Feature-Level Attention Based Sentence Encoding for Neural Relation Extraction

Distant supervised relation extraction has been widely used to find novel relational facts from text. However, distant supervision inevitably accompanies with the wrong labelling problem, and these noisy data will substantially hurt the performance of relation extraction. To alleviate this issue, we propose a sentence-level attention-based model for relation extraction. In this model, we employ convolutional neural networks to embed the semantics of sentences. Afterwards, we build sentence-level attention over multiple instances, which is expected to dynamically reduce the weights of those noisy instances. Experimental results on real-world datasets show that, our model can make full use of all informative sentences and effectively reduce the influence of wrong labelled instances. Our model achieves significant and consistent improvements on relation extraction as compared with baselines.

This paper aims to study how to use remote monitoring for relation extraction, so as to identify the relationship between entities and provide logical facts. In recent years, document-level relation extraction (DocRE) has attracted much attention. Distant supervision (DS) has been playing an important role in sentence-level relation extraction (RE). Compared with traditional relation extraction methods, DS requires less data. However, the performance of document-level DS is limited by the noise in the long distant text. Previous DS works represent intra-sentential and inter-sentential representations in the same way, and neglect the difference between noise in them. This paper proposes an architecture called RDRS, which represents inter-sentence and intra-sentence relations in different ways, and uses a sentence-level relation model to represent document-level relations. The RDRS contains various modules, in which pairs of entities are separated according to the distribution of their mentions. In addition, this paper also improves the performance of inter-sentence representation by associating intra-sentence representation with inter-sentence representation. The experiments are carried out on Document-level Relation Extraction Dataset (DocRED). Experiments on DocRED show that the method has a significant improvement over the baseline. This model is better than previous models that represent inter-sentence and intra-sentence relations in the same way.

Recently, deep neural network based methods have been widely used in relation extraction, which is an important task for knowledge base population, question answering and other natural language applications, to learn proper features from entities pairs and other sentence parts to extract relations from text. As a kind of important information, the value of position is always been underestimated, which causes a low weight of position information in various models and finally hurts the performance of relation extraction task. To alleviate this issue, we propose a position-enhanced embedding model based on convolutional neural network. In this model, we split the sentence representation into three parts based on the entity pairs in the sentence, and use three independent convolutional networks to learn features. Furthermore, we concatenate the output from different branches and employ a softmax layer to compute the probability for each relation. Experimental results on wildly used datasets achieve considerable improvements on relation extraction as compared with baselines, which shows that our proposed model can make full use of position information.

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.

Web texts typically undergo the open-ended growth of new relations. Traditional relation extraction methods lack automatic annotation and perform poorly on new relation extraction tasks. We propose an open-domain relation extraction system (ORES) based on distant supervision and few-shot learning to solve this problem. More specifically, we utilize tBERT to design instance selector 1, implementing automatic labeling in the data mining component. Meanwhile, we design example selector 2 based on K-BERT in the new relation extraction component. The real-time data management component outputs new relational data. Experiments show that ORES can filter out higher quality and diverse instances for better new relation learning. It achieves significant improvement compared to Neural Snowball with fewer seed sentences.

There is a huge amount of available information stored in unstructured plain text. Relation Extraction (RE) is an important task in the process of converting unstructured resources into machine-readable format. RE is usually considered as a classification problem where a set of features are extracted from the training sentences and thereafter passed to a classifier to predict the relation labels. Existing methods either manually design these features or automatically build them by means of deep neural networks. However, in many cases these features are general and do not accurately reflect the properties of the input sentences. In addition, these features are only built for the input sentences with no regard to the features of the target relations. In this paper, we follow a different approach to perform the RE task. We propose an extended autoencoder model to automatically build vector representations for sentences and relations from their distinctive features. The built vectors are high abstract continuous vector representations (embeddings) where task related features are preserved and noisy irrelevant features are eliminated. Similarity measures are then used to find the sentence-relation semantic similarities using their representations in order to label sentences with the most similar relations. The conducted experiments show that the proposed model is effective in labeling new sentences with their correct semantic relations.

