Search

The automatic semantic structuring of scientific text allows for more efficient reading of research articles and is an important indexing step for academic search engines. Sequential sentence classification is an essential structuring task and targets the categorisation of sentences based on their content and context. However, the potential of transfer learning for sentence classification across different scientific domains and text types, such as full papers and abstracts, has not yet been explored in prior work. In this paper, we present a systematic analysis of transfer learning for scientific sequential sentence classification. For this purpose, we derive seven research questions and present several contributions to address them: (1) We suggest a novel uniform deep learning architecture and multi-task learning for cross-domain sequential sentence classification in scientific text. (2) We tailor two transfer learning methods to deal with the given task, namely sequential transfer learning and multi-task learning. (3) We compare the results of the two best models using qualitative examples in a case study. (4) We provide an approach for the semi-automatic identification of semantically related classes across annotation schemes and analyse the results for four annotation schemes. The clusters and underlying semantic vectors are validated using k-means clustering. (5) Our comprehensive experimental results indicate that when using the proposed multi-task learning architecture, models trained on datasets from different scientific domains benefit from one another. Our approach significantly outperforms state of the art on full paper datasets while being on par for datasets consisting of abstracts.

Sequential sentence classification deals with the categorisation of sentences based on their content and context. Applied to scientific texts, it enables the automatic structuring of research papers and the improvement of academic search engines. However, previous work has not investigated the potential of transfer learning for sentence classification across different scientific domains and the issue of different text structure of full papers and abstracts. In this paper, we derive seven related research questions and present several contributions to address them: First, we suggest a novel uniform deep learning architecture and multi-Task learning for cross-domain sequential sentence classification in scientific texts. Second, we tailor two common transfer learning methods, sequential transfer learning and multi-Task learning, to deal with the challenges of the given task. Semantic relatedness of tasks is a prerequisite for successful transfer learning of neural models. Consequently, our third contribution is an approach to semi-Automatically identify semantically related classes from different annotation schemes and we present an analysis of four annotation schemes. Comprehensive experimental results indicate that models, which are trained on datasets from different scientific domains, benefit from one another when using the proposed multi-Task learning architecture. We also report comparisons with several state-of-The-Art approaches. Our approach outperforms the state of the art on full paper datasets significantly while being on par for datasets consisting of abstracts.

Today’s scholarly communication is a document-centred process and as such, rather inefficient. Fundamental contents of research papers are not accessible by computers since they are only present in unstructured PDF files. Therefore, current research infrastructures are not able to assist scientists appropriately in their core research tasks. This thesis addresses this issue and proposes methods to automatically extract relevant information from scientific articles for Research Knowledge Graphs (RKGs) that represent scholarly knowledge structured and interlinked. First, this thesis conducts a requirements analysis for an Open Research Knowledge Graph (ORKG). We present literature-related use cases of researchers that should be supported by an ORKG-based system and their specific requirements for the underlying ontology and instance data. Based on this analysis, the identified use cases are categorised into two groups: The first group of use cases needs manual or semi-automatic approaches for knowledge graph (KG) construction since they require high correctness of the instance data. The second group requires high completeness and can tolerate noisy instance data. Thus, this group needs automatic approaches for KG population. This thesis focuses on the second group of use cases and provides contributions for machine learning tasks that aim to support them. To assess the relevance of a research paper, scientists usually skim through titles, abstracts, introductions, and conclusions. An organised presentation of the articles' essential information would make this process more time-efficient. The task of sequential sentence classification addresses this issue by classifying sentences in an article in categories like research problem, used methods, or obtained results. To address this problem, we propose a novel unified cross-domain multi-task deep learning approach that makes use of datasets from different scientific domains (e.g. biomedicine and computer graphics) and va, Die Kommunikation von Forschungsergebnissen erfolgt heutzutage in Form von Dokumenten und ist aus verschiedenen Gründen ineffizient. Wesentliche Inhalte von Forschungsarbeiten sind für Computer nicht zugänglich, da sie in unstrukturierten PDF-Dateien verborgen sind. Daher können derzeitige Forschungsinfrastrukturen Forschende bei ihren Kernaufgaben nicht angemessen unterstützen. Diese Arbeit befasst sich mit dieser Problemstellung und untersucht Methoden zur automatischen Extraktion von relevanten Informationen aus Forschungspapieren für Forschungswissensgraphen (Research Knowledge Graphs). Solche Graphen sollen wissenschaftliches Wissen maschinenlesbar strukturieren und verknüpfen. Zunächst wird eine Anforderungsanalyse für einen Open Research Knowledge Graph (ORKG) durchgeführt. Wir stellen literaturbezogene Anwendungsfälle von Forschenden vor, die durch ein ORKG-basiertes System unterstützt werden sollten, und deren spezifische Anforderungen an die zugrundeliegende Ontologie und die Instanzdaten. Darauf aufbauend werden die identifizierten Anwendungsfälle in zwei Gruppen eingeteilt: Die erste Gruppe von Anwendungsfällen benötigt manuelle oder halbautomatische Ansätze für die Konstruktion eines ORKG, da sie eine hohe Korrektheit der Instanzdaten erfordern. Die zweite Gruppe benötigt eine hohe Vollständigkeit der Instanzdaten und kann fehlerhafte Daten tolerieren. Daher erfordert diese Gruppe automatische Ansätze für die Konstruktion des ORKG. Diese Arbeit fokussiert sich auf die zweite Gruppe von Anwendungsfällen und schlägt Methoden für maschinelle Aufgabenstellungen vor, die diese Anwendungsfälle unterstützen können. Um die Relevanz eines Forschungsartikels effizient beurteilen zu können, schauen sich Forschende in der Regel die Titel, Zusammenfassungen, Einleitungen und Schlussfolgerungen an. Durch eine strukturierte Darstellung von wesentlichen Informationen des Artikels könnte dieser Prozess zeitsparender gestaltet werden. Die Aufgabenstellung der sequenziell

