Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas

A new method to extract n-Ary relation instances from scientific documents

Relation Extraction (RE) is at the core of many Natural Language Understanding tasks, including knowledge-base population and Question Answering.However, any Natural Language Processing system is exposed to biases, and the analysis of these has not received much attention in RE.We propose a new method for inspecting bias in the RE pipeline, which is completely transparent in terms of interpretability.Specifically, in this work we analyze biases related to gender and place of birth.Our methodology includes (i) obtaining semantic triplets (subject, object, semantic relation) involving 'person' entities from RE resources, (ii) collecting meta-information ('gender' and 'place of birth') using Entity Linking technologies, and then (iii) analyze the distribution of triplets across different groups (e.g., men versus women).We investigate bias at two levels: In the training data of three commonly used RE datasets (SRED FM , CrossRE, NYT), and in the predictions of a state-of-the-art RE approach (ReLiK).To enable cross-dataset analysis, we introduce a taxonomy of relation types mapping the label sets of different RE datasets to a unified label space.Our findings reveal that bias is a compounded issue affecting underrepresented groups within data and predictions for RE.

We introduce and discuss a connectedness induced by n-ary relations (\(n>1\) an integer) on their underlying sets. In particular, we focus on certain n-ary relations with the induced connectedness allowing for a definition of digital Jordan curves. For every integer \(n>1\), we introduce one such n-ary relation on the digital plane \({\mathbb {Z}}^2\) and prove a digital analogue of the Jordan curve theorem for the induced connectedness. It follows that these n-ary relations may be used as convenient structures on the digital plane for the study of geometric properties of digital images. For \(n=2\), such a structure coincides with the (specialization order of the) Khalimsky topology and, for \(n>2\), it allows for a variety of Jordan curves richer than that provided by the Khalimsky topology.

In the expanding landscape of biomedical literature, numerous latent associations outlined in scholarly papers await discovery and integration into biomedical databases. Biomedical Natural Language Processing (NLP) research focuses on automating knowledge extraction and mining from this literature, particularly emphasizing the essential task of Relation Extraction (RE). However, existing models have limitations, mainly in their applicability to partial datasets for RE tasks. Moreover, conventional models often treat RE as a binary classification challenge, which proves suboptimal given the diverse relationships, including intricate ones like similarity and hierarchy, present in the RE dataset. These limitations are exacerbated by the models’ inability to capture word-level positional nuances and sentence-level language features. In response to these challenges, we present a novel RE model called BicapBert. This model integrates neural networks and capsule networks, enhancing them with hybrid knowledge graph embeddings to extract relevant features. BicapBert utilizes PubMedBERT and capsule networks to extract word-level positional and sentence-level language features. It further captures knowledge features from a biomedical knowledge graph, integrating them with the aforementioned linguistic features. The amalgamated information is then input into a multi-layer perceptron, culminating in results derived through a softmax classifier. Experimental evaluations on three extensive RE task datasets showcase the state-of-the-art performance of our proposed model. Additionally, we validate the model’s efficacy on three randomly selected biomedical datasets for various tasks, further affirming its superiority.

Matrix factorization of knowledge bases in universal schema has facilitated accurate distantlysupervised relation extraction.This factorization encodes dependencies between textual patterns and structured relations using lowdimensional vectors defined for each entity pair; although these factors are effective at combining evidence for an entity pair, they are inaccurate on rare pairs, or for relations that depend crucially on the entity types.On the other hand, tensor factorization is able to overcome these shortcomings when applied to link prediction by maintaining entity-wise factors.However these models have been unsuitable for universal schema.In this paper we first present an illustration on synthetic data that explains the unsuitability of tensor factorization to relation extraction with universal schemas.Since the benefits of tensor and matrix factorization are complementary, we then investigate two hybrid methods that combine the benefits of the two paradigms.We show that the combination can be fruitful: we handle ambiguously phrased relations, achieve gains in accuracy on real-world relations, and demonstrate that entity embeddings encode entity types.

