Tasks, domains, and languages for information extraction

Onyshkevych, Boyan; Okurowski, Mary Ellen; Carlson, Lynn

doi:10.3115/1119149.1119165

Cited by 6 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most prior event extraction work has focused on news articles, resulting in the development of several datasets (Onyshkevych et al, 1993;Grishman and Sundheim, 1996;Pustejovsky et al, 2003b;Doddington et al, 2004;Lee et al, 2012;Cybulska and Vossen, 2014;Mitamura et al, 2016). Recently, event extraction has also been explored in other domains such as biology (Wattarujeekrit et al, 2004;Kim et al, 2008Kim et al, , 2009Berant et al, 2014), Wikipedia articles (Araki and Mitamura, 2018), social media data (Ritter et al, 2012;Li et al, 2014;Jain et al, 2016) and literary novels (Sims et al, 2019).…”

Section: Event Extractionmentioning

confidence: 99%

Adapting Event Extractors to Medical Data: Bridging the Covariate Shift

Naik

Lehman

Rosé

2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

View full text Add to dashboard Cite

We tackle the task of adapting event extractors to new domains without labeled data, by aligning the marginal distributions of source and target domains. As a testbed, we create two new event extraction datasets using English texts from two medical domains: (i) clinical notes, and (ii) doctor-patient conversations. We test the efficacy of three marginal alignment techniques: (i) adversarial domain adaptation (ADA), (ii) domain adaptive fine-tuning (DAFT), and (iii) a new instance weighting technique based on language model likelihood scores (LIW). LIW and DAFT improve over a no-transfer BERT baseline on both domains, but ADA only improves on notes. Deeper analysis of performance under different types of shifts (e.g., lexical shift, semantic shift) explains some of the variations among models. Our best-performing models reach F1 scores of 70.0 and 72.9 on notes and conversations respectively, using no labeled target data.

show abstract

Section: Event Extractionmentioning

confidence: 99%

Adapting Event Extractors to Medical Data: Bridging the Covariate Shift

Naik

Lehman

Rosé

2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

View full text Add to dashboard Cite

show abstract

“…For more information on the template design see [4]. Also see [5] for a discussion of selection of the articles in the corpora and preparation of the data, and [6] for a discussion of the different extraction tasks, domains, and languages.…”

Section: The Preparation Of Templatesmentioning

confidence: 99%

Comparing human and machine performance for natural language information extraction

Will

1993

Proceedings of a Workshop on Held at Fredericksburg, Virginia September 19-23, 1993 -

View full text Add to dashboard Cite

This paper presents results from a study comparing human performance on the text of natural language information extraction with that of machine extraction systems that were developed as part of the ARPA Tipster program. Information extraction is shown to be a difficult task for both humans and machines. Evidence for one set of text material, English Microelectronics, indicated that a human analyst produces about half the errors as does machine systems.

show abstract

“…Information extraction has long been an active subarea of natural language processing (NLP) (Onyshkevych et al, 1993;Freitag, 2000). A particularly important class of extraction tasks is ERE detection in which an object, typically an element in a knowledge base, is created for each ENTITY, RELATION, and EVENT identified in a given text (Song et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Untitled

Bommasani¹,

Katiyar

Cardie

2019

Proceedings of the Third Workshop on Structured Prediction For

View full text Add to dashboard Cite

We propose structured encoding as a novel approach to learning representations for relations and events in neural structured prediction. Our approach explicitly leverages the structure of available relation and event metadata to generate these representations, which are parameterized by both the attribute structure of the metadata as well as the learned representation of the arguments of the relations and events. We consider affine, biaffine, and recurrent operators for building hierarchical representations and modelling underlying features. Without task-specific knowledge sources or domain engineering, we significantly improve over systems and baselines that neglect the available metadata or its hierarchical structure. We observe across-the-board improvements on the BeSt 2016/2017 sentiment analysis task of at least 2.3 (absolute) and 10.6% (relative) F-measure over the previous stateof-the-art.

show abstract

Tasks, domains, and languages for information extraction

Cited by 6 publications

References 0 publications

Adapting Event Extractors to Medical Data: Bridging the Covariate Shift

Adapting Event Extractors to Medical Data: Bridging the Covariate Shift

Comparing human and machine performance for natural language information extraction

Untitled

Contact Info

Product

Resources

About