PyTorchKR Papers

최신 논문

총 2,675편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.14443

Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension

Conventional Machine Reading Comprehension (MRC) has been well-addressed by pattern matching, but the ability of commonsense reasoning remains a gap between humans and machines. Previous methods tackle this problem by enriching word representations via pre-trained Knowledge Graph Embeddings (KGE). However, they make limited use of a large number of connections between nodes in Knowledge Graphs (KG), which could be pivotal cues to build the commonsense reasoning chains. In this paper, we propose a Plug-and-play module to IncorporatE Connection information for commonsEnse Reasoning (PIECER). Beyond enriching word representations with knowledge embeddings, PIECER constructs a joint query-passage graph to explicitly guide commonsense reasoning by the knowledge-oriented connections between words. Further, PIECER has high generalizability since it can be plugged into suitable positions in any MRC model. Experimental results on ReCoRD, a large-scale public MRC dataset requiring commonsense reasoning, show that PIECER introduces stable performance improvements for four representative base MRC models, especially in low-resource settings.

arXiv:2103.13009공식 코드 · Papers with Code

UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark

Commonsense AI has long been seen as a near impossible goal -- until recently. Now, research interest has sharply increased with an influx of new benchmarks and models. We propose two new ways to evaluate commonsense models, emphasizing their generality on new tasks and building on diverse, recently introduced benchmarks. First, we propose a new multitask benchmark, RAINBOW, to promote research on commonsense models that generalize well over multiple tasks and datasets. Second, we propose a novel evaluation, the cost equivalent curve, that sheds new insight on how the choice of source datasets, pretrained language models, and transfer learning methods impacts performance and data efficiency. We perform extensive experiments -- over 200 experiments encompassing 4800 models -- and report multiple valuable and sometimes surprising findings, e.g., that transfer almost always leads to better or equivalent performance if following a particular recipe, that QA-based commonsense datasets transfer well with each other, while commonsense knowledge graphs do not, and that perhaps counter-intuitively, larger models benefit more from transfer than smaller ones. Last but not least, we introduce a new universal commonsense reasoning model, UNICORN, that establishes new state-of-the-art performance across 8 popular commonsense benchmarks, aNLI (87.3%), CosmosQA (91.8%), HellaSWAG (93.9%), PIQA (90.1%), SocialIQa (83.2%), WinoGrande (86.6%), CycIC (94.0%) and CommonsenseQA (79.3%).

arXiv:2103.11951공식 코드 · Papers with Code

Demographic Aware Probabilistic Medical Knowledge Graph Embeddings of Electronic Medical Records

Medical knowledge graphs (KGs) constructed from Electronic Medical Records (EMR) contain abundant information about patients and medical entities. The utilization of KG embedding models on these data has proven to be efficient for different medical tasks. However, existing models do not properly incorporate patient demographics and most of them ignore the probabilistic features of the medical KG. In this paper, we propose DARLING (Demographic Aware pRobabiListic medIcal kNowledge embeddinG), a demographic-aware medical KG embedding framework that explicitly incorporates demographics in the medical entities space by associating patient demographics with a corresponding hyperplane. Our framework leverages the probabilistic features within the medical entities for learning their representations through demographic guidance. We evaluate DARLING through link prediction for treatments and medicines, on a medical KG constructed from EMR data, and illustrate its superior performance compared to existing KG embedding models.

arXiv:2103.10379

ChronoR: Rotation Based Temporal Knowledge Graph Embedding

Despite the importance and abundance of temporal knowledge graphs, most of the current research has been focused on reasoning on static graphs. In this paper, we study the challenging problem of inference over temporal knowledge graphs. In particular, the task of temporal link prediction. In general, this is a difficult task due to data non-stationarity, data heterogeneity, and its complex temporal dependencies. We propose Chronological Rotation embedding (ChronoR), a novel model for learning representations for entities, relations, and time. Learning dense representations is frequently used as an efficient and versatile method to perform reasoning on knowledge graphs. The proposed model learns a k-dimensional rotation transformation parametrized by relation and time, such that after each fact's head entity is transformed using the rotation, it falls near its corresponding tail entity. By using high dimensional rotation as its transformation operator, ChronoR captures rich interaction between the temporal and multi-relational characteristics of a Temporal Knowledge Graph. Experimentally, we show that ChronoR is able to outperform many of the state-of-the-art methods on the benchmark datasets for temporal knowledge graph link prediction.

