Semantic passage segmentation based on sentence topics for question answering

We propose a semantic passage segmentation method for a Question Answering (QA) system. We define a semantic passage as sentences grouped by semantic coherence, determined by the topic assigned to individual sentences. Topic assignments are done by a sentence classifier based on a statistical classification technique, Maximum Entropy (ME), combined with multiple linguistic features. We ran experiments to evaluate the proposed method and its impact on application tasks, passage retrieval and template-filling for question answering. The experimental result shows that our semantic passage retrieval method using topic matching is more useful than fixed length passage retrieval. With the template-filling task used for information extraction in the QA system, the value of the sentence topic assignment method was reinforced.     

Applying question answering technology to locating malevolent online content

We have empirically compared two classes of technologies capable of locating potentially malevolent online content: 1) popular keyword searching, currently widely used by law enforcement and general public, and 2) emerging question answering (QA). The Google search engine exemplified the first approach. To exemplify the second, we further advanced the pattern based probabilistic QA approach and implemented a proof-of-concept prototype that was capable of finding web pages that provide the answers to the given questions, including non-factual ones (e.g. “How to build a pipe bomb?”). The answers to those question typically indicate the presence of malevolent content. Our findings suggest that QA technology can be a good addition to the traditional keyword searching for the task of locating malevolent online content and, possibly, for a more general task of interactive online information exploration.     

Instance-sequence reasoning for video question answering

Video question answering (Video QA) involves a thorough understanding of video content and question language, as well as the grounding of the textual semantic to the visual content of videos. Thus, to answer the questions more accurately, not only the semantic entity should be associated with certain visual instance in video frames, but also the action or event in the question should be localized to a corresponding temporal slot. It turns out to be a more challenging task that requires the ability of conducting reasoning with correlations between instances along temporal frames. In this paper, we propose an instance-sequence reasoning network for video question answering with instance grounding and temporal localization. In our model, both visual instances and textual representations are firstly embedded into graph nodes, which benefits the integration of intra- and inter-modality. Then, we propose graph causal convolution (GCC) on graph-structured sequence with a large receptive field to capture more causal connections, which is vital for visual grounding and instance-sequence reasoning. Finally, we evaluate our model on TVQA+ dataset, which contains the groundtruth of instance grounding and temporal localization, three other Video QA datasets and three multimodal language processing datasets. Extensive experiments demonstrate the effectiveness and generalization of the proposed method. Specifically, our method outperforms the state-of-the-art methods on these benchmarks.     

A survey on question answering technology from an information retrieval perspective

This article provides a comprehensive and comparative overview of question answering technology. It presents the question answering task from an information retrieval perspective and emphasises the importance of retrieval models, i.e., representations of queries and information documents, and retrieval functions which are used for estimating the relevance between a query and an answer candidate. The survey suggests a general question answering architecture that steadily increases the complexity of the representation level of questions and information objects. On the one hand, natural language queries are reduced to keyword-based searches, on the other hand, knowledge bases are queried with structured or logical queries obtained from the natural language questions, and answers are obtained through reasoning. We discuss different levels of processing yielding bag-of-words-based and more complex representations integrating part-of-speech tags, classification of the expected answer type, semantic roles, discourse analysis, translation into a SQL-like language and logical representations.     

Skeleton parsing for complex question answering over knowledge bases

Answering complex questions involving multiple relations over knowledge bases is a challenging task. Many previous works rely on dependency parsing. However, errors in dependency parsing would influence their performance, in particular for long complex questions. In this paper, we propose a novel skeleton grammar to represent the high-level structure of a complex question. This lightweight formalism and its BERT-based parsing algorithm help to improve the downstream dependency parsing. To show the effectiveness of skeleton, we develop two question answering approaches: skeleton-based semantic parsing (called SSP) and skeleton-based information retrieval (called SIR). In SSP, skeleton helps to improve structured query generation. In SIR, skeleton helps to improve path ranking. Experimental results show that, thanks to skeletons, our approaches achieve state-of-the-art results on three datasets: LC-QuAD 1.0, GraphQuestions, and ComplexWebQuestions 1.1.     

