A Survey of Multilingual Event Extraction from Text

Danilova, Vera; Alexandrov, Mikhail; Blanco, Xavier

doi:10.1007/978-3-319-07983-7_13

Cited by 7 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some surveys have already dealt with the extraction of events from the text, maintaining a specific focus (decision support systems [18], [19], multilingual [20], social media [21], [22], biomedical [8], [23], [24], open domain [25]) or proposing a general and systematic review [26]. Even though the aforementioned articles testify to the upsurge of event-related activities, to our best knowledge, there is little work taking into account the link between EE and NLU on a higher abstraction level, without adopting a closed view linked to the task or domain.…”

Section: Summary Of the Surveymentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Event Extraction for Natural Language Understanding: Riding the Biomedical Literature Wave

Frisoni¹,

Moro

Carbonaro

2021

IEEE Access

View full text Add to dashboard Cite

Motivation: The scientific literature embeds an enormous amount of relational knowledge, encompassing interactions between biomedical entities, like proteins, drugs, and symptoms. To cope with the everincreasing number of publications, researchers are experiencing a surge of interest in extracting valuable, structured, concise, and unambiguous information from plain texts. With the development of deep learning, the granularity of information extraction is evolving from entities and pairwise relations to events. Events can model complex interactions involving multiple participants having a specific semantic role, also handling nested and overlapping definitions. After being studied for years, automatic event extraction is on the road to significantly impact biology in a wide range of applications, from knowledge base enrichment to the formulation of new research hypotheses. Results: This paper provides a comprehensive and up-to-date survey on the link between event extraction and natural language understanding, focusing on the biomedical domain. First, we establish a flexible event definition, summarizing the terminological efforts conducted in various areas. Second, we present the event extraction task, the related challenges, and the available annotated corpora. Third, we deeply explore the most representative methods and present an analysis of the current state-of-the-art, accompanied by performance discussion. To help researchers navigate the avalanche of event extraction works, we provide a detailed taxonomy for classifying the contributions proposed by the community. Fourth, we compare solutions applied in biomedicine with those evaluated in other domains, identifying research opportunities and providing insights for strategies not yet explored. Finally, we discuss applications and our envisions about future perspectives, moving the needle on explainability and knowledge injection.INDEX TERMS Biomedical text mining, event extraction, natural language understanding, semantic parsing.

show abstract

Section: Summary Of the Surveymentioning

confidence: 99%

“…Coarse-grained types are typically used as targets for rare events without appropriate fine-grained types 11. Interestingly, in some general-domain knowledge bases (like AT OM IC[248] and AT OM IC20 20[249] for commonsense reasoning), an event is directly represented as a sentence instead of a structured format.VOLUME 4, 2016 …”

mentioning

confidence: 99%

A Survey on Event Extraction for Natural Language Understanding: Riding the Biomedical Literature Wave

Frisoni¹,

Moro

Carbonaro

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Distant supervision is less applicable for the task of event extraction because very few dynamic events are included in KBs. These approaches, however, incorporate language-specific characteristics and thus are costly in requiring substantial amount of annotations to adapt to a new language (Chen and Vincent, 2012;Blessing and Schütze, 2012;Li et al, 2012;Danilova et al, 2014;Agerri et al, 2016;Hsi et al, 2016;Feng et al, 2016).…”

Section: Related Workmentioning

confidence: 99%

Cross-lingual Structure Transfer for Relation and Event Extraction

Subburathinam

Ji³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

The identification of complex semantic structures such as events and entity relations, already a challenging Information Extraction task, is doubly difficult from sources written in under-resourced and under-annotated languages. We investigate the suitability of crosslingual structure transfer techniques for these tasks. We exploit relation-and event-relevant language-universal features, leveraging both symbolic (including part-of-speech and dependency path) and distributional (including type representation and contextualized representation) information. By representing all entity mentions, event triggers, and contexts into this complex and structured multilingual common space, using graph convolutional networks, we can train a relation or event extractor from source language annotations and apply it to the target language. Extensive experiments on cross-lingual relation and event transfer among English, Chinese, and Arabic demonstrate that our approach achieves performance comparable to state-of-the-art supervised models trained on up to 3,000 manually annotated mentions: up to 62.6% F-score for Relation Extraction, and 63.1% F-score for Event Argument Role Labeling. The event argument role labeling model transferred from English to Chinese achieves similar performance as the model trained from Chinese. We thus find that language-universal symbolic and distributional representations are complementary for cross-lingual structure transfer.

show abstract

“…This Section provides a brief overview of the general workflow of several systems for political event data collection and coding that process few types of protest events, and of two early prototypes that focus on protest events. Our overview of multilingual news monitoring systems and approaches is given in [3].…”

Section: Related Workmentioning

confidence: 99%

A Pipeline for Multilingual Protest Event Selection and Annotation

Danilova

2015

2015 26th International Workshop on Database and Expert Systems Applications (DEXA)

Self Cite

View full text Add to dashboard Cite

This paper presents a pipeline for multilingual analysis of contentious social behaviour. Its basic functionalities include news articles extraction from a variety of multilingual news sources (in Bulgarian, French, Polish, Russian, Spanish, and Swedish), protest event selection and an ontology-based event annotation. The results are output in CSV format. An evaluation of protest event selection and annotation (Event Reason slot) algorithms is presented.

show abstract

A Survey of Multilingual Event Extraction from Text

Cited by 7 publications

References 4 publications

A Survey on Event Extraction for Natural Language Understanding: Riding the Biomedical Literature Wave

A Survey on Event Extraction for Natural Language Understanding: Riding the Biomedical Literature Wave

Cross-lingual Structure Transfer for Relation and Event Extraction

A Pipeline for Multilingual Protest Event Selection and Annotation

Contact Info

Product

Resources

About