SCIR: A Self-Correcting Iterative Refinement Framework for Enhanced Information Extraction Based on Schema

Information extraction (IE) systems are costly to build because they require development texts, parsing tools, and specialized dictionaries for each application domain and each natural language that needs to be processed. We present a novel method for rapidly creating IE systems for new languages by exploiting existing IE systems via cross-language projection. Given an IE system for a source language (e.g., English), we can transfer its annotations to corresponding texts in a target language (e.g., French) and learn information extraction rules for the new language automatically. In this paper, we explore several ways of realizing both the transfer and learning processes using off-the-shelf machine translation systems, induced word alignment, attribute projection, and transformation-based learning. We present a variety of experiments that show how an English IE system for a plane crash domain can be leveraged to automatically create a French IE system for the same domain.

Information Extraction (IE) systems assist analysts to assimilate information from electronic documents. This paper focuses on IE tasks designed to support information discovery applications. Since information discovery implies examining large volumes of heterogeneous documents for situations that cannot be anticipated a priori, they require IE systems to have breadth as well as depth. This implies the need for a domain-independent IE system that can easily be customized for specific domains: end users must be given tools to customize the system on their own. It also implies the need for defining new intermediate level IE tasks that are richer than the subject-verb-object (SVO) triples produced by shallow systems, yet not as complex as the domain-specific scenarios defined by the Message Understanding Conference (MUC). This paper describes InfoXtract, a robust, scalable, intermediate-level IE engine that can be ported to various domains. It describes new IE tasks such as synthesis of entity profiles, and extraction of concept-based general events which represent realistic near-term goals focused on deriving useful, actionable information. Entity profiles consolidate information about a person/organization/location etc. within a document and across documents into a single template; this takes into account aliases and anaphoric references as well as key relationships and events pertaining to that entity. Concept-based events attempt to normalize information such as time expressions (e.g., yesterday) as well as ambiguous location references (e.g., Buffalo). These new tasks facilitate the correlation of output from an IE engine with structured data to enable text mining. InfoXtract's hybrid architecture comprised of grammatical processing and machine learning is described in detail. Benchmarking results for the core engine and applications utilizing the engine are presented.

A real-world information extraction (IE) system for semi-structured document images often involves a long pipeline of multiple modules, whose complexity dramatically increases its development and maintenance cost. One can instead consider an end- to-end model that directly maps the input to the target output and simplify the entire process. However, such generation approach is known to lead to unstable performance if not designed carefully. Here we present our recent effort on transitioning from our existing pipeline-based IE system to an end-to-end system focusing on practical challenges that are associated with replacing and deploying the system in real, large-scale production. By carefully formulating document IE as a sequence generation task, we show that a single end-to-end IE system can be built and still achieve competent performance.

DWIE: An entity-centric dataset for multi-task document-level information extraction

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.

BackgroundBioinformatics tools for automatic processing of biomedical literature are invaluable for both the design and interpretation of large-scale experiments. Many information extraction (IE) systems that incorporate natural language processing (NLP) techniques have thus been developed for use in the biomedical field. A key IE task in this field is the extraction of biomedical relations, such as protein-protein and gene-disease interactions. However, most biomedical relation extraction systems usually ignore adverbial and prepositional phrases and words identifying location, manner, timing, and condition, which are essential for describing biomedical relations. Semantic role labeling (SRL) is a natural language processing technique that identifies the semantic roles of these words or phrases in sentences and expresses them as predicate-argument structures. We construct a biomedical SRL system called BIOSMILE that uses a maximum entropy (ME) machine-learning model to extract biomedical relations. BIOSMILE is trained on BioProp, our semi-automatic, annotated biomedical proposition bank. Currently, we are focusing on 30 biomedical verbs that are frequently used or considered important for describing molecular events.ResultsTo evaluate the performance of BIOSMILE, we conducted two experiments to (1) compare the performance of SRL systems trained on newswire and biomedical corpora; and (2) examine the effects of using biomedical-specific features. The experimental results show that using BioProp improves the F-score of the SRL system by 21.45% over an SRL system that uses a newswire corpus. It is noteworthy that adding automatically generated template features improves the overall F-score by a further 0.52%. Specifically, ArgM-LOC, ArgM-MNR, and Arg2 achieve statistically significant performance improvements of 3.33%, 2.27%, and 1.44%, respectively.ConclusionWe demonstrate the necessity of using a biomedical proposition bank for training SRL systems in the biomedical domain. Besides the different characteristics of biomedical and newswire sentences, factors such as cross-domain framesets and verb usage variations also influence the performance of SRL systems. For argument classification, we find that NE (named entity) features indicating if the target node matches with NEs are not effective, since NEs may match with a node of the parsing tree that does not have semantic role labels in the training set. We therefore incorporate templates composed of specific words, NE types, and POS tags into the SRL system. As a result, the classification accuracy for adjunct arguments, which is especially important for biomedical SRL, is improved significantly.

