2020 ScientificTextMiningandKnowledg
- (Jiang & Shang, 2020) ⇒ Meng Jiang, and Jingbo Shang. (2020). “Scientific Text Mining and Knowledge Graphs.” Tutorial in the the 26th ACM SIGKDD Conferences on Knowledge Discovery and Data Mining (KDD-2020).
Subject Headings: Scientific Text Mining.
Notes
- 08:00-08:10 Introduction (Shang) slides video
- 08:10-09:00 Mining Structures from Scientific Text (Shang): Phrase mining, etc. slides video
- 09:00-09:35 Extracting Information from Scientific Text (Jiang) slides video
- 09:35-10:05 Building Scientific Knowledge Graphs (Shang): Ontology, taxonomy, etc. slides video
- 10:05-10:30 Building Scientific Knowledge Graphs (Jiang): Biomedical KG, etc. slides video
- 10:30-10:40 Conclusions (Jiang) slides video
Cited By
Quotes
Abstract
Unstructured scientific text, in various forms of textual artifacts, including manuscripts, publications, patents, and proposals, is used to store the tremendous wealth of knowledge discovered after weeks, months, and years, developing hypotheses, working in the lab or clinic, and analyzing results. A grand challenge on data mining research is to develop effective methods for transforming the scientific text into well-structured forms (e.g., ontology, taxonomy, knowledge graphs), so that machine intelligent systems can build on them for hypothesis generation and validation. In this tutorial, we provide a comprehensive overview on recent research and development in this direction. First, we introduce a series of text mining methods that extract phrases, entities, scientific concepts, relations, claims, and experimental evidence. Then we discuss methods that construct and learn from scientific knowledge graphs for accurate search, document classification, and exploratory analysis. Specifically, we focus on scalable, effective, weakly supervised methods that work on text in sciences (e.g., chemistry, biology).
Introduction
Chapter 1 Part 1: Phrase Mining
Chapter 1 Part 2: Named Entity Recognition and Neural Language Models
Chapter 1 Part 3: Relation Extraction and Attribute Discovery
Chapter 1 Part 4: Scientific Statements
Chapter 2 Part 1: Taxonomy Construction
Chapter 2 Part 2: Knowledge Graph Learning
Conclusions
- Methods for extracting entities (methods, research topics, technologies, tasks, materials, metrics, research contributions) and relationships from research publications
- Methods for extracting metadata about authors, documents, datasets, grants, affiliations and others.
- Methods for quality assessment of scientific knowledge graphs
- Methods for the exploration, retrieval and visualization of scientific knowledge graphs
- Scientific claims identification from textual contents • Novel user interfaces for interaction with paper, metadata, content, software and data
- Data models (e.g., ontologies, vocabularies, schemas) for the description of scholarly data and the linking between scholarly data/software and academic papers that report or cite them
- Automatic or semi-automatic approaches to making sense of research dynamics
- Applications for the (semi-)automatic annotation of scholarly papers
- Description and use of provenance information of scholarly data
- Theoretical models describing the rhetorical and argumentative structure of scholarly papers and their application in practice
- Novel user interfaces for interaction with paper, metadata, content, software and data
- Visualization of related papers or data according to multiple dimensions (semantic similarity of abstracts, keywords, etc.)
References
;
| Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
|---|---|---|---|---|---|---|---|---|---|---|
| 2020 ScientificTextMiningandKnowledg | Meng Jiang Jingbo Shang | Scientific Text Mining and Knowledge Graphs | 2020 |