Pipelines for Procedural Information Extraction from Scientific Literature: Towards Recipes using Machine Learning and Data Science
This paper describes a machine learning and data science pipeline for structured information extraction from documents, implemented as a suite of open-source tools and extensions to existing tools. It centers around a methodology for extracting procedural information in the form of recipes, stepwise procedures for creating an artifact (in this case synthesizing a nanomaterial), from published scientific literature. From our overall goal of producing recipes from free text, we derive the technical objectives of a system consisting of pipeline stages: document acquisition and filtering, payload extraction, recipe step extraction as a relationship extraction task, recipe assembly, and presentation through an information retrieval interface with question answering (QA) functionality. This system meets computational information and knowledge management (CIKM) requirements of metadata-driven payload extraction, named entity extraction, and relationship extraction from text. Functional contributions described in this paper include semi-supervised machine learning methods for PDF filtering and payload extraction tasks, followed by structured extraction and data transformation tasks beginning with section extraction, recipe steps as information tuples, and finally assembled recipes. Measurable objective criteria for extraction quality include precision and recall of recipe steps, ordering constraints, and QA accuracy, precision, and recall. Results, key novel contributions, and significant open problems derived from this work center around the attribution of these holistic quality measures to specific machine learning and inference stages of the pipeline, each with their performance measures. The desired recipes contain identified preconditions, material inputs, and operations, and constitute the overall output generated by our computational information and knowledge management (CIKM) system.
Code (1)
Tasks
BIG-bench Machine LearningEntity Extraction using GANInformation RetrievalManagementQuestion AnsweringRetrievalSimilar Papers 제목 키워드 기반
Exploring LLMs for Scientific Information Extraction Using The SciEx Framework
Large language models (LLMs) are increasingly touted as powerful tools for automating scientific information extraction. However, existing methods and tools often struggle with the realities of scientific literature: lon…
Information ExtractionSciClaims: An End-to-End Generative System for Biomedical Claim Analysis
Validating key claims in scientific literature, particularly in biomedical research, is essential for ensuring accuracy and advancing knowledge. This process is critical in sectors like the pharmaceutical industry, where…
Claim VerificationInformation RetrievalRetrievalCollage: Decomposable Rapid Prototyping for Information Extraction on Scientific PDFs
Recent years in NLP have seen the continued development of domain-specific information extraction tools for scientific documents, alongside the release of increasingly multimodal pretrained transformer models. While the …
The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures
Materials science literature contains millions of materials synthesis procedures described in unstructured natural language text. Large-scale analysis of these synthesis procedures would facilitate deeper scientific unde…
Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature
Automated knowledge extraction from scientific literature can potentially accelerate materials discovery. We have investigated an approach for extracting synthesis protocols for reticular materials from scientific litera…
HallucinationIn-Context LearningPrompt Engineering