This paper investigates the impact of knowledge extraction methods on the effectiveness of RAG (Retrieval-Augmented Generation) systems that utilize knowledge graphs. It highlights that the quality of the knowledge graph, which is formed using various knowledge extraction methods, is crucial for overcoming limitations of large language models (LLMs), such as “hallucinations”. The paper analyzes the architectures of LightRAG and GraphRAG, emphasizing that the selection of an optimal knowledge extraction strategy depends on specific tasks and the subject area. LLMs have advanced significantly, but they have limitations, including generating factually incorrect information (“hallucinations”) and possessing “outdated knowledge”. RAG systems were proposed to address these issues by combining LLMs with external knowledge bases. This approach reduces hallucinations, ensures factual accuracy, solves the problem of outdated knowledge, and increases transparency. Knowledge graphs are powerful tools for structuring information, consisting of entities (nodes) and relations (edges). They enhance RAG systems by enabling more precise and contextually grounded retrieval compared to keyword-based searches. The quality of a knowledge graph depends on the knowledge extraction methods used, which include named entity recognition (NER), relation extraction (RE), entity linking (EL), and event extraction. Different methods, such as rule-based, classical machine learning, and deep learning approaches, have varying trade-offs in terms of accuracy, completeness, and scalability. Entity linking and knowledge graph completion are also crucial for accuracy and richness. LightRAG and GraphRAG are two main graph-based RAG systems. LightRAG uses the knowledge graph as a quick reference, requiring high precision in knowledge extraction to avoid noise degradation. GraphRAG uses the knowledge graph as a domain model, where completeness of extracted knowledge is more critical, though systematic errors are still harmful. Both systems rely on LLMs for knowledge extraction, which makes them dependent on the LLM’s quality and the size of document fragments processed. The theoretical analysis confirms that the effectiveness of RAG systems is critically dependent on knowledge extraction methods. The quality, completeness, and accuracy of the knowledge graph directly influence the RAG system’s ability to provide relevant, accurate, and truthful answers. Different RAG system architectures like LightRAG and GraphRAG have distinct requirements for knowledge graph characteristics, prioritizing either accuracy or completeness in knowledge extraction.

IntroductionRecent artificial intelligence (AI) advances can generate human-like responses to a wide range of queries, making them a useful tool for healthcare applications. Therefore, the potential use of large language models (LLMs) in controlled environments regarding efficacy, reproducibility, and operability will be of paramount interest.ObjectiveWe investigated if and how GPT 3.5 and GPT 4 models can be directly used as a part of a GxP validated system and compared the performance of externally hosted GPT 3.5 and GPT 4 against LLMs, which can be hosted internally. We explored zero-shot LLM performance for named entity recognition (NER) and relation extraction tasks, investigated which LLM has the best zero-shot performance to be used potentially for generating training data proposals, evaluated the LLM performance of seven entities for medical NER in zero-shot experiments, selected one model for further performance improvement (few-shot and fine-tuning: Zephyr-7b-beta), and investigated how smaller open-source LLMs perform in contrast to GPT models and to a small fine-tuned T5 Base.MethodsWe performed reproducibility experiments to evaluate if LLMs can be used in controlled environments and utilized guided generation to use the same prompt across multiple models. Few-shot learning and quantized low rank adapter (QLoRA) fine-tuning were applied to further improve LLM performance.Results and ConclusionWe demonstrated that zero-shot GPT 4 performance is comparable with a fine-tuned T5, and Zephyr performed better than zero-shot GPT 3.5, but the recognition of product combinations such as product event combination was significantly better by using a fine-tuned T5. Although Open AI launched recently GPT versions to improve the generation of consistent output, both GPT variants failed to demonstrate reproducible results. The lack of reproducibility together with limitations of external hosted systems to keep validated systems in a state of control may affect the use of closed and proprietary models in regulated environments. However, due to the good NER performance, we recommend using GPT for creating annotation proposals for training data as a basis for fine-tuning.