A question answering system for project management applications

The usage of computer applications in the construction industry is increasing, as is the complexity of software applications and this makes it difficult for project personnel to maintain familiarity. Furthermore, the causes of practical problems, such as project delays and cost over-runs, are often not derivable from the output of most software. A question answering system provides a means for directly extracting knowledge from this output. This paper begins with an examination of issues involved in building such a system. An emerging industry standard, ifcXML, is adopted as the knowledge representation format, thereby reducing the effort that is necessary to build a knowledge base. We then explore the mechanisms that use information in the knowledge base for question understanding. A prototype system has been built and tested to illustrate usefulness for project management applications.     

基于实体排序和联合事实选择的知识库问答

针对大多数简单知识库问答模型没有充分利用候选实体排序,并且往往忽略实体和关系之间依赖的问题,提出了基于实体排序和联合事实选择的方法。整个过程分为模式抽取、实体排序和联合事实选择三个步骤。首先,通过BILSTM-CRF算法对自然语言问题进行模式提取,将其划分为实体提及（mention）和问题模式（pattern）两部分;然后,同时利用subject（主题实体）和mention的字面和语义相似性对候选实体进行排序,抽取相关事实;最后,为了能在候选事实池中选择出最正确的实体—关系对,联合事实选择模型利用多级别编码增强整个过程。实验证明,该方法在simple questions dataset的准确率、召回率都有明显的提升。实验结果表明所提方法在知识库的简单问答上具有可行性。     

网络答疑本体的生成与匹配方法研究*

针对网络答疑具体任务,提出答疑本体概念,构建答疑本体,并提出一种基于答疑本体的答案匹配方法和相似度计算公式。公式不仅考虑词之间的相似度,还考虑问题答案对(QAp)在本体中的位置。该位置信息隐含了句子结构上的语义和词的语义扩展。实验结果表明提出的答疑本体能够有效表示QAp,易于答疑系统的检索匹配。     

基于HNC句类的社区问答系统问句检索模型构建

社区问答系统中充斥着大量的噪声,给用户检索信息造成麻烦,以往的问句检索模型大多集中在词语层面。针对以上问题构建句子层面的问句检索模型。新模型基于概念层次网络（hierarchincal network of concept,HNC）理论当中的句类知识,从句子的语用、语法和语义三个层面计算问句间相似度。通过问句分类算法确定查询问句和候选问句的问句类别,得到问句间的语用相似度,利用句类表达式的结构和语义块组成分别计算问句间的语法及语义相似度。在真实数据集上的实验表明,基于HNC句类的新模型提高了问句检索结果的准确性。     

The measurement of user satisfaction with question answering systems

Question Answering Systems (QAS) are receiving increasing attention from IS researchers, particularly those in the information retrieval and natural language processing communities. Evaluation of an IS's success and user satisfaction are important issues, especially for emerging online service systems using the Internet. Although many QAS have been implemented, little work has been done on the development of an evaluation model for them. Our purpose was to develop a validated instrument to measure user satisfaction with QAS (USQAS). The proposed validated instrument was intended as a reference for the design of QAS from a user's perspective.     

问答系统中问题模式分类与相似度计算方法

基于FAQ库的限定域自动问答系统由于更具实用性而成为自然语言处理领域的研究热点,而问题之间的相似度计算是其中最关键的技术。现有的问句相似度计算技术在处理带有上下文情景描述的问题时效果较差。针对现有技术存在的问题,提出将用户问题分为简洁模式问题（SMQs）和情景模式问题（CMQs）,并提出了基于规则的问题模式分类算法。在此基础上,进一步提出了综合考察情景相似度和问句相似度的情景模式问题（CMQs）相似度计算方法。实验结果表明,问题模式分类算法取得了90%以上的准确率和召回率,情景模式问题相似度计算方法在时间复杂度较低的情况下也取得了74.3%的正确率。     