Current science communication has a number of drawbacks and bottlenecks which have been subject of discussion lately: Among others, the rising number of published articles makes it nearly impossible to get a full overview of the state of the art in a certain field, or reproducibility is hampered by fixed-length, document-based publications which normally cannot cover all details of a research work. Recently, several initiatives have proposed knowledge graphs (KG) for organising scientific information as a solution to many of the current issues. The focus of these proposals is, however, usually restricted to very specific use cases. In this paper, we aim to transcend this limited perspective and present a comprehensive analysis of requirements for an Open Research Knowledge Graph (ORKG) by (a) collecting and reviewing daily core tasks of a scientist, (b) establishing their consequential requirements for a KG-based system, (c) identifying overlaps and specificities, and their coverage in current solutions. As a result, we map necessary and desirable requirements for successful KG-based science communication, derive implications, and outline possible solutions.

Citation recommendation for research papers is a valuable task that can help researchers improve the quality of their work by suggesting relevant related work. Current approaches for this task rely primarily on the text of the papers and the citation network. In this paper, we propose to exploit an additional source of information, namely research knowledge graphs (KG) that interlink research papers based on mentioned scientific concepts. Our experimental results demonstrate that the combination of information from research KGs with existing state-of-the-art approaches is beneficial. Experimental results are presented for the STM-KG (STM: Science, Technology, Medicine), which is an automatically populated knowledge graph based on the scientific concepts extracted from papers of ten domains. The proposed approach outperforms the state of the art with a mean average precision of 20.6% (+0.8) for the top-50 retrieved results., Comment: Accepted for publication in 25th International Conference on Theory and Practice of Digital Libraries (TPDL), 2021

Current science communication has a number of drawbacks and bottlenecks which have been subject of discussion lately: Among others, the rising number of published articles makes it nearly impossible to get a full overview of the state of the art in a certain field, or reproducibility is hampered by fixed-length, document-based publications which normally cannot cover all details of a research work. Recently, several initiatives have proposed knowledge graphs (KG) for organising scientific information as a solution to many of the current issues. The focus of these proposals is, however, usually restricted to very specific use cases. In this paper, we aim to transcend this limited perspective and present a comprehensive analysis of requirements for an Open Research Knowledge Graph (ORKG) by (a) collecting and reviewing daily core tasks of a scientist, (b) establishing their consequential requirements for a KG-based system, (c) identifying overlaps and specificities, and their coverage in current solutions. As a result, we map necessary and desirable requirements for successful KG-based science communication, derive implications, and outline possible solutions., Comment: arXiv admin note: text overlap with arXiv:2005.10334

Sequential sentence classification deals with the categorisation of sentences based on their content and context. Applied to scientific texts, it enables the automatic structuring of research papers and the improvement of academic search engines. However, previous work has not investigated the potential of transfer learning for sentence classification across different scientific domains and the issue of different text structure of full papers and abstracts. In this paper, we derive seven related research questions and present several contributions to address them: First, we suggest a novel uniform deep learning architecture and multi-task learning for cross-domain sequential sentence classification in scientific texts. Second, we tailor two common transfer learning methods, sequential transfer learning and multi-task learning, to deal with the challenges of the given task. Semantic relatedness of tasks is a prerequisite for successful transfer learning of neural models. Consequently, our third contribution is an approach to semi-automatically identify semantically related classes from different annotation schemes and we present an analysis of four annotation schemes. Comprehensive experimental results indicate that models, which are trained on datasets from different scientific domains, benefit from one another when using the proposed multi-task learning architecture. We also report comparisons with several state-of-the-art approaches. Our approach outperforms the state of the art on full paper datasets significantly while being on par for datasets consisting of abstracts., Comment: Accepted for publication in ACM/IEEE Joint Conference on Digital Libraries (JCDL), 2022