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.

BackgroundNatural Language Processing (NLP) applications have developed over the past years in various fields including its application to clinical free text for named entity recognition and relation extraction. However, there has been rapid developments the last few years that there's currently no overview of it. Moreover, it is unclear how these models and tools have been translated into clinical practice. We aim to synthesize and review these developments. MethodsWe reviewed literature from 2010 to date, searching PubMed, Scopus, the Association of Computational Linguistics (ACL), and Association of Computer Machinery (ACM) libraries for studies of NLP systems performing general-purpose (i.e., not disease- or treatment-specific) information extraction and relation extraction tasks in unstructured clinical text (e.g., discharge summaries). ResultsWe included in the review 94 studies with 30 studies published in the last three years. Machine learning methods were used in 68 studies, rule-based in 5 studies, and both in 22 studies. 63 studies focused on Named Entity Recognition, 13 on Relation Extraction and 18 performed both. The most frequently extracted entities were “problem”, “test” and “treatment”. 72 studies used public datasets and 22 studies used proprietary datasets alone. Only 14 studies defined clearly a clinical or information task to be addressed by the system and just three studies reported its use outside the experimental setting. Only 7 studies shared a pre-trained model and only 8 an available software tool. DiscussionMachine learning-based methods have dominated the NLP field on information extraction tasks. More recently, Transformer-based language models are taking the lead and showing the strongest performance. However, these developments are mostly based on a few datasets and generic annotations, with very few real-world use cases. This may raise questions about the generalizability of findings, translation into practice and highlights the need for robust clinical evaluation.

One promising application of natural language processing (NLP) research is in the area of information extraction (IE). In this paper, we present work flow of our IE system for the extraction of semantically rich information from the unstructured or semi-structured Chinese web pages. Knowledge engineering approach and automatic training approach are used to extract pattern and built knowledge repository. General IE system needs to label the unlabeled training Web pages. A novel methodology that does not need to label text is developed, including hierarchy filtration pattern matching based on syntax in best distance method and maximum forward boundary recognition using organization suffix repository and part of speech tagging method. As for applications of IE, a new application system based on IE is built. It is object-level vertical search system and object here is Chinese people, so IE is concerned with extracting people's related attributes from a collection of web pages about Chinese people. The results are displayed as hierarchy directory tree according to people's attributes. The system makes user find people quickly and easily.

The development of an information extraction (IE) system for Thai documents raises a number of issues which are not important for IE in English and other European languages. We describe the characteristics of written Thai and the problem statements, and our approach to the Thai IE system. The structure of written Thai is highly ambiguous, which requires more sophisticated techniques than are necessary to perform comparable IE tasks in most European languages, and large amounts of domain knowledge to cope with these ambiguities. The basic characteristic of this system is to provide different natural language components to assess the surface structure of the documents. These components include word segmentation, specific lexical structure terms identification and part-of-speech tagger. Further analysis is to perform a shallow parsing based on the relevant regions that contain the specific trigger terms or patterns specified in the extraction templates. Finally, the information of interest is extracted from the grammar trees in corresponding to predefined concept definitions and returns the users with a list of answers responding to each concept.

Entity and relation extraction (ERE) is a major task in information extraction and knowledge mapping. Existing methods usually consider two tasks, named entity recognition (NER) and relation extraction (RE), separately using a pipeline approach, which loses a lot of interaction information between tasks and contextual information of text sequences. In order to settle this problem, this paper proposes an end-to-end entity relation joint extraction method based on the head-entity attention mechanism and fusing contextual semantic features. The overall structure of this method adopts BERT-CRF to decode the header entity and its type, and then uses the header entity information as the Query in the attention mechanism, while fusing entity type label embedding and entity relative position to achieve feature enhancement, which enhances the information interaction between entity model and relational model. In the experiments of the commonly used English dataset NYT and Chinese dataset DuIE, this method has achieved high extraction accuracy and F1 score. It is shown that the model is applicable in both English and Chinese contexts.

A novel prompting method for few-shot NER via LLMs

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