Extracting causal relations from the literature with word vector mapping

An, Ning; Xiao, Yue; Yuan, Jing; Yang, Jiaoyun; Alterovitz, Gil

doi:10.1016/j.compbiomed.2019.103524

Cited by 15 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, terms were manually classified as potential causes, outcomes, protective factors, or indicators, based on domain knowledge. Efforts are underway to develop unsupervised algorithms capable of distilling implied causal links from scientific abstracts (An et al, 2019). Future research might substantially advance theory formation by applying such methods to the present corpus.…”

Section: Strengths and Limitationsmentioning

confidence: 99%

Mapping Phenomena Relevant to Adolescent Emotion Regulation: A Text-Mining Systematic Review

Lissa

2021

Adolescent Res Rev

View full text Add to dashboard Cite

Adolescence is a developmentally sensitive period for emotion regulation with potentially lifelong implications for mental health and well-being. Although substantial empirical research has addressed this topic, the literature is fragmented across subdisciplines, and an overarching theoretical framework is lacking. The first step toward constructing a unifying framework is identifying relevant phenomena. This systematic review of 6305 articles used text mining to identify phenomena relevant to adolescents’ emotion regulation. First, a baseline was established of relevant phenomena discussed in theory and recent narrative reviews. Then, article keywords and abstracts were analyzed using text mining, examining term frequency as an indicator of relevance and term co-occurrence as an indicator of association. The results reflected themes commonly featured in theory and narrative reviews, such as socialization and neurocognitive development, but also identified undertheorized themes, such as developmental disorders, physical health, external stressors, structural disadvantage, substance use, identity and moral development, and sexual development. The findings illustrate how text mining systematic reviews, a novel approach, may complement narrative reviews. Future theoretical work might integrate these undertheorized themes into an overarching framework, and empirical research might consider them as promising areas for future research, or as potential confounders in research on adolescents’ emotion regulation.

show abstract

Section: Strengths and Limitationsmentioning

confidence: 99%

Mapping Phenomena Relevant to Adolescent Emotion Regulation: A Text-Mining Systematic Review

Lissa

2021

Adolescent Res Rev

View full text Add to dashboard Cite

show abstract

“…Causal relation extraction tasks can be mainly categorized into unsupervised [ 13 , 14 ], supervised [ 15 , 16 ], and hybrid approaches [ 12 , 17 , 18 ]. The unsupervised approaches are mainly pattern-based approach, which use causative verbs, causal links, and causal relations between words or phrases to extract cause effect pairs.…”

Section: Related Workmentioning

confidence: 99%

“…In this work, the causality relations are defined by a set of terms, such as “causes” and “effects,” with associated strength. An et al [ 10 ] explored extracting causal relations using syntactic analysis with word embedding. They used designed syntactic patterns to first obtain triples including the cause and effect pairs, verb that links the pairs, and a binary term denoting whether the relation is passive or negative.…”

Section: Related Workmentioning

confidence: 99%

“…Due to the importance of causality extraction in medical domains, several works [ 7 – 10 ] have been proposed, which either identify causal relations from sentences or extract cause and effect pairs to build causal networks. These existing works either use a set of known syntactic patterns to extract the cause and effect entities or use machine learning models to identify those entity pairs.…”

Section: Introductionmentioning

confidence: 99%

“…For example, consider the sentence “Deficiency in Vitamin D can cause increased mortality rate in Covid-19 patients.” One of the existing methods, which we refer to as Logical-Rule Based method [ 11 ], extracts “Vitamin D” as the cause term and “increased mortality rate” as the effect term, seemingly conveying the erroneous fact that “Vitamin D causes increase mortality rate”—whereas, it is not “Vitamin D,” but the “deficiency of Vitamin D” is the culprit. Another existing method, which we refer to as Word Vector Mapping Based method [ 12 ] extract “Defficiency” as the cause term and “increase mortality rate” as the effect term, leaves the readers dumbfounded with the question, deficiency of what? Given the abundance of longer cause and effect phrases in the medical text, a new causality extraction method is needed which is better at capturing the complete cause and effect phrases, thus retaining the integrity of the fact intended in a causal sentence.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Informative Causality Extraction from Medical Literature via Dependency-Tree–Based Patterns

Kabir

Almulhim

Luo

et al. 2022

J Healthc Inform Res

View full text Add to dashboard Cite

Extracting cause-effect entities from medical literature is an important task in medical information retrieval. A solution for solving this task can be used for compilation of various causality relations, such as causality between disease and symptoms, between medications and side effects, and between genes and diseases. Existing solutions for extracting cause-effect entities work well for sentences where the cause and the effect phrases are name entities, single-word nouns, or noun phrases consisting of two to three words. Unfortunately, in medical literature, cause and effect phrases in a sentence are not simply nouns or noun phrases, rather they are complex phrases consisting of several words, and existing methods fail to correctly extract the cause and effect entities in such sentences. Partial extraction of cause and effect entities conveys poor quality, non-informative, and often, contradictory facts, comparing to the one intended in the given sentence. In this work, we solve this problem by designing an unsupervised method for cause and effect phrase extraction, PatternCausality , which is specifically suitable for the medical literature. Our proposed approach first uses a collection of cause-effect dependency patterns as template to extract head words of cause and effect phrases and then it uses a novel phrase extraction method to obtain complete and meaningful cause and effect phrases from a sentence. Experiments on a cause-effect dataset built from sentences from PubMed articles show that for extracting cause and effect entities, PatternCausality is substantially better than the existing methods—with an order of magnitude improvement in the F -score metric over the best of the existing methods. We also build different variants of PatternCausality , which use different phrase extraction methods; all variants are better than the existing methods. PatternCausality and its variants also show modest performance improvement over the existing methods for extracting cause and effect entities in a domain-neutral benchmark dataset, in which cause and effect entities are nouns or noun phrases consisting of one to two words.

show abstract

Causality extraction model based on two-stage GCN

et al. 2022

View full text Add to dashboard Cite

In the traditional methods, the low identification accuracy of cascade implicit causalities is caused by the lack of causal inference. To solve this problem, we propose a causality extraction model based on GCN to infer the causality of the text. It can analyze the cause-effect existing in the text and realize the deep extraction under semantic enhancement. First, the data are preprocessed, and BERT is used for pre-training. In the pre-training, the candidate entities are selected by entity links. The text encoding is used context semantics and embedding location coding. Then, the semantic dependency graph is used to obtain the relationship between entities. In addition, the nodes and edges obtained by the previous step are input into the first-stage GCN to extract the whole causality. Finally, the entity relation graph obtained by the first-stage GCN is introduced into the second-stage GCN for cascade inference. The causality of the cascade is inferred and extracted by a two-stage GCN. Experiments show that the model can find implicit causality more accurately generate new implicit causal entities on the original causality.

show abstract

Extracting causal relations from the literature with word vector mapping

Cited by 15 publications

References 11 publications

Mapping Phenomena Relevant to Adolescent Emotion Regulation: A Text-Mining Systematic Review

Mapping Phenomena Relevant to Adolescent Emotion Regulation: A Text-Mining Systematic Review

Informative Causality Extraction from Medical Literature via Dependency-Tree–Based Patterns

Causality extraction model based on two-stage GCN

Contact Info

Product

Resources

About