Our goal is to answer elementary-level science questions using knowledge extracted automatically from science textbooks, expressed in a subset of first-order logic. Given the incomplete and noisy nature of these automatically extracted rules, Markov Logic Networks (MLNs) seem a natural model to use, but the exact way of leveraging MLNs is by no means obvious. We investigate three ways of applying MLNs to our task. In the first, we simply use the extracted science rules directly as MLN clauses. Unlike typical MLN applications, our domain has long and complex rules, leading to an unmanageable number of groundings. We exploit the structure present in hard constraints to improve tractability, but the formulation remains ineffective. In the second approach, we instead interpret science rules as describing prototypical entities, thus mapping rules directly to grounded MLN assertions, whose constants are then clustered using existing entity resolution methods. This drastically simplifies the network, but still suffers from brittleness. Finally, our third approach, called Praline, uses MLNs to align the lexical elements as well as define and control how inference should be performed in this task. Our experiments, demonstrating a 15\% accuracy boost and a 10x reduction in runtime, suggest that the flexibility and different inference semantics of Praline are a better fit for the natural language question answering task.
Some questions have multiple answers that are not equally correct, i.e. answers are different under different conditions. Conditions are used to distinguish answers as well as to provide additional information to support them. In this paper, we study a more challenging task where answers are constrained by a list of conditions that logically interact, which requires performing logical reasoning over the conditions to determine the correctness of the answers. Even more challenging, we only provide evidences for a subset of the conditions, so some questions may not have deterministic answers. In…
Research on open-domain question answering (QA) has a long tradition. A challenge in this domain is answering complex questions (CQA) that require complex inference methods and large amounts of knowledge. In low resource languages, such as Persian, there are not many datasets for open-domain complex questions and also the language processing toolkits are not very accurate. In this paper, we propose a knowledge-based approach for answering Persian complex questions using Farsbase; the Persian knowledge graph, exploiting PeCoQ; the newly created complex Persian question dataset. In this work, we…
We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation. We encode tables as graphs using a graph neural network model based on the Transformer architecture. The answers are then selected from the encoded graph using a pointer network. This model is appropriate for processing conversations around structured data, where the attention mechanism that selects the answers to a question can also be used to resolve conversational references. We demonstrate the validity of…
Qualitative relationships describe how increasing or decreasing one property (e.g. altitude) affects another (e.g. temperature). They are an important aspect of natural language question answering and are crucial for building chatbots or voice agents where one may enquire about qualitative relationships. Recently a dataset about question answering involving qualitative relationships has been proposed, and a few approaches to answer such questions have been explored, in the heart of which lies a semantic parser that converts the natural language input to a suitable logical form. A problem with …
Georgia Institute of Technology（佐治亚理工学院）；Cisco（思科）；Georgia Tech Research Institute（佐治亚理工研究所）
Visual question answering (VQA) has been gaining a lot of traction in the machine learning community in the recent years due to the challenges posed in understanding information coming from multiple modalities (i.e., images, language). In VQA, a series of questions are posed based on a set of images and the task at hand is to arrive at the answer. To achieve this, we take a symbolic reasoning based approach using the framework of formal logic. The image and the questions are converted into symbolic representations on which explicit reasoning is performed. We propose a formal logic framework wh…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Arizona State University（亚利桑那州立大学）
While in recent years machine learning (ML) based approaches have been the popular approach in developing end-to-end question answering systems, such systems often struggle when additional knowledge is needed to correctly answer the questions. Proposed alternatives involve translating the question and the natural language text to a logical representation and then use logical reasoning. However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text. The proposed method use…
University of Washington（华盛顿大学）；Allen Institute for AI（艾伦人工智能研究所）