Supervised learning is a classic paradigm of relation extraction (RE). However, a well-performing model can still confidently make arbitrarily wrong predictions when exposed to samples of unseen relations. In this work, we propose a relation extraction method with rejection option to improve robustness to unseen relations. To enable the classifier to reject unseen relations, we introduce contrastive learning techniques and carefully design a set of class-preserving transformations to improve the discriminability between known and unseen relations. Based on the learned representation, inputs of unseen relations are assigned a low confidence score and rejected. Off-the-shelf open relation extraction (OpenRE) methods can be adopted to discover the potential relations in these rejected inputs. In addition, we find that the rejection can be further improved via readily available distantly supervised data. Experiments on two public datasets prove the effectiveness of our method capturing discriminative representations for unseen relation rejection.KeywordsRelation extractionRejection optionDeep learning

To optimize in-context learning in biomedical natural language processing by improving example selection. We introduce a novel multi-mode retrieval-augmented generation (MMRAG) framework, which integrates 4 retrieval strategies: (1) Random Mode, selecting examples arbitrarily; (2) Top Mode, retrieving the most relevant examples based on similarity; (3) Diversity Mode, ensuring variation in selected examples; and (4) Class Mode, selecting category-representative examples. This study evaluates MMRAG on 3 core biomedical NLP tasks: Named Entity Recognition (NER), Relation Extraction (RE), and Text Classification (TC). The datasets used include BC2GM for gene and protein mention recognition (NER), DDI for drug-drug interaction extraction (RE), GIT for general biomedical information extraction (RE), and HealthAdvice for health-related text classification (TC). The framework is tested with 2 large language models (Llama-2-7B and Llama-3-8B) and 3 retrievers (Contriever, MedCPT, and BGE-Large) to assess performance across different retrieval strategies. The results from the Random Mode indicate that providing more examples in the prompt improves the model's generation performance. Meanwhile, Top Mode and Diversity Mode significantly outperform Random Mode on the RE (DDI) task, achieving an F1 score of 0.9669-a 26.4% improvement. Among the 3 retrievers tested, Contriever outperformed the other 2 in a greater number of experiments. Additionally, Llama 2 and Llama 3 demonstrated varying capabilities across different tasks, with Llama 3 showing a clear advantage in handling NER tasks. MMRAG effectively enhances biomedical in-context learning by refining example selection, mitigating data scarcity issues, and demonstrating superior adaptability for NLP-driven healthcare applications.

Extracting information from unstructured and semi-structured geoscience literature is a crucial step in conducting geological research. The traditional machine learning extraction paradigm requires a substantial amount of high-quality manually annotated data for model training, which is time-consuming, labor-intensive, and not easily transferable to new fields. Recently, large language models (LLMs) (e.g., ChatGPT, GPT-4, and LLaMA), have shown great performance in various natural language processing (NLP) tasks, such as question answering, machine translation, and text generation. A substantial body of work has demonstrated that LLMs possess strong in-context learning (ICL) and even zero-shot learning capabilities to solve downstream tasks without specifically designed supervised fine-tuning. In this paper, we propose utilizing LLMs for geoscience literature information extraction. Specifically, we design a hierarchical PDF parsing pipeline and an automated knowledge extraction process, which can significantly reduce the need for manual data annotation, assisting geoscientists in literature data mining. For the hierarchical PDF parsing pipeline, firstly, a document layout detection model fine-tuned on geoscience literature is employed for layout detection, obtaining layout detection information for the document. Secondly, based on the document layout information, an optical character content parsing model is used for content parsing, obtaining the text structure and plain text corresponding to the content. Finally, the text structure and plain text are combined and reconstructed to ultimately obtain the parsed structured data. For the automated knowledge extraction process, firstly, the parsed long text is segmented into paragraphs to adapt to the input length limit of LLMs. Subsequently, a few-shot prompting method is employed for structured knowledge extraction, encompassing two tasks: attribute value extraction and triplet extraction. In attribute value extraction, prompts are generated automatically by the LLMs based on the subdomain and attribute names, facilitating the location and extraction of values related to subdomain attribute names in the text. For triplet extraction, the LLMs employ a procedural approach to entity extraction, entity type extraction, and relation extraction, following the knowledge graph structure pattern. Finally, the extracted structured knowledge is stored in the form of knowledge graphs, facilitating further analysis and integration of various types of knowledge from the literature. Our proposed approach turns out to be simple, flexible, and highly effective in geoscience literature information extraction. Demonstrations of information extraction in subdomains such as radiolarian fossils and fluvial facies have yielded satisfactory results. The extraction efficiency has significantly improved, and feedback from domain experts indicates a relatively high level of accuracy in the extraction process. The extracted results can be used to construct a foundational knowledge graph for geoscience literature, supporting the comprehensive construction and efficient application of a geoscience knowledge graph.

