With the large volume of unstructured data that increases constantly on the web, the motivation of representing the knowledge in this data in the machine-understandable form is increased. Ontology is one of the major cornerstones of representing the information in a more meaningful way on the semantic Web. The current ontology repositories are quite limited either for their scope or for currentness. In addition, the current ontology extraction systems have many shortcomings and drawbacks, such as using a small dataset, depending on a large amount predefined patterns to extract semantic relations, and extracting a very few types of relations. The aim of this paper is to introduce a proposal of automatically extracting semantic concepts and relations from scientific publications. This paper suggests new types of semantic relations and points out of using deep learning (DL) models for semantic relation extraction.
University College London（伦敦大学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and materials. Although this was a new task, we had a total of 26 submissions across 3 evaluation scenarios. We expect the task and the findings reported in this paper to be relevant for researchers working on understanding scientific content, as well as the broader knowledge base population and information extraction communities.
Grounding Fallacies Misrepresenting Scientific Publications in Evidence
Ubiquitous Knowledge Processing Lab (UKP Lab)（通用知识处理实验室（UKP实验室））；TU Darmstadt（达姆施塔特工业大学）；Hessian Center for AI (hessian.AI)（黑森人工智能中心）；IT:U Interdisciplinary Transformation University Austria（奥地利跨学科转型大学（IT:U））；IBM Research Ireland（IBM爱尔兰研究院）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）
Recent transformer-based approaches demonstrate promising results on relational scientific information extraction. Existing datasets focus on high-level description of how research is carried out. Instead we focus on the subtleties of how experimental associations are presented by building SciClaim, a dataset of scientific claims drawn from Social and Behavior Science (SBS), PubMed, and CORD-19 papers. Our novel graph annotation schema incorporates not only coarse-grained entity spans as nodes and relations as edges between them, but also fine-grained attributes that modify entities and their …
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Identifying the intent of a citation in scientific papers (e.g., background information, use of methods, comparing results) is critical for machine reading of individual publications and automated analysis of the scientific literature. We propose structural scaffolds, a multitask model to incorporate structural information of scientific papers into citations for effective classification of citation intents. Our model achieves a new state-of-the-art on an existing ACL anthology dataset (ACL-ARC) with a 13.3% absolute increase in F1 score, without relying on external linguistic resources or hand…
Despite peer-reviewing being an essential component of academia since the 1600s, it has repeatedly received criticisms for lack of transparency and consistency. We posit that recent work in machine learning and explainable AI provide tools that enable insights into the decisions from a given peer review process. We start by extracting global explanations in the form of linguistic features that affect the acceptance of a scientific paper for publication on an open peer-review dataset. Second, since such global explanations do not justify causal interpretations, we provide a methodology for dete…
The emergence of knowledge graphs in the scholarly communication domain and recent advances in artificial intelligence and natural language processing bring us closer to a scenario where intelligent systems can assist scientists over a range of knowledge-intensive tasks. In this paper we present experimental results about the generation of word embeddings from scholarly publications for the intelligent processing of scientific texts extracted from SciGraph. We compare the performance of domain-specific embeddings with existing pre-trained vectors generated from very large and general purpose c…
Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
We propose a novel unsupervised keyphrase extraction approach that filters candidate keywords using outlier detection. It starts by training word embeddings on the target document to capture semantic regularities among the words. It then uses the minimum covariance determinant estimator to model the distribution of non-keyphrase word vectors, under the assumption that these vectors come from the same distribution, indicative of their irrelevance to the semantics expressed by the dimensions of the learned vector representation. Candidate keyphrases only consist of words that are detected as out…
We present the Webis-STEREO-21 dataset, a massive collection of Scientific Text Reuse in Open-access publications. It contains more than 91 million cases of reused text passages found in 4.2 million unique open-access publications. Featuring a high coverage of scientific disciplines and varieties of reuse, as well as comprehensive metadata to contextualize each case, our dataset addresses the most salient shortcomings of previous ones on scientific writing. Webis-STEREO-21 allows for tackling a wide range of research questions from different scientific backgrounds, facilitating both qualitativ…
