Statistical anaphora resolution in biomedical texts

Gasperin, Caroline; Briscoe, Ted

doi:10.3115/1599081.1599114

Cited by 32 publications

(29 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The area of statistical anaphora resolution had been approached by computer linguists. Gasperin and Briscoe [8] applied an statistical approach for anaphora resolution in biomedical texts. They built a system which was based on the naive-Bayes classifier.…”

Section: Related Workmentioning

confidence: 99%

Extracting and enriching workflows from text

Schumacher

Minor

Schulte-Zurhausen

2013

2013 IEEE 14th International Conference on Information Reuse &Amp; Integration (IRI)

View full text Add to dashboard Cite

This paper is on a workflow extraction framework which allows to derive a formal representation based on workflows from textual descriptions of instructions, for instance, of aircraft repair procedures from a maintenance manual. The framework applies a pipes-and-filters architecture and uses NLP (Natural Language Processing) tools to perform information extraction steps automatically. In detail, the paper presents on the step of anaphora resolution to enrich the workflow extracted so far. We introduce a lexical approach and two further approaches based on a set of association rules which are created during a statistical analysis of a corpus of workflows. The results of the approaches are compared to each other. For the evaluation, we use 37 workflows which have been created by a human expert.

show abstract

Section: Related Workmentioning

confidence: 99%

Extracting and enriching workflows from text

Schumacher

Minor

Schulte-Zurhausen

2013

2013 IEEE 14th International Conference on Information Reuse &Amp; Integration (IRI)

View full text Add to dashboard Cite

show abstract

“…Unlike the work of (Castaño et al, 2002), (Gasperin and Briscoe, 2008), and (Gasperin, 2009) that resolved coreferential relations on certain restricted entities in the biomedical domain, we resolve all NP coreferential relations. Although the GENIA corpus contains 1,999 biomedical abstracts, Yang et al (2004) tested only on 200 abstracts under 5-fold cross validation.…”

Section: Related Workmentioning

confidence: 99%

Domain Adaptation with Active Learning for Coreference Resolution

Zhao¹,

Ng²

2014

Proceedings of the 5th International Workshop on Health Text Mining and Information Analysis (Louhi)

View full text Add to dashboard Cite

In the literature, most prior work on coreference resolution centered on the newswire domain. Although a coreference resolution system trained on the newswire domain performs well on newswire texts, there is a huge performance drop when it is applied to the biomedical domain. In this paper, we present an approach integrating domain adaptation with active learning to adapt coreference resolution from the newswire domain to the biomedical domain. We explore the effect of domain adaptation, active learning, and target domain instance weighting for coreference resolution. Experimental results show that domain adaptation with active learning and target domain instance weighting achieves performance on MEDLINE abstracts similar to a system trained on coreference annotation of only target domain training instances, but with a greatly reduced number of target domain training instances that we need to annotate.

show abstract

“…It is well-known that there are large differences in reference phenomena between scientific text and other domains (Gasperin, 2009). In scientific text, it is assumed that the reader has a relatively high level of background.…”

Section: Annotation Schemementioning

confidence: 99%

“…Resolving anaphora in scientific text has only recently gained interest in the research community and focuses mostly on the biomedical domain (Gasperin, 2009;Batista-Navarro and Ananiadou, 2011;Cohen et al, 2010). Some work has been done for other disciplines, such as computational linguistics.…”

Section: Related Workmentioning

confidence: 99%

“…They might also be of use in higherlevel text understanding tasks such as textual entailment (Mirkin et al, 2010) or summarisation based on argument overlap (Kintsch and van Dijk, 1978;Fang and Teufel, 2014). Gasperin (2009) showed that biological texts differ considerably from other text genres, such as news text or dialogue. In this respect, our results confirm that the proportion between non-referring and referring entities in scientific text differs from that reported for other genres.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Resolving Coreferent and Associative Noun Phrases in Scientific Text

Roesiger¹,

Teufel²

2014

Proceedings of the Student Research Workshop at the 14th Conference of the European Chapter of the Association for Computationa

View full text Add to dashboard Cite

We present a study of information status in scientific text as well as ongoing work on the resolution of coreferent and associative anaphora in two different scientific disciplines, namely computational linguistics and genetics. We present an annotated corpus of over 8000 definite descriptions in scientific articles. To adapt a state-of-the-art coreference resolver to the new domain, we develop features aimed at modelling technical terminology and integrate these into the coreference resolver. Our results indicate that this integration, combined with domain-dependent training data, can outperform the performance of an out-of-the-box coreference resolver. For the (much harder) task of resolving associative anaphora, our preliminary results show the need for and the effect of semantic features.

show abstract

Statistical anaphora resolution in biomedical texts

Cited by 32 publications

References 59 publications

Extracting and enriching workflows from text

Extracting and enriching workflows from text

Domain Adaptation with Active Learning for Coreference Resolution

Resolving Coreferent and Associative Noun Phrases in Scientific Text

Contact Info

Product

Resources

About