Many natural language questions require qualitative, quantitative or logical comparisons between two entities or events. This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions by integrating logic rules and neural models. Our method leverages logical and linguistic knowledge to augment labeled training data and then uses a consistency-based regularizer to train the model. Improving the global consistency of predictions, our approach achieves large improvements over previous methods in a variety of question answering (QA) tasks including …
State-of-the-art approaches to reasoning and question answering over knowledge graphs (KGs) usually scale with the number of edges and can only be applied effectively on small instance-dependent subgraphs. In this paper, we address this issue by showing that multi-hop and more complex logical reasoning can be accomplished separately without losing expressive power. Motivated by this insight, we propose an approach to multi-hop reasoning that scales linearly with the number of relation types in the graph, which is usually significantly smaller than the number of edges or nodes. This produces a …
University of Technology Sydney（悉尼科技大学）；Microsoft（微软）
Many algorithms for Knowledge-Based Question Answering (KBQA) depend on semantic parsing, which translates a question to its logical form. When only weak supervision is provided, it is usually necessary to search valid logical forms for model training. However, a complex question typically involves a huge search space, which creates two main problems: 1) the solutions limited by computation time and memory usually reduce the success rate of the search, and 2) spurious logical forms in the search results degrade the quality of training data. These two problems lead to a poorly-trained semantic …
Sun Yat-sen University（中山大学）；Microsoft Research（微软研究院）
We study question answering over a dynamic textual environment. Although neural network models achieve impressive accuracy via learning from input-output examples, they rarely leverage various types of knowledge and are generally not interpretable. In this work, we propose a graph-based approach, where a heterogeneous graph is automatically built with factual knowledge of the context, temporal knowledge of the past states, and logical knowledge that combines human-curated knowledge bases and rule bases. We develop a graph neural network over the constructed graph, and train the model in an end…
York University（约克大学）；Nanyang Technological University（南洋理工大学）；Salesforce Research（赛富时研究院）
Charts are very popular for analyzing data. When exploring charts, people often ask a variety of complex reasoning questions that involve several logical and arithmetic operations. They also commonly refer to visual features of a chart in their questions. However, most existing datasets do not focus on such complex reasoning questions as their questions are template-based and answers come from a fixed-vocabulary. In this work, we present a large-scale benchmark covering 9.6K human-written questions as well as 23.1K questions generated from human-written chart summaries. To address the unique c…
Given an image, a back-ground knowledge, and a set of questions about an object, human learners answer the questions very consistently regardless of question forms and semantic tasks. The current advancement in neural-network based Visual Question Answering (VQA), despite their impressive performance, cannot ensure such consistency due to identically distribution (i.i.d.) assumption. We propose a new model-agnostic logic constraint to tackle this issue by formulating a logically consistent loss in the multi-task learning framework as well as a data organisation called family-batch and hybrid-b…
PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering
School of Computer Science and Technology, Xi’an Jiaotong University（西安交通大学计算机科学与技术学院）；Ministry of Education Key Laboratory of Intelligent Networks and Network Security（教育部智能网络与网络安全重点实验室）；Shaanxi Province Key Laboratory of Big Data Knowledge Engineering（陕西省大数据知识工程重点实验室）
Parsing natural language questions into executable logical forms is a useful and interpretable way to perform question answering on structured data such as knowledge bases (KB) or databases (DB). However, existing approaches on semantic parsing cannot adapt to both modalities, as they suffer from the exponential growth of the logical form candidates and can hardly generalize to unseen data. In this work, we propose Uni-Parser, a unified semantic parser for question answering (QA) on both KB and DB. We introduce the primitive (relation and entity in KB, and table name, column name and cell valu…
We implement Groenendijk and Stokhof's partition semantics of questions in a simple question answering algorithm. The algorithm is sound, complete, and based on tableau theorem proving. The algorithm relies on a syntactic characterization of answerhood: Any answer to a question is equivalent to some formula built up only from instances of the question. We prove this characterization by translating the logic of interrogation to classical predicate logic and applying Craig's interpolation theorem.