University of Pennsylvania（宾夕法尼亚大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Syracuse University（雪城大学）
Claims are a fundamental unit of scientific discourse. The exponential growth in the number of scientific publications makes automatic claim extraction an important problem for researchers who are overwhelmed by this information overload. Such an automated claim extraction system is useful for both manual and programmatic exploration of scientific knowledge. In this paper, we introduce a new dataset of 1,500 scientific abstracts from the biomedical domain with expert annotations for each sentence indicating whether the sentence presents a scientific claim. We introduce a new model for claim ex…
Shanghai Jiao Tong University（上海交通大学）；Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences（中国科学院地理科学与资源研究所）
Understanding the origin and influence of the publication's idea is critical to conducting scientific research. However, the proliferation of scientific publications makes it difficult for researchers to sort out the evolution of all relevant literature. To this end, we present IdeaReader, a machine reading system that finds out which papers are most likely to inspire or be influenced by the target publication and summarizes the ideas of these papers in natural language. Specifically, IdeaReader first clusters the references and citations (first-order or higher-order) of the target publication…
ETH Zurich（苏黎世联邦理工学院）；SUPSI（瑞士南部应用科学与艺术大学）；HE-Arc（阿尔高等工程学院）；Dalle Molle Institute for Artificial Intelligence USI-SUPSI（USI-SUPSI达尔·莫勒人工智能研究所）
The scientific publication output grows exponentially. Therefore, it is increasingly challenging to keep track of trends and changes. Understanding scientific documents is an important step in downstream tasks such as knowledge graph building, text mining, and discipline classification. In this workshop, we provide a better understanding of keyword and keyphrase extraction from the abstract of scientific publications.
Waseda University（早稻田大学）；University of Mannheim（曼海姆大学）；Waseda Research Institute for Science and Engineering（早稻田大学科学与工程研究院）
Providing visual summaries of scientific publications can increase information access for readers and thereby help deal with the exponential growth in the number of scientific publications. Nonetheless, efforts in providing visual publication summaries have been few and far apart, primarily focusing on the biomedical domain. This is primarily because of the limited availability of annotated gold standards, which hampers the application of robust and high-performing supervised learning techniques. To address these problems we create a new benchmark dataset for selecting figures to serve as visu…
Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection
Charles University, Prague（查尔斯大学，布拉格）；Independent Researcher（独立研究者）；University of Helsinki, Finland（赫尔辛基大学）；University of British Columbia, Vancouver, Canada（不列颠哥伦比亚大学，温哥华，加拿大）；Chosun University, South Korea（成均馆大学，韩国）
Interdisciplinary Centre for Mathematical and Computational Modelling, University of Warsaw（华沙大学跨学科数学与计算建模中心）
In this work, we compare two simple methods of tagging scientific publications with labels reflecting their content. As a first source of labels Wikipedia is employed, second label set is constructed from the noun phrases occurring in the analyzed corpus. We examine the statistical properties and the effectiveness of both approaches on the dataset consisting of abstracts from 0.7 million of scientific documents deposited in the ArXiv preprint collection. We believe that obtained tags can be later on applied as useful document features in various machine learning tasks (document similarity, clu…
Several methods have been explored for automating parts of Systematic Mapping (SM) and Systematic Review (SR) methodologies. Challenges typically evolve around the gaps in semantic understanding of text, as well as lack of domain and background knowledge necessary to bridge that gap. In this paper we investigate possible ways of automating parts of the SM/SR process, i.e. that of extracting keywords and key-phrases from scientific documents using unsupervised methods, which are then used as a basis to construct the corresponding Classification Scheme using semantic key-phrase clustering techni…
Nguyen Tat Thanh University（阮爱国大学）；Yeungnam University（岭南大学）；Information Technology College（信息技术学院）；University of Information Technology（信息技术大学）；Chung-Ang University（中央大学）
In this work, we propose a new approach for discovering various relationships among keywords over the scientific publications based on a Markov Chain model. It is an important problem since keywords are the basic elements for representing abstract objects such as documents, user profiles, topics and many things else. Our model is very effective since it combines four important factors in scientific publications: content, publicity, impact and randomness. Particularly, a recommendation system (called SciRecSys) has been presented to support users to efficiently find out relevant articles.
