Constructing Biological Knowledge Bases by Extracting Information from Text Sources

By Mark W. Craven, Johan Kumlien. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Training Classifiers with Natural Language Explanations (2018, methodology): “In distant supervision (Craven et al., 1999; Mintz et al., 2009) and multi-instance learning (Riedel et al., 2010; Hoffmann et al., 2011), an existing knowledge base is used to (probabilistically) impute a training set.”
Constructing Datasets for Multi-hop Reading Comprehension Across Documents (2017, background): “There is a plethora of manually curated structured resources (Ashburner et al., 2000; The UniProt Consortium, 2017) which can either serve as ground truth or to induce training data using distant supervision for NLP systems (Craven and Kumlien, 1999; Bobic et al., 2012).”
WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia (2016, background): “A substantial body of work in relation extraction (RE) follows the distant supervision paradigm (Craven and Kumlien, 1999), where sentences containing both arguments of a knowledge base (KB) triple are assumed to express the triple’s relation.”
Distant supervision for relation extraction without labeled data (2009, methodology): “…used by Snow et al. (2005) for exploiting WordNet to extract hyper-nym (is-a) relations between entities, and is similar to the use of weakly labeled data in bioinformatics (Craven and Kumlien, 1999; Morgan et al 1: Ten relation instances extracted by our system that did not appear in Freebase.”
Data Programming: Creating Large Training Sets, Quickly (2016, background): “The canonical example is relation extraction from text, wherein a knowledge base of known relations is heuristically mapped to label a set of mentions in an input corpus as ground truth examples [7,20].”
Concept annotation in the CRAFT corpus (2012, unknown): “…assertions ( e.g. , protein-disease associations and subcellular, cell-type, and tissue localizations of proteins) for Naïve-Bayes-model-based systems trained on a corpus of abstracts in which such assertions were manually annotated, as compared to a basic sentence-cooccurrence-based method [17].”
Extracting the Names of Genes and Gene Products with a Hidden Markov Model (2000, background): “, 1999)(Craven and Kumlien, 1999), to help solve some of the problems that are associated with information overload.”
Mining knowledge from text using information extraction (2005, background): “In biomedical text, one can identify that a protein interacts with another protein or that a protein is located in a particular part of the cell [10; 23].”
Mining the Biomedical Literature in the Genomic Era: An Overview (2003, unknown): “Craven et al. (Craven and Kumlien, 1999; Ray and Craven, 2001) have extended this line of work, developing systems to distinguish fact-bearing sentences from “uninteresting” sentences.”
Term identification in the biomedical literature (2004, background): “Craven and Kumlien [30], on the other hand, collected a set of instances of sub-cellular locations of proteins from the Yeast Protein Database [31] and then identified sentences from the associated PubMed citations in order to get an annotated corpora.”
Leveraging Linguistic Structure For Open Domain Information Extraction (2015, background): “The most common of these are distantly supervised relation extractors (Craven and Kumlien, 1999; Wu and Weld, 2007; Mintz et al., 2009; Sun et al., 2011), and rule based systems (Soderland, 1997; Grish-man and Min, 2010; Chen et al., 2010).”
CoLAKE: Contextualized Language and Knowledge Embedding (2020, methodology): “…inspires the potential applications of WK graph, for example, (a) CoLAKE may help to denoise distantly annotated samples of relation extraction (Craven and Kumlien, 1999; Mintz et al., 2009), (b) CoLAKE can be used to measure the quality of graph-to-text templates (Davison et al., 2019;…”
Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations (2011, unknown): “Craven and Kumlien (1999) introduced the idea by matching the Yeast Protein Database (YPD) to the abstracts of papers in PubMed and training a naive-Bayes extractor.”
Accomplishments and challenges in literature data mining for biology (2002, methodology): “Craven and Kumlien (1999) reported an experiment where they used the subcellular localization ﬁeld of the Yeast Protein Database (Hodges et al. , 1998).”