Diverse classifiers with label dependencies for long-tail relation extraction in big data

Document-level relation extraction (RE), which requires integrating and reasoning information to identify multiple possible relations among entities. However, previous research typically performed reasoning on heterogeneous graphs and set a global threshold for multiple relations classification, regardless of interaction reasoning information among multiple relations and positive–negative samples imbalance on databases. This paper proposes a novel framework for Document-level RE with two techniques, dual attention fusion and dynamic asymmetric loss. Concretely, to obtain more interdependency feature learning, we construct entity pairs and contextual matrixes using multi-head axial attention and co-attention mechanism to learn the interaction among entity pairs deeply. To alleviate the hard-thresholds influence from positive–negative imbalance samples, we dynamically adjust weights to optimize the probabilities of different labels. We evaluate our model on two benchmark document-level RE datasets, DocRED and CDR. Experimental results show that our DASL (Dual Attention fusion and dynamic aSymmetric Loss) obtains superior performance on two public datasets, we further provide extensive experiments to analyze how dual attention fusion and dynamic asymmetric loss guide the model for better extracting multi-label relations among entities.

Document-level relation extraction (RE) has attracted considerable attention, because a large number of relational facts are expressed in multiple sentences. Recently, encoder-aggregator based models have become promising for document-level RE. However, these models have two shortcomings: (i) they cannot obtain contextualized representations of a mention by low computational cost, when the mention is involved in different entity pairs; (ii) they ignore the different weights for the mention pairs of a target entity pair. To tackle the above two problems, in this paper, we propose a novel encoder-attender-aggregator model, which introduces two attenders between the encoder and aggregator. Specifically, a mutual attender is first employed on the selected head and tail mentions to efficiently produce contextualized mention representations. Then, an integration attender is utilized to weight the mention pairs of a target entity pair. Extensive experiments on two document-level RE datasets show that the proposed model performs better than the state-of-the-art baselines. Our codes are publicly available at "https://github.com/nefujiangping/EncAttAgg".

Document-level relation extraction (RE) poses new challenges compared to its sentence-level counterpart. One document commonly contains multiple entity pairs, and one entity pair occurs multiple times in the document associated with multiple possible relations. In this paper, we propose two novel techniques, adaptive thresholding and localized context pooling, to solve the multi-label and multi-entity problems. The adaptive thresholding replaces the global threshold for multi-label classification in the prior work with a learnable entities-dependent threshold. The localized context pooling directly transfers attention from pre-trained language models to locate relevant context that is useful to decide the relation. We experiment on three document-level RE benchmark datasets: DocRED, a recently released large-scale RE dataset, and two datasets CDRand GDA in the biomedical domain. Our ATLOP (Adaptive Thresholding and Localized cOntext Pooling) model achieves an F1 score of 63.4, and also significantly outperforms existing models on both CDR and GDA. We have released our code at https://github.com/wzhouad/ATLOP.

Two evaluations on Ontology-style relation annotations

A vast amount of usable electronic data is in the form of unstructured text. The relation extraction task aims to identify useful information in text (e.g. PersonW works for OrganisationX, GeneY encodes ProteinZ) and recode it in a format such as a relational database or RDF triplestore that can be more effectively used for querying and automated reasoning. A number of resources have been developed for training and evaluating automatic systems for relation extraction in different domains. However, comparative evaluation is impeded by the fact that these corpora use different markup formats and notions of what constitutes a relation. We describe the preparation of corpora for comparative evaluation of relation extraction across domains based on the publicly available ACE 2004, ACE 2005 and BioInfer data sets. We present a common document type using token standoff and including detailed linguistic markup, while maintaining all information in the original annotation. The subsequent reannotation process normalises the two data sets so that they comply with a notion of relation that is intuitive, simple and informed by the semantic web. For the ACE data, we describe an automatic process that automatically converts many relations involving nested, nominal entity mentions to relations involving non-nested, named or pronominal entity mentions. For example, the first entity is mapped from ‘one’ to ‘Amidu Berry’ in the membership relation described in ‘Amidu Berry, one half of PBS’. Moreover, we describe a comparably reannotated version of the BioInfer corpus that flattens nested relations, maps part-whole to part-part relations and maps n-ary to binary relations. Finally, we summarise experiments that compare approaches to generic relation extraction, a knowledge discovery task that uses minimally supervised techniques to achieve maximally portable extractors. These experiments illustrate the utility of the corpora.1