SUTD-MIT International Design Centre（新加坡科技设计大学-麻省理工学院国际设计中心）；Singapore University of Technology and Design（新加坡科技设计大学）
The scientific world is changing at a rapid pace, with new technology being developed and new trends being set at an increasing frequency. This paper presents a framework for conducting scientific analyses of academic publications, which is crucial to monitor research trends and identify potential innovations. This framework adopts and combines various techniques of Natural Language Processing, such as word embedding and topic modelling. Word embedding is used to capture semantic meanings of domain-specific words. We propose two novel scientific publication embedding, i.e., PUB-G and PUB-W, wh…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；University of Potsdam（波茨坦大学）
Scholarly Argumentation Mining (SAM) has recently gained attention due to its potential to help scholars with the rapid growth of published scientific literature. It comprises two subtasks: argumentative discourse unit recognition (ADUR) and argumentative relation extraction (ARE), both of which are challenging since they require e.g. the integration of domain knowledge, the detection of implicit statements, and the disambiguation of argument structure. While previous work focused on dataset construction and baseline methods for specific document sections, such as abstract or results, full-tex…
Panasonic Corporation（松下公司）；National Institute of Advanced Industrial Science and Technology (AIST)（日本产业技术综合研究所（AIST））；Toyota Technological Institute（丰田工学院）
The synthesis process is essential for achieving computational experiment design in the field of inorganic materials chemistry. In this work, we present a novel corpus of the synthesis process for all-solid-state batteries and an automated machine reading system for extracting the synthesis processes buried in the scientific literature. We define the representation of the synthesis processes using flow graphs, and create a corpus from the experimental sections of 243 papers. The automated machine-reading system is developed by a deep learning-based sequence tagger and simple heuristic rule-bas…
To enable efficient exploration of Web-scale scientific knowledge, it is necessary to organize scientific publications into a hierarchical concept structure. In this work, we present a large-scale system to (1) identify hundreds of thousands of scientific concepts, (2) tag these identified concepts to hundreds of millions of scientific publications by leveraging both text and graph structure, and (3) build a six-level concept hierarchy with a subsumption-based model. The system builds the most comprehensive cross-domain scientific concept ontology published to date, with more than 200 thousand…
The number of scientific articles has grown rapidly over the years and there are no signs that this growth will slow down in the near future. Because of this, it becomes increasingly difficult to keep up with the latest developments in a scientific field. To address this problem, we present here an approach to help researchers learn about the latest developments and findings by extracting in a normalized form core claims from scientific articles. This normalized representation is a controlled natural language of English sentences called AIDA, which has been proposed in previous work as a metho…
Faculty of Informatics, Masaryk University（马萨里克大学信息学院）
In this paper, we investigate mathematical content representations suitable for the automated classification of and the similarity search in STEM documents using standard machine learning algorithms: the Latent Dirichlet Allocation (LDA) and the Latent Semantic Indexing (LSI). The methods are evaluated on a subset of arXiv.org papers with the Mathematics Subject Classification (MSC) as a reference classification and using the standard precision/recall/F1-measure metrics. The results give insight into how different math representations may influence the performance of the classification and sim…
We investigate the self-attention mechanism of BERT in a fine-tuning scenario for the classification of scientific articles over a taxonomy of research disciplines. We observe how self-attention focuses on words that are highly related to the domain of the article. Particularly, a small subset of vocabulary words tends to receive most of the attention. We compare and evaluate the subset of the most attended words with feature selection methods normally used for text classification in order to characterize self-attention as a possible feature selection approach. Using ConceptNet as ground truth…
Extracting metadata from scientific papers can be considered a solved problem in NLP due to the high accuracy of state-of-the-art methods. However, this does not apply to German scientific publications, which have a variety of styles and layouts. In contrast to most of the English scientific publications that follow standard and simple layouts, the order, content, position and size of metadata in German publications vary greatly among publications. This variety makes traditional NLP methods fail to accurately extract metadata from these publications. In this paper, we present a method that ext…
