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

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.

Distantly Supervised Relation Extraction (DSRE) aims to automatically identify semantic relationships within large text corpora by aligning with external knowledge bases. Despite the success of current methods in automating data annotation, they introduce two main challenges: label noise and data long-tail distribution. Label noise results in inaccurate annotations, which can undermine the quality of relation extraction. The long-tail problem, on the other hand, leads to an imbalanced model that struggles to extract less frequent, long-tail relations. In this paper, we introduce a novel relation extraction framework based on multi-level hierarchical attention. This approach utilizes Graph Attention Networks (GATs) to model the hierarchical structure of the relations, capturing the semantic dependencies between relation types and generating relation embeddings that reflect the overall hierarchical framework. To improve the classification process, we incorporate a multi-level classification structure guided by hierarchical attention, which enhances the accuracy of both head and tail relation extraction. A local probability constraint is introduced to ensure coherence across the classification levels, fostering knowledge transfer from frequent to less frequent relations. Experimental evaluations on the New York Times (NYT) dataset demonstrate that our method outperforms existing baselines, particularly in the context of long-tail relation extraction, offering a comprehensive solution to the challenges of DSRE.

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.

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

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

Most existing relation extraction approaches exclusively target binary relations, and n-ary relation extraction is relatively unexplored. Current state-of-the-art n-ary relation extraction method is based on a supervised learning approach and, therefore, may suffer from the lack of sufficient relation labels. In this paper, we propose a novel approach to cross-sentence n-ary relation extraction based on universal schemas. To alleviate the sparsity problem and to leverage inherent decomposability of n-ary relations, we propose to learn relation representations of lower-arity facts that result from decomposing higher-arity facts. The proposed method computes a score of a new n-ary fact by aggregating scores of its decomposed lower-arity facts. We conduct experiments with datasets for ternary relation extraction and empirically show that our method improves the n-ary relation extraction performance compared to previous methods.

In this research, we manually create high-quality datasets in the digital humanities domain for the evaluation of language models, specifically word embedding models. The first step comprises the creation of unigram and n-gram datasets for two fantasy novel book series for two task types each, analogy and doesn’t-match. This is followed by the training of models on the two book series with various popular word embedding model types such as word2vec, GloVe, fastText, or LexVec. Finally, we evaluate the suitability of word embedding models for such specific relation extraction tasks in a situation of comparably small corpus sizes. In the evaluations, we also investigate and analyze particular aspects such as the impact of corpus term frequencies and task difficulty on accuracy. The datasets, and the underlying system and word embedding models are available on github and can be easily extended with new datasets and tasks, be used to reproduce the presented results, or be transferred to other domains.KeywordsWord embeddingsDigital humanities datasetDataset evaluation

The syntactic information of a dependency tree is an essential feature in relation extraction studies. Traditional dependency-based relation extraction methods can be categorized into hard pruning methods, which aim to remove unnecessary information, and soft pruning methods, which aim to utilize all lexical information. However, hard pruning has the potential to overlook important lexical information, while soft pruning can weaken the syntactic information between entities. As a result, recent studies in relation extraction have been shifting from dependency-based methods to pre-trained language model (LM) based methods. Nonetheless, LM-based methods increasingly demand larger language models and additional data. This trend leads to higher resource consumption, longer training times, and increased computational costs, yet often results in only marginal performance improvements. To address this problem, we propose a relation extraction model based on an entity-centric dependency tree: a dependency tree that is reconstructed by considering entities as root nodes. Using the entity-centric dependency tree, the proposed method can capture the syntactic information of an input sentence without losing lexical information. Additionally, we propose a novel model that utilizes entity-centric dependency trees in conjunction with language models, enabling efficient relation extraction without the need for additional data or larger models. In experiments with representative sentence-level relation extraction datasets such as TACRED, Re-TACRED, and SemEval 2010 Task 8, the proposed method achieves F1-scores of 74.9%, 91.2%, and 90.5%, respectively, which are state-of-the-art performances.

Addressing the policy challenges and opportunities of “Big data”

Distant supervision is an efficient approach for various tasks, such as relation extraction. Most of the recent literature on distantly supervised relation extraction generates labeled data by heuristically aligning knowledge bases with text corpora and then trains supervised relation classification models based on statistical learning. However, extracting long tail relations from the automatically labeled data is still a challenging problem even in big data. Inspired by explanation-based learning (EBL), this paper proposes an EBL-based approach to tackle this problem. The proposed approach can learn relation extraction rules effectively using unlabeled data. Experiments on the New York Times corpus demonstrate that our approach outperforms the baseline approach especially on long tail data.

Distant supervision (DS) has been widely used for relation extraction (RE), which automatically generates large‐scale labeled data. However, there is a wrong labeling problem, which affects the performance of RE. Besides, the existing method suffers from the lack of useful semantic features for some positive training instances. To address the above problems, we propose a novel RE model with sentence selection and interaction representation for distantly supervised RE. First, we propose a pattern method based on the relation trigger words as a sentence selector to filter out noisy sentences to alleviate the wrong labeling problem. After clean instances are obtained, we propose the interaction representation using the word‐level attention mechanism‐based entity pairs to dynamically increase the weights of the words related to entity pairs, which can provide more useful semantic information for relation prediction. The proposed model outperforms the strongest baseline by 2.61 in F1‐score on a widely used dataset, which proves that our model performs significantly better than the state‐of‐the‐art RE systems.

The goal of relation extraction is to obtain relational facts from plain text, which can benefit a variety of natural language processing tasks. To address the challenge of automatically labeling large-scale training data, a distant supervision strategy is introduced to relation extraction by heuristically aligning entity pairs in plain text with the knowledge base. Unfortunately, the method is vulnerable to the noisy label problem due to the incompletion of the exploited knowledge base. Existing works focus on the specific algorithms, but few works summarize the commonalities between different methods and the influencing factors of these denoising mechanisms. In this paper, we propose three main factors that impact the label denoising of distantly supervised relation extraction, including labeling assumption, prior knowledge and confidence level. In order to analyze how these factors influence the denoising effectiveness, we build a unified neural framework with word, sentence and label denoising modules for relation extraction. Then we conduct experiments to evaluate and compare these factors according to ten neural schemes. In addition, we discuss the typical cases of these factors and find that influential word-level prior knowledge and partial confidence for distantly supervised labels can significantly affect the denoising performance. These implicational findings can provide researchers with more insight of distantly supervised relation extraction.