MedLogic-AQA: Enhancing Medical Question Answering with Abstractive Models Focusing on Logical Structures
School of AI and Data Science, Indian Institute of Technology Jodhpur（印度焦特布尔印度理工学院人工智能与数据科学学院）；Department of Computer Science and Engineering, Indian Institute of Technology Patna（印度巴特那印度理工学院计算机科学与工程系）
UMass-Amherst（马萨诸塞大学阿默斯特分校）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research, Cambridge（IBM剑桥研究院）
We explore state-of-the-art neural models for question answering on electronic medical records and improve their ability to generalize better on previously unseen (paraphrased) questions at test time. We enable this by learning to predict logical forms as an auxiliary task along with the main task of answer span detection. The predicted logical forms also serve as a rationale for the answer. Further, we also incorporate medical entity information in these models via the ERNIE architecture. We train our models on the large-scale emrQA dataset and observe that our multi-task entity-enriched mode…
Microsoft Research（微软研究院）；Nanjing University（南京大学）；Nankai University（南开大学）；Harbin Institute of Technology（哈尔滨工业大学）
Pre-trained language models (PLMs) have shown their effectiveness in multiple scenarios. However, KBQA remains challenging, especially regarding coverage and generalization settings. This is due to two main factors: i) understanding the semantics of both questions and relevant knowledge from the KB; ii) generating executable logical forms with both semantic and syntactic correctness. In this paper, we present a new KBQA model, TIARA, which addresses those issues by applying multi-grained retrieval to help the PLM focus on the most relevant KB contexts, viz., entities, exemplary logical forms, …
Department of Computer Science ETH Zurich（苏黎世联邦理工学院计算机科学系）；ETH Zurich（苏黎世联邦理工学院）；Switzerland（瑞士）
Advances in natural language processing tasks have gained momentum in recent years due to the increasingly popular neural network methods. In this paper, we explore deep learning techniques for answering multi-step reasoning questions that operate on semi-structured tables. Challenges here arise from the level of logical compositionality expressed by questions, as well as the domain openness. Our approach is weakly supervised, trained on question-answer-table triples without requiring intermediate strong supervision. It performs two phases: first, machine understandable logical forms (programs…
Arizona State University（亚利桑那州立大学）；University of Maryland, College Park（马里兰大学学院市分校）
In this work, we explore a genre of puzzles ("image riddles") which involves a set of images and a question. Answering these puzzles require both capabilities involving visual detection (including object, activity recognition) and, knowledge-based or commonsense reasoning. We compile a dataset of over 3k riddles where each riddle consists of 4 images and a groundtruth answer. The annotations are validated using crowd-sourced evaluation. We also define an automatic evaluation metric to track future progress. Our task bears similarity with the commonly known IQ tasks such as analogy solving, seq…
University of Auckland（奥克兰大学）；University of Birmingham（伯明翰大学）
State of the art algorithms for many pattern recognition problems rely on deep network models. Training these models requires a large labeled dataset and considerable computational resources. Also, it is difficult to understand the working of these learned models, limiting their use in some critical applications. Towards addressing these limitations, our architecture draws inspiration from research in cognitive systems, and integrates the principles of commonsense logical reasoning, inductive learning, and deep learning. In the context of answering explanatory questions about scenes and the un…
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM TJ Watson Research Center（IBM托马斯·J·沃森研究中心）；University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carle Illinois College of Medicine（伊利诺伊大学卡勒医学院）
We propose a novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks. We demonstrate an instance of this methodology in generating a large-scale QA dataset for electronic medical records by leveraging existing expert annotations on clinical notes for various NLP tasks from the community shared i2b2 datasets. The resulting corpus (emrQA) has 1 million question-logical form and 400,000+ question-answer evidence pairs. We characterize the dataset and explore its learning potential by training baseline mode…
Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）；The Open University of China（国家开放大学）
University of Bonn（波恩大学）；Zerotha Research（泽罗塔研究院）；Cerence GmbH（赛轮思有限公司）；University of Siegen（锡根大学）；Amazon（亚马逊）；Institute for Applied Informatics（应用信息学研究所）