Distant supervision for relation extraction is a task of recognizing semantic relations between entities in a large amount of plain text weakly supervised by external knowledge bases, which can benefit many NLP applications, such as knowledge graph completion and question answering. While it significantly alleviates the expensive cost for data labeling, it severely suffers from noisy labels. In this paper, we propose a Multi-head Self-attention Network (MSNet)-based label denoising method for relation extraction. More specifically, we encode the words, entities and their positions information into contextual embeddings via a multi-head self-attention mechanism, then extract the discriminative sentence features with max pooling operation. MSNet can capture the inherent structure of a sentence and model the relatedness between two words without regard to their distance. Moreover, we adopt a novel label confidence learning method to correct the noisy labels. A latent label is predicted step by step during training as the ground-truth according to a curriculum function of label confidence. This label denoising mechanism gradually incorporates the obtained latent label of easy relation patterns into later latent label prediction of hard patterns, which makes latent label consistent learning more reliable. To verify the effectiveness of our proposed method, in addition to the widely used PCNN-based architecture, we also perform the experiment on BiLSTM model as a comparison. The results demonstrate that our approach can outperform the state-of-the-art systems on the popular evaluation dataset.

A region-based hypergraph network for joint entity-relation extraction

Relation extraction is an important task with many applications in natural language processing, such as structured knowledge extraction, knowledge graph construction, and automatic question answering system construction. However, relatively little past work has focused on the construction of the corpus and extraction of Uyghur-named entity relations, resulting in a very limited availability of relation extraction research and a deficiency of annotated relation data. This issue is addressed in the present article by proposing a hybrid Uyghur-named entity relation extraction method that combines a conditional random field model for making suggestions regarding annotation based on extracted relations with a set of rules applied by human annotators to rapidly increase the size of the Uyghur corpus. We integrate our relation extraction method into an existing annotation tool, and, with the help of human correction, we implement Uyghur relation extraction and expand the existing corpus. The effectiveness of our proposed approach is demonstrated based on experimental results by using an existing Uyghur corpus, and our method achieves a maximum weighted average between precision and recall of 61.34%. The method we proposed achieves state-of-the-art results on entity and relation extraction tasks in Uyghur.

End-to-end relation extraction aims to identify named entities and extract relations between them. Most recent work models these two subtasks jointly, either by casting them in one structured prediction framework, or performing multi-task learning through shared representations. In this work, we present a simple pipelined approach for entity and relation extraction, and establish the new state-of-the-art on standard benchmarks (ACE04, ACE05 and SciERC), obtaining a 1.7%-2.8% absolute improvement in relation F1 over previous joint models with the same pre-trained encoders. Our approach essentially builds on two independent encoders and merely uses the entity model to construct the input for the relation model. Through a series of careful examinations, we validate the importance of learning distinct contextual representations for entities and relations, fusing entity information early in the relation model, and incorporating global context. Finally, we also present an efficient approximation to our approach which requires only one pass of both entity and relation encoders at inference time, achieving an 8-16× speedup with a slight reduction in accuracy.

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.

Unsupervised word embeddings have become a popular approach of word representation in NLP tasks. However there are limitations to the semantics represented by unsupervised embeddings, and inadequate fine-tuning of embeddings can lead to suboptimal performance. We propose a novel learning technique called Delta Embedding Learning, which can be applied to general NLP tasks to improve performance by optimized tuning of the word embeddings. A structured regularization is applied to the embeddings to ensure they are tuned in an incremental way. As a result, the tuned word embeddings become better word representations by absorbing semantic information from supervision without “forgetting.” We apply the method to various NLP tasks and see a consistent improvement in performance. Evaluation also confirms the tuned word embeddings have better semantic properties.