arXiv:2103.10367공식 코드 · Papers with Code

Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs

Biomedical knowledge graphs permit an integrative computational approach to reasoning about biological systems. The nature of biological data leads to a graph structure that differs from those typically encountered in benchmarking datasets. To understand the implications this may have on the performance of reasoning algorithms, we conduct an empirical study based on the real-world task of drug repurposing. We formulate this task as a link prediction problem where both compounds and diseases correspond to entities in a knowledge graph. To overcome apparent weaknesses of existing algorithms, we propose a new method, PoLo, that combines policy-guided walks based on reinforcement learning with logical rules. These rules are integrated into the algorithm by using a novel reward function. We apply our method to Hetionet, which integrates biomedical information from 29 prominent bioinformatics databases. Our experiments show that our approach outperforms several state-of-the-art methods for link prediction while providing interpretability.

arXiv:2103.09430공식 코드 · Papers with Code

OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs

Enabling effective and efficient machine learning (ML) over large-scale graph data (e.g., graphs with billions of edges) can have a great impact on both industrial and scientific applications. However, existing efforts to advance large-scale graph ML have been largely limited by the lack of a suitable public benchmark. Here we present OGB Large-Scale Challenge (OGB-LSC), a collection of three real-world datasets for facilitating the advancements in large-scale graph ML. The OGB-LSC datasets are orders of magnitude larger than existing ones, covering three core graph learning tasks -- link prediction, graph regression, and node classification. Furthermore, we provide dedicated baseline experiments, scaling up expressive graph ML models to the massive datasets. We show that expressive models significantly outperform simple scalable baselines, indicating an opportunity for dedicated efforts to further improve graph ML at scale. Moreover, OGB-LSC datasets were deployed at ACM KDD Cup 2021 and attracted more than 500 team registrations globally, during which significant performance improvements were made by a variety of innovative techniques. We summarize the common techniques used by the winning solutions and highlight the current best practices in large-scale graph ML. Finally, we describe how we have updated the datasets after the KDD Cup to further facilitate research advances. The OGB-LSC datasets, baseline code, and all the information about the KDD Cup are available at https://ogb.stanford.edu/docs/lsc/ .

arXiv:2103.09311

Using a Personal Health Library-Enabled mHealth Recommender System for Self-Management of Diabetes Among Underserved Populations: Use Case for Knowledge Graphs and Linked Data

Personal health libraries (PHLs) provide a single point of secure access to patients digital health data and enable the integration of knowledge stored in their digital health profiles with other sources of global knowledge. PHLs can help empower caregivers and health care providers to make informed decisions about patients health by understanding medical events in the context of their lives. This paper reports the implementation of a mobile health digital intervention that incorporates both digital health data stored in patients PHLs and other sources of contextual knowledge to deliver tailored recommendations for improving self-care behaviors in diabetic adults. We conducted a thematic assessment of patient functional and nonfunctional requirements that are missing from current EHRs based on evidence from the literature. We used the results to identify the technologies needed to address those requirements. We describe the technological infrastructures used to construct, manage, and integrate the types of knowledge stored in the PHL. We leverage the Social Linked Data (Solid) platform to design a fully decentralized and privacy-aware platform that supports interoperability and care integration. We provided an initial prototype design of a PHL and drafted a use case scenario that involves four actors to demonstrate how the proposed prototype can be used to address user requirements, including the construction and management of the PHL and its utilization for developing a mobile app that queries the knowledge stored and integrated into the PHL in a private and fully decentralized manner to provide better recommendations. The proposed PHL helps patients and their caregivers take a central role in making decisions regarding their health and equips their health care providers with informatics tools that support the collection and interpretation of the collected knowledge.