This paper addresses the task of conversational question answering (ConvQA) over knowledge graphs (KGs). The majority of existing ConvQA methods rely on full supervision signals with a strict assumption of the availability of gold logical forms of queries to extract answers from the KG. However, creating such a gold logical form is not viable for each potential question in a real-world scenario. Hence, in the case of missing gold logical forms, the existing information retrieval-based approaches use weak supervision via heuristics or reinforcement learning, formulating ConvQA as a KG path rank…
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory and control, facilitates data-driven iterative reasoning. This makes it an ideal candidate for solving tasks that involve logical reasoning. Our experiments with 20 bAbI tasks demonstrate the value of MAC net as a data-efficient and interpretable architecture for Natural Language Q…
Multi-hop Question Answering (QA) requires the machine to answer complex questions by finding scattering clues and reasoning from multiple documents. Graph Network (GN) and Question Decomposition (QD) are two common approaches at present. The former uses the "black-box" reasoning process to capture the potential relationship between entities and sentences, thus achieving good performance. At the same time, the latter provides a clear reasoning logical route by decomposing multi-hop questions into simple single-hop sub-questions. In this paper, we propose a novel method to complete multi-hop QA…
Oxford University Computing Laboratory（牛津大学计算实验室）；Dresden University of Technology（德累斯顿工业大学）；The University of Manchester（曼彻斯特大学）
Conjunctive queries play an important role as an expressive query language for Description Logics (DLs). Although modern DLs usually provide for transitive roles, conjunctive query answering over DL knowledge bases is only poorly understood if transitive roles are admitted in the query. In this paper, we consider unions of conjunctive queries over knowledge bases formulated in the prominent DL SHIQ and allow transitive roles in both the query and the knowledge base. We show decidability of query answering in this setting and establish two tight complexity bounds: regarding combined complexity,…
Answering logical queries over incomplete knowledge bases is challenging because: 1) it calls for implicit link prediction, and 2) brute force answering of existential first-order logic queries is exponential in the number of existential variables. Recent work of query embeddings provides fast querying, but most approaches model set logic with closed regions, so lack negation. Query embeddings that do support negation use densities that suffer drawbacks: 1) only improvise logic, 2) use expensive distributions, and 3) poorly model answer uncertainty. In this paper, we propose Logic Embeddings, …
Neural-Symbolic Logic Query Answering in Non-Euclidean Space
Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（巴黎-罗克琴堡研究所）；Rajiv Gandhi University（拉朱·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒尔研究实验室）
We examine the recently proposed language of Logical Credal Networks, in particular investigating the consequences of various Markov conditions. We introduce the notion of structure for a Logical Credal Network and show that a structure without directed cycles leads to a well-known factorization result. For networks with directed cycles, we analyze the differences between Markov conditions, factorization results, and specification requirements.
We study the problem of finite ontology mediated query answering (FOMQA), the variant of OMQA where the represented world is assumed to be finite, and thus only finite models of the ontology are considered. We adopt the most typical setting with unions of conjunctive queries and ontologies expressed in description logics (DLs). The study of FOMQA is relevant in settings that are not finitely controllable. This is the case not only for DLs without the finite model property, but also for those allowing transitive role declarations. When transitive roles are allowed, evaluating queries is challen…
Query containment and query answering are two important computational tasks in databases. While query answering amounts to compute the result of a query over a database, query containment is the problem of checking whether for every database, the result of one query is a subset of the result of another query. In this paper, we deal with unions of conjunctive queries, and we address query containment and query answering under Description Logic constraints. Every such constraint is essentially an inclusion dependencies between concepts and relations, and their expressive power is due to the poss…
Czech Technical University in Prague（布拉格捷克理工大学）；KU Leuven（鲁汶大学）
We study lifted weight learning of Markov logic networks. We show that there is an algorithm for maximum-likelihood learning of 2-variable Markov logic networks which runs in time polynomial in the domain size. Our results are based on existing lifted-inference algorithms and recent algorithmic results on computing maximum entropy distributions.
