an answer candidate set. Conventional AS methods generally address this task by independently matching the question and each candidate. However, since the matching information between the question and a single candidate is usually limited, it is not enough to use the question as the only evidence to estimate the correctness of each candidate. To address this problem, we propose a novel reinforcement learning (RL) based multi-step ranking model, named MS-Ranker, which accumulates candidate. In specific, we explicitly consider the potential correctness of candidates when accumulating information and update the evidence with a gating mechanism. Moreover, as we use a listwise ranking reward, our model learns to pay more attention to the overall performance. Experiments on three benchmarks, namely WikiQA, SemEval-2016 CQA and SelQA, show that our model significantly outperforms existing methods that do not rely on external resources. [ABSTRACT FROM AUTHOR]

In recent years, Question Answering systems have become more popular and widely used by users. Despite the increasing popularity of these systems, their performance is not even sufficient for textual data and requires further research. These systems consist of several parts that one of them is the Answer Selection component. This component detects the most relevant answer from a list of candidate answers. The methods presented in previous researches have attempted to provide an independent model to undertake the answer-selection task. An independent model cannot comprehend the syntactic and semantic features of questions and answers with a small training dataset. To fill this gap, language models can be employed in implementing the answer selection part. This action enables the model to have a better understanding of the language in order to understand questions and answers better than previous works. In this research, we will present the 'BAS' stands for BERT Answer Selection that uses the BERT language model to comprehend language. The empirical results of applying the model on the TrecQA Raw, TrecQA Clean, and WikiQA datasets demonstrate that using a robust language model such as BERT can enhance the performance. Using a more robust classifier also enhances the effect of the language model on the answer selection component. The results demonstrate that language comprehension is an essential requirement in natural language processing tasks such as answer selection. [ABSTRACT FROM AUTHOR]

Addressing Answer Selection (AS) tasks with complex neural networks typically requires a large amount of annotated data to increase the accuracy of the models. In this work, we are interested in simple models that can potentially give good performance on datasets with no or few annotations. First, we propose new unsupervised baselines that leverage distributed word and sentence representations. Second, we compare the ability of our neural architectures to learn from few annotated examples in a weakly supervised scheme and we demonstrate how these methods can benefit from a pre-training on an external dataset. With an emphasis on results reproducibility, we show that our simple methods can reach or approach state-of-the-art performances on four common AS datasets.

Answer selection is a crucial subtask in the question answering (QA) system. Conventional avenues for this task mainly concentrate on developing linguistic tools that are limited in both performance and practicability. Answer selection approaches based on deep learning have been well investigated with the tremendous success of deep learning in natural language processing. However, the traditional neural networks employed in existing answer selection models, i.e., recursive neural network or convolutional neural network, typically suffer from obtaining the global text information due to their operating mechanisms. The recent Transformer neural network is considered to be good at extracting the global information by employing only self-attention mechanism. Thus, in this paper, we design a Transformer-based neural network for answer selection, where we deploy a bidirectional long short-term memory (BiLSTM) behind the Transformer to acquire both global information and sequential features in the question or answer sentence. Different from the original Transformer, our Transformer-based network focuses on sentence embedding rather than the seq2seq task. In addition, we employ a BiLSTM rather than utilizing the position encoding to incorporate sequential features as the universal Transformer does. Furthermore, we apply three aggregated strategies to generate sentence embeddings for question and answer, i.e., the weighted mean pooling, the max pooling, and the attentive pooling, leading to three corresponding Transformer-based models, i.e., QA-TFWP, QA-TFMP, and QA-TFAP, respectively. Finally, we evaluate our proposals on a popular QA dataset WikiQA. The experimental results demonstrate that our proposed Transformer-based answer selection models can produce a better performance compared with several competitive baselines. In detail, our best model outperforms the state-of-the-art baseline by up to 2.37%, 2.83%, and 3.79% in terms of MAP, MRR, and accuracy, respectively.

