Syntactic Simplification and Semantic Enrichment-Trimming Dependency Graphs for Event Extraction

Buyko, Ekaterina; Faessler, Erik; Wermter, Joachim; Hahn, Udo

doi:10.1111/j.1467-8640.2011.00402.x

Cited by 14 publications

(12 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was shown in [33] that the size of this subgraph correlates with the class of the event: positive instances are present typically in smaller subgraphs. For the same dataset, in [34] it is shown that the distance between trigger and potential arguments is much smaller for positive than for negative instances.…”

Section: Resultsmentioning

confidence: 99%

A detailed error analysis of 13 kernel methods for protein-protein interaction extraction

et al. 2013

View full text Add to dashboard Cite

BackgroundKernel-based classification is the current state-of-the-art for extracting pairs of interacting proteins (PPIs) from free text. Various proposals have been put forward, which diverge especially in the specific kernel function, the type of input representation, and the feature sets. These proposals are regularly compared to each other regarding their overall performance on different gold standard corpora, but little is known about their respective performance on the instance level.ResultsWe report on a detailed analysis of the shared characteristics and the differences between 13 current methods using five PPI corpora. We identified a large number of rather difficult (misclassified by most methods) and easy (correctly classified by most methods) PPIs. We show that kernels using the same input representation perform similarly on these pairs and that building ensembles using dissimilar kernels leads to significant performance gain. However, our analysis also reveals that characteristics shared between difficult pairs are few, which lowers the hope that new methods, if built along the same line as current ones, will deliver breakthroughs in extraction performance.ConclusionsOur experiments show that current methods do not seem to do very well in capturing the shared characteristics of positive PPI pairs, which must also be attributed to the heterogeneity of the (still very few) available corpora. Our analysis suggests that performance improvements shall be sought after rather in novel feature sets than in novel kernel functions.

show abstract

Section: Resultsmentioning

confidence: 99%

A detailed error analysis of 13 kernel methods for protein-protein interaction extraction

et al. 2013

View full text Add to dashboard Cite

show abstract

“…This higher performance can be explained by the fact that the SPIES system was evaluated only on a corpus that contained no sentence without a positive example. Filtering by trigger-word-based pattern evaluation was also performed by Cohen et al [ 16 ] and by Buyko et al [ 27 ], specifically for the BioNLP task. Cohen et al [ 16 ] order trigger words by frequency and keep only the top 10-30% (depending on the event type) for pattern generation.…”

Section: Discussionmentioning

confidence: 99%

Simple tricks for improving pattern-based information extraction from the biomedical literature

2010

View full text Add to dashboard Cite

BackgroundPattern-based approaches to relation extraction have shown very good results in many areas of biomedical text mining. However, defining the right set of patterns is difficult; approaches are either manual, incurring high cost, or automatic, often resulting in large sets of noisy patterns.ResultsWe propose several techniques for filtering sets of automatically generated patterns and analyze their effectiveness for different extraction tasks, as defined in the recent BioNLP 2009 shared task. We focus on simple methods that only take into account the complexity of the pattern and the complexity of the texts the patterns are applied to. We show that our techniques, despite their simplicity, yield large improvements in all tasks we analyzed. For instance, they raise the F-score for the task of extraction gene expression events from 24.8% to 51.9%.ConclusionsAlready very simple filtering techniques may improve the F-score of an information extraction method based on automatically generated patterns significantly. Furthermore, the application of such methods yields a considerable speed-up, as fewer matches need to be analysed. Due to their simplicity, the proposed filtering techniques also should be applicable to other methods using linguistic patterns for information extraction.

show abstract

“…Semantic relations are usually binary, and can be expressed as grammaticosemantic links between lexical units, e.g. named entities, for example: X father-of Y or father-of(X, Y) where X and Y are instances of named entity types; by syntactic dependencies, which approximate the underlying semantic relationships [15]; or by conventional RDF S-V-O triples, which is a universal representation of relations. Moreover, semantic relations are often terminological relations, e.g.…”

Section: Relations and Eventsmentioning

confidence: 99%

Mining semantics for culturomics

Borin

Dubhashi

Forsberg

et al. 2013

Proceedings of the 2013 International Workshop on Mining Unstructured Big Data Using Natural Language Processing

View full text Add to dashboard Cite

The massive amounts of text data made available through the Google Books digitization project have inspired a new field of big-data textual research. Named culturomics, this field has attracted the attention of a growing number of scholars over recent years. However, initial studies based on these data have been criticized for not referring to relevant work in linguistics and language technology. This paper provides some ideas, thoughts and first steps towards a new culturomics initiative, based this time on Swedish data, which pursues a more knowledge-based approach than previous work in this emerging field. The amount of new Swedish text produced daily and older texts being digitized in cultural heritage projects grows at an accelerating rate. These volumes of text being available in digital form have grown far beyond the capacity of human readers, leaving automated semantic processing of the texts as the only realistic option for accessing and using the information contained in them. The aim of our recently initiated research program is to advance the state of the art in language technology resources and methods for semantic processing of Big Swedish text and focus on the theoretical and methodological advancement of the state of the art in extracting and correlating information from large volumes of Swedish text using a combination of knowledge-based and statistical methods.

show abstract

Syntactic Simplification and Semantic Enrichment-Trimming Dependency Graphs for Event Extraction

Cited by 14 publications

References 40 publications

A detailed error analysis of 13 kernel methods for protein-protein interaction extraction

A detailed error analysis of 13 kernel methods for protein-protein interaction extraction

Simple tricks for improving pattern-based information extraction from the biomedical literature

Mining semantics for culturomics

Contact Info

Product

Resources

About