Markov logic uses weighted formulas to compactly encode a probability distribution over possible worlds. Despite the use of logical formulas, Markov logic networks (MLNs) can be difficult to interpret, due to the often counter-intuitive meaning of their weights. To address this issue, we propose a method to construct a possibilistic logic theory that exactly captures what can be derived from a given MLN using maximum a posteriori (MAP) inference. Unfortunately, the size of this theory is exponential in general. We therefore also propose two methods which can derive compact theories that still …
Combining first-order logic and probability has long been a goal of AI. Markov logic (Richardson & Domingos, 2006) accomplishes this by attaching weights to first-order formulas and viewing them as templates for features of Markov networks. Unfortunately, it does not have the full power of first-order logic, because it is only defined for finite domains. This paper extends Markov logic to infinite domains, by casting it in the framework of Gibbs measures (Georgii, 1988). We show that a Markov logic network (MLN) admits a Gibbs measure as long as each ground atom has a finite number of neighbor…
Markov Logic Networks (MLN) and Probabilistic Soft Logic (PSL) are widely applied formalisms in Statistical Relational Learning, an emerging area in Artificial Intelligence that is concerned with combining logical and statistical AI. Despite their resemblance, the relationship has not been formally stated. In this paper, we describe the precise semantic relationship between them from a logical perspective. This is facilitated by first extending fuzzy logic to allow weights, which can be also viewed as a generalization of PSL, and then relate that generalization to MLN. We observe that the rela…
DISIM Università di L’Aquila（拉奎拉大学DISIM）；DMI Università di Perugia（佩鲁贾大学DMI）
In recent work we defined resource-based answer set semantics, which is an extension to answer set semantics stemming from the study of its relationship with linear logic. In fact, the name of the new semantics comes from the fact that in the linear-logic formulation every literal (including negative ones) were considered as a resource. In this paper, we propose a query-answering procedure reminiscent of Prolog for answer set programs under this extended semantics as an extension of XSB-resolution for logic programs with negation. We prove formal properties of the proposed procedure. Under con…
A prominent problem in knowledge representation is how to answer queries taking into account also the implicit consequences of an ontology representing domain knowledge. While this problem has been widely studied within the realm of description logic ontologies, it has been surprisingly neglected within the context of vague or imprecise knowledge, particularly from the point of view of mathematical fuzzy logic. In this paper we study the problem of answering conjunctive queries and threshold queries w.r.t. ontologies in fuzzy DL-Lite. Specifically, we show through a rewriting approach that thr…
Exploring the Paradigm Shift from Grounding to Skolemization for Complex Query Answering on Knowledge Graphs
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；School of Data Science, Lingnan University（岭南大学数据科学学院）；School of Science and Technology, Hong Kong Metropolitan University（香港理工大学科技学院）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）
The paper introduces k-bounded MAP inference, a parameterization of MAP inference in Markov logic networks. k-Bounded MAP states are MAP states with at most k active ground atoms of hidden (non-evidence) predicates. We present a novel delayed column generation algorithm and provide empirical evidence that the algorithm efficiently computes k-bounded MAP states for meaningful real-world graph matching problems. The underlying idea is that, instead of solving one large optimization problem, it is often more efficient to tackle several small ones.
Institute for Collaborating and Communicating Systems（协作与交流系统研究所）；School of Informatics（信息学院）；University of Edinburgh（爱丁堡大学）
In this work we present Cutting Plane Inference (CPI), a Maximum A Posteriori (MAP) inference method for Statistical Relational Learning. Framed in terms of Markov Logic and inspired by the Cutting Plane Method, it can be seen as a meta algorithm that instantiates small parts of a large and complex Markov Network and then solves these using a conventional MAP method. We evaluate CPI on two tasks, Semantic Role Labelling and Joint Entity Resolution, while plugging in two different MAP inference methods: the current method of choice for MAP inference in Markov Logic, MaxWalkSAT, and Integer Line…
Sapienza Università di Roma（罗马大学）；Università degli Studi di Bergamo（贝加莫大学）
We study privacy-preserving query answering in Description Logics (DLs). Specifically, we consider the approach of controlled query evaluation (CQE) based on the notion of instance indistinguishability. We derive data complexity results for query answering over DL-Lite$_{\mathcal{R}}$ ontologies, through a comparison with an alternative, existing confidentiality-preserving approach to CQE. Finally, we identify a semantically well-founded notion of approximated query answering for CQE, and prove that, for DL-Lite$_{\mathcal{R}}$ ontologies, this form of CQE is tractable with respect to data com…