논문 ID: document/9262038

Entity Alignment for Knowledge Graphs with Multi-order Convolutional Networks

Knowledge graphs (KGs) have become popular structures for unifying real-world entities by modelling the relationships between them and their attributes. Entity alignment -- the task of identifying corresponding entities across different KGs -- has attracted a great deal of attention in both academia and industry. However, existing alignment techniques often require large amounts of labelled data, are unable to encode multi-modal data simultaneously, and enforce only few consistency constraints. In this paper, we propose an end-to-end, unsupervised entity alignment framework for cross-lingual KGs that fuses different types of information in order to fully exploit the richness of KG data. The model captures the relation-based correlation between entities by using a multi-order graph convolutional neural (GCN) model that is designed to satisfy the consistency constraints, while incorporating the attribute-based correlation via a translation machine. We adopt a late-fusion mechanism to combine all the information together, which allows these approaches to complement each other and thus enhances the final alignment result, and makes the model more robust to consistency violations. Empirical results show that our model is more accurate and orders of magnitude faster than existing baselines. We also demonstrate its sensitivity to hyper-parameters, effort saving in terms of labelling, and the robustness against adversarial conditions.

arXiv:2103.08893

KGSynNet: A Novel Entity Synonyms Discovery Framework with Knowledge Graph

Entity synonyms discovery is crucial for entity-leveraging applications. However, existing studies suffer from several critical issues: (1) the input mentions may be out-of-vocabulary (OOV) and may come from a different semantic space of the entities; (2) the connection between mentions and entities may be hidden and cannot be established by surface matching; and (3) some entities rarely appear due to the long-tail effect. To tackle these challenges, we facilitate knowledge graphs and propose a novel entity synonyms discovery framework, named \emph{KGSynNet}. Specifically, we pre-train subword embeddings for mentions and entities using a large-scale domain-specific corpus while learning the knowledge embeddings of entities via a joint TransC-TransE model. More importantly, to obtain a comprehensive representation of entities, we employ a specifically designed \emph{fusion gate} to adaptively absorb the entities' knowledge information into their semantic features. We conduct extensive experiments to demonstrate the effectiveness of our \emph{KGSynNet} in leveraging the knowledge graph. The experimental results show that the \emph{KGSynNet} improves the state-of-the-art methods by 14.7\% in terms of hits@3 in the offline evaluation and outperforms the BERT model by 8.3\% in the positive feedback rate of an online A/B test on the entity linking module of a question answering system.

arXiv:2103.08819

A Novel Paper Recommendation Method Empowered by Knowledge Graph: for Research Beginners

Searching for papers from different academic databases is the most commonly used method by research beginners to obtain cross-domain technical solutions. However, it is usually inefficient and sometimes even useless because traditional search methods neither consider knowledge heterogeneity in different domains nor build the bottom layer of search, including but not limited to the characteristic description text of target solutions and solutions to be excluded. To alleviate this problem, a novel paper recommendation method is proposed herein by introducing "master-slave" domain knowledge graphs, which not only help users express their requirements more accurately but also helps the recommendation system better express knowledge. Specifically, it is not restricted by the cold start problem and is a challenge-oriented method. To identify the rationality and usefulness of the proposed method, we selected two cross-domains and three different academic databases for verification. The experimental results demonstrate the feasibility of obtaining new technical papers in the cross-domain scenario by research beginners using the proposed method. Further, a new research paradigm for research beginners in the early stages is proposed herein.

arXiv:2103.08588

iWarded: A System for Benchmarking Datalog+/- Reasoning (technical report)

Recent years have seen increasing popularity of logic-based reasoning systems, with research and industrial interest as well as many flourishing applications in the area of Knowledge Graphs. Despite that, one can observe a substantial lack of specific tools able to generate nontrivial reasoning settings and benchmark scenarios. As a consequence, evaluating, analysing and comparing reasoning systems is a complex task, especially when they embody sophisticated optimizations and execution techniques that leverage the theoretical underpinnings of the adopted logic fragment. In this paper, we aim at filling this gap by introducing iWarded, a system that can generate very large, complex, realistic reasoning settings to be used for the benchmarking of logic-based reasoning systems adopting Datalog+/-, a family of extensions of Datalog that has seen a resurgence in the last few years. In particular, iWarded generates reasoning settings for Warded Datalog+/-, a language with a very good tradeoff between computational complexity and expressive power. In the paper, we present the iWarded system and a set of novel theoretical results adopted to generate effective scenarios. As Datalog-based languages are of general interest and see increasing adoption, we believe that iWarded is a step forward in the empirical evaluation of current and future systems.