Coreference resolution is essential for automatic text understanding to facilitate high-level information retrieval tasks such as text summarisation or question answering. Previous work indicates that the performance of state-of-the-art approaches (e.g. based on BERT) noticeably declines when applied to scientific papers. In this paper, we investigate the task of coreference resolution in research papers and subsequent knowledge graph population. We present the following contributions: (1) We annotate a corpus for coreference resolution that comprises 10 different scientific disciplines from Science, Technology, and Medicine (STM); (2) We propose transfer learning for automatic coreference resolution in research papers; (3) We analyse the impact of coreference resolution on knowledge graph (KG) population; (4) We release a research KG that is automatically populated from 55,485 papers in 10 STM domains. Comprehensive experiments show the usefulness of the proposed approach. Our transfer learning approach considerably outperforms state-of-the-art baselines on our corpus with an F1 score of 61.4 (+11.0), while the evaluation against a gold standard KG shows that coreference resolution improves the quality of the populated KG significantly with an F1 score of 63.5 (+21.8)., Comment: Accepted for publication in 43rd European Conference on Information Retrieval (ECIR), 2021

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 following features: 1) a generic conceptual formalism for scientific entities in a multidisciplinary scientific context; 2) the feasibility of the domain-independent human annotation of scientific entities under such a generic formalism; 3) a performance benchmark obtainable for automatic extraction of multidisciplinary scientific entities using BERT-based neural models; 4) a delineated 3-step entity resolution procedure for human annotation of the scientific entities via encyclopedic entity linking and lexicographic word sense disambiguation; and 5) human evaluations of Babelfy returned encyclopedic links and lexicographic senses for our entities. Our findings cumulatively indicate that human annotation and automatic learning of multidisciplinary scientific concepts as well as their semantic disambiguation in a wide-ranging setting as STEM is reasonable.

Current science communication has a number of drawbacks and bottlenecks which have been subject of discussion lately: Among others, the rising number of published articles makes it nearly impossible to get an overview of the state of the art in a certain field, or reproducibility is hampered by fixed-length, document-based publications which normally cannot cover all details of a research work. Recently, several initiatives have proposed knowledge graphs (KGs) for organising scientific information as a solution to many of the current issues. The focus of these proposals is, however, usually restricted to very specific use cases. In this paper, we aim to transcend this limited perspective by presenting a comprehensive analysis of requirements for an Open Research Knowledge Graph (ORKG) by (a) collecting daily core tasks of a scientist, (b) establishing their consequential requirements for a KG-based system, (c) identifying overlaps and specificities, and their coverage in current solutions. As a result, we map necessary and desirable requirements for successful KG-based science communication, derive implications and outline possible solutions., Comment: Accepted for publishing in 24th International Conference on Theory and Practice of Digital Libraries, TPDL 2020

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 following features: 1) a generic conceptual formalism for scientific entities in a multidisciplinary scientific context; 2) the feasibility of the domain-independent human annotation of scientific entities under such a generic formalism; 3) a performance benchmark obtainable for automatic extraction of multidisciplinary scientific entities using BERT-based neural models; 4) a delineated 3-step entity resolution procedure for human annotation of the scientific entities via encyclopedic entity linking and lexicographic word sense disambiguation; and 5) human evaluations of Babelfy returned encyclopedic links and lexicographic senses for our entities. Our findings cumulatively indicate that human annotation and automatic learning of multidisciplinary scientific concepts as well as their semantic disambiguation in a wide-ranging setting as STEM is reasonable., Comment: Published in LREC 2020. Publication URL https://www.aclweb.org/anthology/2020.lrec-1.268/; Dataset DOI https://doi.org/10.25835/0017546

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 of concepts between domains. Second, we present two deep learning systems as baselines. In particular, we propose active learning to deal with different domains in our task. The experimental results show that (1) a substantial agreement is achievable by non-experts after consultation with domain experts, (2) the baseline system achieves a fairly high F1 score, (3) active learning enables us to nearly halve the amount of required training data., Comment: Accepted for publishing in 42nd European Conference on IR Research, ECIR 2020