Current research on knowledge graph construction is focused chiefly on general-purpose fields, whereas constructing knowledge graphs in vertically segmented professional fields faces numerous difficulties. To solve the problems of complex relation types of domain entities, the lack of a large amount of annotated corpus, and the difficulty of extraction, this study proposed a method for constructing domain-annotated datasets based on publicly available texts on the web, which integrates remote supervision and semi-supervision. For the relational triad extraction of a given core entity (an entity lexicon defined semi-automatically by experts), an inflated gate attention network structure for increasing the perceptual field of the model is proposed. In addition, a relational extraction model, Ro-DGANet, was designed based on this structure, incorporating the idea of a probability graph. The Ro-DGANet model was experimentally evaluated on the publicly available Chinese datasets LIC2019 and CHIP2020 and compared with the mainstream relation extraction models, achieving the best results with F1 values of 82.99% and 66.39%, respectively. Finally, the Ro-DGANet model was applied to the relation extraction task of equipment components in industrial scenarios and to the relation extraction task of core knowledge points of programming languages. The analysis results show that the proposed method is applicable to open relation extraction among core entities in different domains with reliable performance and portability.

Boundary assembling method for joint entity and relation extraction

Knowledge Graph is a semantic network that reveals the relationship between entities, which construction is to describe various entities, concepts and their relationships in the real world. Since knowledge graph can effectively reveal the relationship between the different knowledge items, it has been widely utilized in the intelligent education. In particular, relation extraction is the critical part of knowledge graph and plays a very important role in the construction of knowledge graph. According to the different magnitude of data labeling, entity relationship extraction tasks of deep learning can be divided into two categories: supervised and distant supervised. Supervised learning approaches can extract effective entity relationships. However, these approaches rely on labeled data heavily resulting in the time-consuming and laborconsuming. The distant supervision approach is widely concerned by researchers because it can generate the entity relation extraction automatically. However, the development and application of the distant supervised approach has been seriously hindered due to the noises, lack of information and disequilibrium in the relation extraction tasks. Inspired by the above analysis, the paper proposes a novel curriculum points relationship extraction model based on the distant supervision. In particular, firstly the research of the distant supervised relationship extraction model based on the sentence bag attention mechanism to extract the relationship of curriculum points. Secondly, the research of knowledge graph construction based on the knowledge ontology. Thirdly, the development of curriculum semantic retrieval platform based on Web. Compared with the existing advanced models, the AUC of this system is increased by 14.2%; At the same time, taking "big data processing" course in computer field as an example, the relationship extraction result with F1 value of 88.1% is realized. The experimental results show that the proposed model provides an effective solution for the development and application of knowledge graph in the field of intelligent education.

Organized relational knowledge in the form of “knowledge graphs” is important for many applications. However, the ability to populate knowledge bases with facts automatically extracted from documents has improved frustratingly slowly. This paper simultaneously addresses two issues that have held back prior work. We first propose an effective new model, which combines an LSTM sequence model with a form of entity position-aware attention that is better suited to relation extraction. Then we build TACRED, a large (119,474 examples) supervised relation extraction dataset obtained via crowdsourcing and targeted towards TAC KBP relations. The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance. When the model trained on this new dataset replaces the previous relation extraction component of the best TAC KBP 2015 slot filling system, its F1 score increases markedly from 22.2% to 26.7%.