Answer selection is an essential step in a question answering (QA) system. Traditional methods for this task mainly focus on developing linguistic features that are limited in practice. With the great success of deep learning method in distributed text representation, deep learning-based answer selection approaches have been well investigated, which mainly employ only one neural network, i.e., convolutional neural network (CNN) or long short term memory (LSTM), leading to failures in extracting some rich sentence features. Thus, in this paper, we propose a collaborative learning-based answer selection model (QA-CL), where we deploy a parallel training architecture to collaboratively learn the initial word vector matrix of the sentence by CNN and bidirectional LSTM (BiLSTM) at the same time. In addition, we extend our model by incorporating the sentence embedding generated by the QA-CL model into a joint distributed sentence representation using a strong unsupervised baseline weight removal (WR), i.e., the QA-CLWR model. We evaluate our proposals on a popular QA dataset, InsuranceQA. The experimental results indicate that our proposed answer selection methods can produce a better performance compared with several strong baselines. Finally, we investigate the models’ performance with respect to different question types and find that question types with a medium number of questions have a better and more stable performance than those types with too large or too small number of questions.

The answer selection task is one of the most important issues within the automatic question answering system, and it aims to automatically find accurate answers to questions. Traditional methods for this task use manually generated features based on tf-idf and n-gram models to represent texts, and then select the right answers according to the similarity between the representations of questions and the candidate answers. Nowadays, many question answering systems adopt deep neural networks such as convolutional neural network (CNN) to generate the text features automatically, and obtained better performance than traditional methods. CNN can extract consecutive n-gram features with fixed length by sliding fixed-length convolutional kernels over the whole word sequence. However, due to the complex semantic compositionality of the natural language, there are many phrases with variable lengths and be composed of non-consecutive words in natural language, such as these phrases whose constituents are separated by other words within the same sentences. But the traditional CNN is unable to extract the variable length n-gram features and non-consecutive n-gram features. In this paper, we propose a multi-scale deformable convolutional neural network to capture the non-consecutive n-gram features by adding offset to the convolutional kernel, and also propose to stack multiple deformable convolutional layers to mine multi-scale n-gram features by the means of generating longer n-gram in higher layer. Furthermore, we apply the proposed model into the task of answer selection. Experimental results on public dataset demonstrate the effectiveness of our proposed model in answer selection.

Given a question and its answer candidates (named QA corpus), answer selection is the task of identifying the most relevant answers to the question. Answer selection is widely used in question answering, web search, and so on. Current deep neural network models primarily utilize local features extracted from input question‐answer pairs (QA pairs). However, the global features contained in QA corpora are under‐utilized, and we argue that these global features substantially contribute to the answer selection task. To verify this point of view, we propose a novel model that combines local and global features for answer selection. In our model, two different global feature extractors are employed to extract statistical global features and deep global features from a QA corpus, respectively. Furthermore, we investigate the integration of these global features with local features in various experimental settings: statistical global features, deep global features, and a combination of statistical and deep global features. Our experimental results show that the global features are effective for answer selection. Our model obtains new state‐of‐the‐art results on two public answer selection datasets and performs especially well on YahooCQA, where it achieves 9.2 and 6% higher precision@1 (P@1) and mean reciprocal rank (MRR) scores than previously published models. [ABSTRACT FROM AUTHOR]

The goal of answer selection is to select the most applicable answers from an answer candidate pool. It plays an essential role in numerous applications in information retrieval (IR) and natural language processing (NLP). In this paper, we introduce a novel Knowledge-enhanced Hierarchical Attention mechanism for Answer Selection (KHAAS), which fully exploits the common sense knowledge from knowledge bases (KBs) and input textual information. Specifically, we first devise a three-stage knowledge-enhanced hierarchical attention mechanism, including the word-level attention, the phrase-level attention, and the document-level attention to learn the fact-aware intra-document features within questions and answers by fusing the knowledge from both the question/answer and KB. Hence, we can leverage the semantic compositionality of the question/answer and learn more holistic knowledge-enhanced intra-document features of the question/answer at three levels of granularity. Second, after obtaining the knowledge-enhanced question and answer representations, we employ a multi-perspective co-attention network to learn the complex inter-document relationships between the question and answer representations from different representation subspaces, which can capture the interactive semantics of the question and answer representations at three levels. Finally, we propose an adaptive decision fusion method to learn a more effective and robust ensemble answer selection model by adaptively combining multiple classifiers learned with different levels of features. Experimental results on three large-scale answer selection datasets demonstrate that KHAAS consistently outperforms the compared methods. [ABSTRACT FROM AUTHOR]