基于Web的问答系统综述

微软小冰引发了问答系统的新一轮研究热潮。作为一种新型的信息检索方式,问答系统能直接以自然语言与用户进行人性化的交互。而基于Web的问答系统能通过搜索引擎获取开放的互联网上的各种相关信息,并将以自然语言形式表述的准确答案返回给用户,因此此类系统同时具有搜索引擎和问答系统的优点。首先,对基于Web的问答系统的研究背景与发展历史进行了概述;然后,详细介绍了基于Web的问答系统的架构及其问题分析、信息检索、答案抽取这三大关键技术的研究进展;在此基础上,分析了基于Web的问答系统所面临的问题;最后,对基于Web的问答系统的未来发展趋势进行了展望。     

A building regulation question answering system: A deep learning methodology

Regulations play an important role in assuring the quality of a building’s construction and minimizing its adverse environmental impacts. Engineers and the like need to retrieve regulatory information to ensure a building conforms to specified standards. Despite the availability of search engines and digital databases that can be used to store regulations, engineers, for example, are unable to retrieve information for domain-specific needs in a timely manner. As a consequence, users often have to deal with the burden of browsing and filtering information, which can be a time-consuming process. This research develops a robust end-to-end methodology to improve the efficiency and effectiveness of retrieving queries pertaining to building regulations. The developed methodology integrates information retrieval with a deep learning model of Natural Language Processing (NLP) to provide precise and rapid answers to user’s questions from a collection of building regulations. The methodology is evaluated and a prototype system to retrieve queries is developed. The paper’s contribution is therefore twofold as it develops a: (1) methodology that combines NLP and deep learning to be able to address queries raised about the building regulations; and (2) chatbot of question answering system, which we refer to as QAS4CQAR. Our proposed methodology has powerful feature representation and learning capability and therefore can potentially be adopted to building regulations in other jurisdictions.     

基于多路语义图网络的图像自动问答

基于视觉特征与文本特征融合的图像问答已经成为自动问答的热点研究问题之一。现有的大部分模型都是通过注意力机制来挖掘图像和问题语句之间的关联关系,忽略了图像区域和问题词在同一模态之中以及不同视角的关联关系。针对该问题,提出一种基于多路语义图网络的图像自动问答模型（MSGN）,从多个角度挖掘图像和问题之间的语义关联。MSGN利用图神经网络模型挖掘图像区域和问题词细粒度的模态内模态间的关联关系,进而提高答案预测的准确性。模型在公开的图像问答数据集上的实验结果表明,从多个角度挖掘图像和问题之间的语义关联可提高图像问题答案预测的性能。     

AquaLog: An ontology-driven question answering system for organizational semantic intranets

The semantic web vision is one in which rich, ontology-based semantic markup will become widely available. The availability of semantic markup on the web opens the way to novel, sophisticated forms of question answering. AquaLog is a portable question-answering system which takes queries expressed in natural language and an ontology as input, and returns answers drawn from one or more knowledge bases (KBs). We say that AquaLog is portable because the configuration time required to customize the system for a particular ontology is negligible. AquaLog presents an elegant solution in which different strategies are combined together in a novel way. It makes use of the GATE NLP platform, string metric algorithms, WordNet and a novel ontology-based relation similarity service to make sense of user queries with respect to the target KB. Moreover it also includes a learning component, which ensures that the performance of the system improves over the time, in response to the particular community jargon used by end users.     

Structure-sensitive semantic matching for aggregate question answering over knowledge base

Aggregate question answering essentially returns answers for given questions by obtaining query graphs with unique dependencies between values and corresponding objects. Word order dependency, as the key to uniquely identify dependency of the query graph, reflects the dependencies between the words in the question. However, due to the semantic gap caused by the expression difference between questions encoded with word vectors and query graphs represented with logical formal elements, it is not trivial to match the correct query graph for the question. Most existing approaches design more expressive query graphs for complex questions and rank them just by directly calculating their similarities, ignoring the semantic gap between them. In this paper, we propose a novel Structure-sensitive Semantic Matching(SSM) approach that learns aligned representations of dependencies in questions and query graphs to eliminate their gap. First, we propose a cross-structure matching module to bridge the gap between two modalities(i.e., textual question and query graph). Then, we propose an entropy-based gated AQG filter to remove the structural noise caused by the uncertainty of dependencies. Finally, we present a two-channel query graph representation that fuses the semantics of abstract structure and grounding content of the query graph explicitly. Experimental results show that SSM could learn aligned representations of questions and query graphs to eliminate the gaps between their dependencies, and improves up to 12% (F1 score) on aggregation questions of two benchmark datasets.     

