Scientific concepts are often defined inconsistently across papers, making it difficult to compare findings, reuse terminology, and build reliable downstream resources. We present SciDef, a resource suite for scientific definition extraction. The suite contains DefExtra, a benchmark of 268 human-validated author-stated definitions from 75 academic papers; DefSim, 60 human-labeled definition-pair similarity judgments; and an open LLM-based pipeline for PDF preprocessing, chunking, definition extraction, prompt optimization, and evaluation. We validate the resources by benchmarking 16 language models across prompting strategies and chunking schemes. The strongest set-level configuration achieves a score of 0.397, while the highest-coverage configuration matches at least one prediction to 86.4% of gold definitions but over-generates candidate definitions. We further show that an NLI-based matching metric agrees strongly with human DefSim judgments. These results position SciDef as a reusable benchmark and tooling layer for definition-centric literature analysis, while highlighting relevance-aware filtering as the key bottleneck for fully automatic definition extraction. Code & datasets are available at https://github.com/Media-Bias-Group/SciDef.
From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction
University of Science and Technology of China（中国科学技术大学）；State Key Laboratory of Cognitive Intelligence（认知智能全国重点实验室）；CCCC Second Highway Consultants Co., Ltd.（中交第二公路勘察设计研究院有限公司）
Adapt Semantics, Not Structure: Few-Instance Schema Calibration for Scientific PDF Extraction
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；University of Science and Technology of China（中国科学技术大学）；State Key Laboratory of Cognitive Intelligence（认知智能全国重点实验室）；CCCC Second Highway Consultants Co., Ltd.（中交第二公路勘察设计研究院有限公司）
SciDaSynth: Interactive Structured Data Extraction from Scientific Literature with Large Language Model
Bosch Research North America（博世北美研究院）；Weill Cornell Medicine（威尔康奈尔医学院）；Cornell University（康奈尔大学）；Hong Kong University of Science and Technology（香港科技大学）
MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning
Shenzhen Key Laboratory for High Performance Data Mining（深圳高性能数据挖掘重点实验室）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology（深圳先进技术大学人工智能研究院）
University of Washington（华盛顿大学）；Northwestern University（西北大学）；Allen Institute for AI（艾伦人工智能研究所）
Accurately extracting structured content from PDFs is a critical first step for NLP over scientific papers. Recent work has improved extraction accuracy by incorporating elementary layout information, e.g., each token's 2D position on the page, into language model pretraining. We introduce new methods that explicitly model VIsual LAyout (VILA) groups, i.e., text lines or text blocks, to further improve performance. In our I-VILA approach, we show that simply inserting special tokens denoting layout group boundaries into model inputs can lead to a 1.9% Macro F1 improvement in token classificati…
This paper describes our submission for the SemEval 2018 Task 7 shared task on semantic relation extraction and classification in scientific papers. We extend the end-to-end relation extraction model of (Miwa and Bansal) with enhancements such as a character-level encoding attention mechanism on selecting pretrained concept candidate embeddings. Our official submission ranked the second in relation classification task (Subtask 1.1 and Subtask 2 Senerio 2), and the first in the relation extraction task (Subtask 2 Scenario 1).