arXiv:2103.07771공식 코드 · Papers with Code

ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation

This paper presents ParaQA, a question answering (QA) dataset with multiple paraphrased responses for single-turn conversation over knowledge graphs (KG). The dataset was created using a semi-automated framework for generating diverse paraphrasing of the answers using techniques such as back-translation. The existing datasets for conversational question answering over KGs (single-turn/multi-turn) focus on question paraphrasing and provide only up to one answer verbalization. However, ParaQA contains 5000 question-answer pairs with a minimum of two and a maximum of eight unique paraphrased responses for each question. We complement the dataset with baseline models and illustrate the advantage of having multiple paraphrased answers through commonly used metrics such as BLEU and METEOR. The ParaQA dataset is publicly available on a persistent URI for broader usage and adaptation in the research community.

arXiv:2103.07766공식 코드 · Papers with Code

Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphs

Neural semantic parsing approaches have been widely used for Question Answering (QA) systems over knowledge graphs. Such methods provide the flexibility to handle QA datasets with complex queries and a large number of entities. In this work, we propose a novel framework named CARTON, which performs multi-task semantic parsing for handling the problem of conversational question answering over a large-scale knowledge graph. Our framework consists of a stack of pointer networks as an extension of a context transformer model for parsing the input question and the dialog history. The framework generates a sequence of actions that can be executed on the knowledge graph. We evaluate CARTON on a standard dataset for complex sequential question answering on which CARTON outperforms all baselines. Specifically, we observe performance improvements in F1-score on eight out of ten question types compared to the previous state of the art. For logical reasoning questions, an improvement of 11 absolute points is reached.

arXiv:2103.08115공식 코드 · Papers with Code

Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts

Many large-scale knowledge bases simultaneously represent two views of knowledge graphs (KGs): an ontology view for abstract and commonsense concepts, and an instance view for specific entities that are instantiated from ontological concepts. Existing KG embedding models, however, merely focus on representing one of the two views alone. In this paper, we propose a novel two-view KG embedding model, JOIE, with the goal to produce better knowledge embedding and enable new applications that rely on multi-view knowledge. JOIE employs both cross-view and intra-view modeling that learn on multiple facets of the knowledge base. The cross-view association model is learned to bridge the embeddings of ontological concepts and their corresponding instance-view entities. The intra-view models are trained to capture the structured knowledge of instance and ontology views in separate embedding spaces, with a hierarchy-aware encoding technique enabled for ontologies with hierarchies. We explore multiple representation techniques for the two model components and investigate with nine variants of JOIE. Our model is trained on large-scale knowledge bases that consist of massive instances and their corresponding ontological concepts connected via a (small) set of cross-view links. Experimental results on public datasets show that the best variant of JOIE significantly outperforms previous models on instance-view triple prediction task as well as ontology population on ontologyview KG. In addition, our model successfully extends the use of KG embeddings to entity typing with promising performance.

arXiv:2103.07102공식 코드 · Papers with Code

Inductive Relation Prediction by BERT

Relation prediction in knowledge graphs is dominated by embedding based methods which mainly focus on the transductive setting. Unfortunately, they are not able to handle inductive learning where unseen entities and relations are present and cannot take advantage of prior knowledge. Furthermore, their inference process is not easily explainable. In this work, we propose an all-in-one solution, called BERTRL (BERT-based Relational Learning), which leverages pre-trained language model and fine-tunes it by taking relation instances and their possible reasoning paths as training samples. BERTRL outperforms the SOTAs in 15 out of 18 cases in both inductive and transductive settings. Meanwhile, it demonstrates strong generalization capability in few-shot learning and is explainable.