Evaluating question answering over linked data

The availability of large amounts of open, distributed, and structured semantic data on the web has no precedent in the history of computer science. In recent years, there have been important advances in semantic search and question answering over RDF data. In particular, natural language interfaces to online semantic data have the advantage that they can exploit the expressive power of Semantic Web data models and query languages, while at the same time hiding their complexity from the user. However, despite the increasing interest in this area, there are no evaluations so far that systematically evaluate this kind of systems, in contrast to traditional question answering and search interfaces to document spaces. To address this gap, we have set up a series of evaluation challenges for question answering over linked data. The main goal of the challenge was to get insight into the strengths, capabilities, and current shortcomings of question answering systems as interfaces to query linked data sources, as well as benchmarking how these interaction paradigms can deal with the fact that the amount of RDF data available on the web is very large and heterogeneous with respect to the vocabularies and schemas used. Here, we report on the results from the first and second of such evaluation campaigns. We also discuss how the second evaluation addressed some of the issues and limitations which arose from the first one, as well as the open issues to be addressed in future competitions.     

Translational relation embeddings for multi-hop knowledge base question answering

Multi-hop Knowledge Base Question Answering (KBQA) aims to predict answers that require multi-hop reasoning from the topic entity in the question over the Knowledge Base (KB). Relation extraction is a core step in KBQA, which extracts the relation path from the topic entity to the answer entity. Compared with single-hop questions, multi-hop ones have more complex syntactic structures to understand, and multi-hop relation paths lead to a larger search space, which makes it much more challenging to extract the correct relation paths. To tackle the above challenges, most existing relation extraction approaches focus on the semantic similarity between questions and relation paths. However, those approaches only consider the word semantics of the relation names but ignore the graph semantics inside the knowledge base. As a result, their generalization ability relying on the naming rules of the relations, making it more difficult to generalize over large knowledge bases.To address the current limitations and take advantage of the graph semantics of relations, we propose a novel translational embedding-based relation extractor that utilizes pretrained embeddings from TransE. In particular, we treat the multi-hop relation path as a translation from the first relation to the last one in the semantic space of TransE. Then we map the question into this space under the supervision of the path embeddings. To take full advantage of the pretrained graph semantics in TransE, we propose a KBQA framework that leverages pretrained relation semantics in relation extraction and pretrained entity semantics in answer selection. Our approach achieves state-of-the-art performance on two benchmark datasets, WebQuestionSP and MetaQA, demonstrating its effectiveness on the multi-hop KBQA task.     

基于Chunk-CRF的情感问答研究

相对于事实性问答系统而言,观点或情感问答系统的研究除了需要考虑观点持有者及情感倾向性等与情感相关问题以外,其难点还在于答案形式更复杂更分散.从百度知道人工搜集了大量的情感问题,并根据情感问题的特征,统计并归纳了五大情感问题类型.问题分类模式与传统事实性问答系统不同,不能仅仅根据疑问词对其进行分类,还需要考虑到观点以及受众的反应.问题分类使用基于Chunk的CRF模型与规则相结合的情感问题分类方法.在答案抽取时结合组块识别的结果和情感的倾向性,并根据情感问题类型的不同采取不同的方法以获取答案.实验结果表明了评价体系的有效性.     

一种基于主题类别信息问句检索的新方法

社区问答系统CQA(Community Question Answering),如雅虎问答是专门为了解决传统搜索引擎的局限来帮助用户获取有用信息的社区。问句检索在CQA中主要是针对用户提出来的新问题,在历史问答对中检索出与用户最相关的问题,从而减少用户等待的时间,给用户带来更好的体验。提出一种基于主题类别信息问句检索的新方法来解决问句检索问题,利用问句的主题类别信息对语言模型进行平滑,同时融入问句的语义信息来解决问句检索问题。实验在Yahoo!Answers上抽取的真实标注数据集上进行,对比实验结果表明,所提出的方法在性能上得到了较好的结果。