Indian Institute of Technology, Gandhinagar（甘地纳加尔印度理工学院）
Automatic scientific keyphrase extraction is a challenging problem facilitating several downstream scholarly tasks like search, recommendation, and ranking. In this paper, we introduce SEAL, a scholarly tool for automatic keyphrase extraction and classification. The keyphrase extraction module comprises two-stage neural architecture composed of Bidirectional Long Short-Term Memory cells augmented with Conditional Random Fields. The classification module comprises of a Random Forest classifier. We extensively experiment to showcase the robustness of the system. We evaluate multiple state-of-the…
Allen Institute for AI（艾伦人工智能研究所）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
Identification of new concepts in scientific literature can help power faceted search, scientific trend analysis, knowledge-base construction, and more, but current methods are lacking. Manual identification cannot keep up with the torrent of new publications, while the precision of existing automatic techniques is too low for many applications. We present an unsupervised concept extraction method for scientific literature that achieves much higher precision than previous work. Our approach relies on a simple but novel intuition: each scientific concept is likely to be introduced or popularize…
Scientific literature is one of the most significant resources for sharing knowledge. Researchers turn to scientific literature as a first step in designing an experiment. Given the extensive and growing volume of literature, the common approach of reading and manually extracting knowledge is too time consuming, creating a bottleneck in the research cycle. This challenge spans nearly every scientific domain. For the materials science, experimental data distributed across millions of publications are extremely helpful for predicting materials properties and the design of novel materials. Howeve…
In this work, we present a weakly supervised sentence extraction technique for identifying important sentences in scientific papers that are worthy of inclusion in the abstract. We propose a new attention based deep learning architecture that jointly learns to identify important content, as well as the cue phrases that are indicative of summary worthy sentences. We propose a new context embedding technique for determining the focus of a given paper using topic models and use it jointly with an LSTM based sequence encoder to learn attention weights across the sentence words. We use a collection…
Indian Institute of Technology, Gandhinagar（印度理工学院甘地讷格尔分校）
Information Extraction (IE) from the tables present in scientific articles is challenging due to complicated tabular representations and complex embedded text. This paper presents TabLeX, a large-scale benchmark dataset comprising table images generated from scientific articles. TabLeX consists of two subsets, one for table structure extraction and the other for table content extraction. Each table image is accompanied by its corresponding LATEX source code. To facilitate the development of robust table IE tools, TabLeX contains images in different aspect ratios and in a variety of fonts. Our …
Kansas State University（堪萨斯州立大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
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 …
This paper studies the automated categorization and extraction of scientific concepts from titles of scientific articles, in order to gain a deeper understanding of their key contributions and facilitate the construction of a generic academic knowledgebase. Towards this goal, we propose an unsupervised, domain-independent, and scalable two-phase algorithm to type and extract key concept mentions into aspects of interest (e.g., Techniques, Applications, etc.). In the first phase of our algorithm we propose PhraseType, a probabilistic generative model which exploits textual features and limited …
Nowadays, metadata information is often given by the authors themselves upon submission. However, a significant part of already existing research papers have missing or incomplete metadata information. German scientific papers come in a large variety of layouts which makes the extraction of metadata a non-trivial task that requires a precise way to classify the metadata extracted from the documents. In this paper, we propose a multimodal deep learning approach for metadata extraction from scientific papers in the German language. We consider multiple types of input data by combining natural la…
Indian Institute of Technology Gandhinagar（甘地纳格尔印度理工学院）
Scientific documents contain tables that list important information in a concise fashion. Structure and content extraction from tables embedded within PDF research documents is a very challenging task due to the existence of visual features like spanning cells and content features like mathematical symbols and equations. Most existing table structure identification methods tend to ignore these academic writing features. In this paper, we adapt the transformer-based language modeling paradigm for scientific table structure and content extraction. Specifically, the proposed model converts a tabu…
As a research community grows, more and more papers are published each year. As a result there is increasing demand for improved methods for finding relevant papers, automatically understanding the key ideas and recommending potential methods for a target problem. Despite advances in search engines, it is still hard to identify new technologies according to a researcher's need. Due to the large variety of domains and extremely limited annotated resources, there has been relatively little work on leveraging natural language processing in scientific recommendation. In this proposal, we aim at ma…
Metadata of scientific articles such as title, abstract, keywords or index terms, body text, conclusion, reference and others play a decisive role in collecting, managing and storing academic data in scientific databases, academic journals and digital libraries. An accurate extraction of these kinds of data from scientific papers is crucial to organize and retrieve important scientific information for researchers as well as librarians. Research social network systems and academic digital library systems provide academic data extracting, organizing and retrieving services. Mostly these types of…
We examine the novel task of domain-independent scientific concept extraction from abstracts of scholarly articles and present two contributions. First, we suggest a set of generic scientific concepts that have been identified in a systematic annotation process. This set of concepts is utilised to annotate a corpus of scientific abstracts from 10 domains of Science, Technology and Medicine at the phrasal level in a joint effort with domain experts. The resulting dataset is used in a set of benchmark experiments to (a) provide baseline performance for this task, (b) examine the transferability …
Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO
HKUST Hong Kong SAR, China（香港科技大学）；SEU Jiangsu, China（江苏大学）；HKUST(GZ) Guangzhou, China（香港科技大学（广州））；Zhipu AI Beijing, China（智谱AI）；HKUST(GZ), HKUST Guangzhou, China（香港科技大学（广州）、香港科技大学）
MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables
Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi（印度德里理工学院亚迪人工智能学院）；Department of Civil Engineering, Indian Institute of Technology Delhi（印度德里理工学院土木工程系）；Department of Computer Science and Engineering, Indian Institute of Technology Delhi（印度德里理工学院计算机科学与工程系）
Within the past few decades we have witnessed digital revolution, which moved scholarly communication to electronic media and also resulted in a substantial increase in its volume. Nowadays keeping track with the latest scientific achievements poses a major challenge for the researchers. Scientific information overload is a severe problem that slows down scholarly communication and knowledge propagation across the academia. Modern research infrastructures facilitate studying scientific literature by providing intelligent search tools, proposing similar and related documents, visualizing citati…
Human-artificial intelligence teaming for scientific information extraction from data-driven additive manufacturing research using large language models
McGill University（麦吉尔大学）；University of Montreal（蒙特利尔大学）；Mila
TIB Leibniz Information Centre for Science and Technology（莱布尼茨科学与技术信息中心（TIB））
We introduce the STEM (Science, Technology, Engineering, and Medicine) Dataset for Scientific Entity Extraction, Classification, and Resolution, version 1.0 (STEM-ECR v1.0). The STEM-ECR v1.0 dataset has been developed to provide a benchmark for the evaluation of scientific entity extraction, classification, and resolution tasks in a domain-independent fashion. It comprises abstracts in 10 STEM disciplines that were found to be the most prolific ones on a major publishing platform. We describe the creation of such a multidisciplinary corpus and highlight the obtained findings in terms of the f…
This paper describes SciClops, a method to help combat online scientific misinformation. Although automated fact-checking methods have gained significant attention recently, they require pre-existing ground-truth evidence, which, in the scientific context, is sparse and scattered across a constantly-evolving scientific literature. Existing methods do not exploit this literature, which can effectively contextualize and combat science-related fallacies. Furthermore, these methods rarely require human intervention, which is essential for the convoluted and critical domain of scientific misinforma…
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
Acronyms and long-forms are commonly found in research documents, more so in documents from scientific and legal domains. Many acronyms used in such documents are domain-specific and are very rarely found in normal text corpora. Owing to this, transformer-based NLP models often detect OOV (Out of Vocabulary) for acronym tokens, especially for non-English languages, and their performance suffers while linking acronyms to their long forms during extraction. Moreover, pretrained transformer models like BERT are not specialized to handle scientific and legal documents. With these points being the …
In order to disseminate the exponential extent of knowledge being produced in the form of scientific publications, it would be best to design mechanisms that connect it with already existing rich repository of concepts -- the Wikipedia. Not only does it make scientific reading simple and easy (by connecting the involved concepts used in the scientific articles to their Wikipedia explanations) but also improves the overall quality of the article. In this paper, we present a novel metapath based method, WikiM, to efficiently wikify scientific abstracts -- a topic that has been rarely investigate…
Literature analysis facilitates researchers better understanding the development of science and technology. The conventional literature analysis focuses on the topics, authors, abstracts, keywords, references, etc., and rarely pays attention to the content of papers. In the field of machine learning, the involved methods (M) and datasets (D) are key information in papers. The extraction and mining of M and D are useful for discipline analysis and algorithm recommendation. In this paper, we propose a novel entity recognition model, called MDER, and constructe datasets from the papers of the PAK…
Jožef Stefan Institute（约瑟夫·斯蒂芬研究所）；Jožef Stefan International Postgraduate School（约瑟夫·斯蒂芬国际研究生院）；University of Maribor（马里博尔大学）
The COVID-19 pandemic triggered a wave of novel scientific literature that is impossible to inspect and study in a reasonable time frame manually. Current machine learning methods offer to project such body of literature into the vector space, where similar documents are located close to each other, offering an insightful exploration of scientific papers and other knowledge sources associated with COVID-19. However, to start searching, such texts need to be appropriately annotated, which is seldom the case due to the lack of human resources. In our system, the current body of COVID-19-related …
Scientific press briefings are a valuable information source. They consist of alternating expert speeches, questions from the audience and their answers. Therefore, they can contribute to scientific and fact-based media coverage. Even though press briefings are highly informative, extracting statements relevant to individual journalistic tasks is challenging and time-consuming. To support this task, an automated statement extraction system is proposed. Claims are used as the main feature to identify statements in press briefing transcripts. The statement extraction task is formulated as a four…
Reproducibility is an important task in scientific research. It is crucial for researchers to compare newly developed systems with the state-of-the-art to assess whether they made a breakthrough. However previous works may not be immediately reproducible, for example due to the lack of source code. In this work we reproduce DEXTER, a system to automatically extract Gene-Disease Associations (GDAs) from biomedical abstracts. The goal is to provide a benchmark for future works regarding Relation Extraction (RE), enabling researchers to test and compare their results.