arXiv:2103.03642공식 코드 · Papers with Code

Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs

Inductive link prediction -- where entities during training and inference stages can be different -- has been shown to be promising for completing continuously evolving knowledge graphs. Existing models of inductive reasoning mainly focus on predicting missing links by learning logical rules. However, many existing approaches do not take into account semantic correlations between relations, which are commonly seen in real-world knowledge graphs. To address this challenge, we propose a novel inductive reasoning approach, namely TACT, which can effectively exploit Topology-Aware CorrelaTions between relations in an entity-independent manner. TACT is inspired by the observation that the semantic correlation between two relations is highly correlated to their topological structure in knowledge graphs. Specifically, we categorize all relation pairs into several topological patterns, and then propose a Relational Correlation Network (RCN) to learn the importance of the different patterns for inductive link prediction. Experiments demonstrate that TACT can effectively model semantic correlations between relations, and significantly outperforms existing state-of-the-art methods on benchmark datasets for the inductive link prediction task.

arXiv:2103.01986

Technical Report on Data Integration and Preparation

AI application developers typically begin with a dataset of interest and a vision of the end analytic or insight they wish to gain from the data at hand. Although these are two very important components of an AI workflow, one often spends the first few weeks (sometimes months) in the phase we refer to as data conditioning. This step typically includes tasks such as figuring out how to prepare data for analytics, dealing with inconsistencies in the dataset, and determining which algorithm (or set of algorithms) will be best suited for the application. Larger, faster, and messier datasets such as those from Internet of Things sensors, medical devices or autonomous vehicles only amplify these issues. These challenges, often referred to as the three Vs (volume, velocity, variety) of Big Data, require low-level tools for data management, preparation and integration. In most applications, data can come from structured and/or unstructured sources and often includes inconsistencies, formatting differences, and a lack of ground-truth labels. In this report, we highlight a number of tools that can be used to simplify data integration and preparation steps. Specifically, we focus on data integration tools and techniques, a deep dive into an exemplar data integration tool, and a deep-dive in the evolving field of knowledge graphs. Finally, we provide readers with a list of practical steps and considerations that they can use to simplify the data integration challenge. The goal of this report is to provide readers with a view of state-of-the-art as well as practical tips that can be used by data creators that make data integration more seamless.

arXiv:2103.01576

FinMatcher at FinSim-2: Hypernym Detection in the Financial Services Domain using Knowledge Graphs

This paper presents the FinMatcher system and its results for the FinSim 2021 shared task which is co-located with the Workshop on Financial Technology on the Web (FinWeb) in conjunction with The Web Conference. The FinSim-2 shared task consists of a set of concept labels from the financial services domain. The goal is to find the most relevant top-level concept from a given set of concepts. The FinMatcher system exploits three publicly available knowledge graphs, namely WordNet, Wikidata, and WebIsALOD. The graphs are used to generate explicit features as well as latent features which are fed into a neural classifier to predict the closest hypernym.

arXiv:2103.00728

BERT-based knowledge extraction method of unstructured domain text

With the development and business adoption of knowledge graph, there is an increasing demand for extracting entities and relations of knowledge graphs from unstructured domain documents. This makes the automatic knowledge extraction for domain text quite meaningful. This paper proposes a knowledge extraction method based on BERT, which is used to extract knowledge points from unstructured specific domain texts (such as insurance clauses in the insurance industry) automatically to save manpower of knowledge graph construction. Different from the commonly used methods which are based on rules, templates or entity extraction models, this paper converts the domain knowledge points into question and answer pairs and uses the text around the answer in documents as the context. The method adopts a BERT-based model similar to BERT's SQuAD reading comprehension task. The model is fine-tuned. And it is used to directly extract knowledge points from more insurance clauses. According to the test results, the model performance is good.

arXiv:2103.00418공식 코드 · Papers with Code

Logic Embeddings for Complex Query Answering

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, a new approach to embedding complex queries that uses Skolemisation to eliminate existential variables for efficient querying. It supports negation, but improves on density approaches: 1) integrates well-studied t-norm logic and directly evaluates satisfiability, 2) simplifies modeling with truth values, and 3) models uncertainty with truth bounds. Logic Embeddings are competitively fast and accurate in query answering over large, incomplete knowledge graphs, outperform on negation queries, and in particular, provide improved modeling of answer uncertainty as evidenced by a superior correlation between answer set size and embedding entropy.