Convolution kernels on constituent, dependency and sequential structures for relation extraction

Nguyen, Truc-Vien T.; Moschitti, Alessandro; Riccardi, Giuseppe

doi:10.3115/1699648.1699684

Cited by 67 publications

(40 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent approach successfully employs a convolution tree kernel over constituent syntactic parse tree [42,46]. The combination of such kernel with others based on grammatical relations from dependency structure was successfully modeled in [30].…”

Section: Related Workmentioning

confidence: 99%

Supervised semantic relation mining from linguistically noisy text documents

Giannone

Basili

Naggar

et al. 2010

IJDAR

Self Cite

View full text Add to dashboard Cite

In this paper, we present models for mining text relations between named entities, which can deal with data highly affected by linguistic noise. Our models are made robust by: (a) the exploitation of state-of-the-art statistical algorithms such as support vector machines (SVMs) along with effective and versatile pattern mining methods, e.g. word sequence kernels; (b) the design of specific features capable of capturing long distance relationships; and (c) the use of domain prior knowledge in the form of ontological constraints, e.g. bounds on the type of relation arguments given by the semantic categories of the involved entities. This property allows for keeping small the training data required by SVMs and consequently lowering the system design costs. We empirically tested our hybrid model in the very complex domain of business intelligence, where the textual data are constituted by reports on investigations into criminal enterprises based on police interrogatory reports, electronic eavesdropping and wiretaps. The target relations are typically established between entities, as they are mentioned in these information sources. The experiments on mining such relations show that our approach with small training data C. Giannone (B) · P. Naggar CM Sistemi s.p

show abstract

Section: Related Workmentioning

confidence: 99%

Supervised semantic relation mining from linguistically noisy text documents

Giannone

Basili

Naggar

et al. 2010

IJDAR

Self Cite

View full text Add to dashboard Cite

show abstract

“…To adapt the tree kernel to medical domain, we followed the approach in (Nguyen et al, 2009) to take the syntactic structures into consideration. We also added the argument types as features to the tree kernel.…”

Section: Baseline Approachesmentioning

confidence: 99%

Medical Relation Extraction with Manifold Models

Wang¹,

Fan²

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

In this paper, we present a manifold model for medical relation extraction. Our model is built upon a medical corpus containing 80M sentences (11 gigabyte text) and designed to accurately and efficiently detect the key medical relations that can facilitate clinical decision making. Our approach integrates domain specific parsing and typing systems, and can utilize labeled as well as unlabeled examples. To provide users with more flexibility, we also take label weight into consideration. Effectiveness of our model is demonstrated both theoretically with a proof to show that the solution is a closed-form solution and experimentally with positive results in experiments.

show abstract

“…Moreover, Moschitti et al in [79] suggested the combination of constituent and dependency parse trees to represent the syntax of a sentence for relation extraction. This idea was continued to improve by augmenting the semantics concerning to entity types and lexical sequences ( [83]). Recently, Reichartz et al in [88] have proposed a novel method of using typed dependency parse trees which include labeled edges and nodes.…”

Section: Supervised Approachmentioning

confidence: 99%

“…In other words, the problem of relation extraction is formulated as a classification problem and relations of unseen entity pairs are classified by a target function which is learnt from a manually labeled training dataset. Previous study applied Support Vector Machine (SVM) ( [18], [79], [83], [87], [88]) to learn the target function from training data and used it to determine the label of the relation between novel entity pairs in the sentence. …”

Section: Supervised Approachmentioning

confidence: 99%

“…Several attempts have been made to extract information from sentences by using natural language processing (NLP) techniques. In this approach, entities are required to be organised in sentences and their syntactic and grammatic features are exploited to build a statistical extraction model by utilising a training dataset with manually labelled data ( [18], [79], [83], [87], [88]). Therefore, those approaches cannot be applied to extract information about entities which are not represented in sentences on web pages, such as lists, or tables, etc.…”

Section: Declaration By Authormentioning

confidence: 99%

See 1 more Smart Citation

Entity Extraction from Unstructured Data on the Web

Huynh¹

View full text Add to dashboard Cite

A large number of web pages contain information about entities in lists where the lists are represented in textual form. Textual lists contain implicit records of entities. However, the field values of such records cannot easily be separated or extracted by automatic processes. This, therefore, remains a challenging research problem in the literature. Previous studies in the literature relied mainly on probabilistic graph-based models to capture the attributes and the likely structures of implicit records in a list. However, one of the important limitations of existing methods is that the structures of the records in input lists were implicitly encoded via training data which was manually created. This thesis aims to investigate novel techniques to acquire automatically information about entities from implicit records embedded in textual lists on the web.This thesis introduces a self-supervised learning framework which exploits both existing data in a knowledge base and the structural similarity between sequences in lists to build an extraction model automatically. In the proposed framework, initial labels for candidate field values are created and assigned to generate label sequences. Then, the structure of implicit records is captured via a graphical model to assign unmatched labels and rectify mismatched labels. As a result of which, the process of entity extraction from lists can be completely unsupervised and automated without user intervention. In order to attain that outcome, we address three substantive research problems that need to be solved in this thesis.Firstly, the text segments in input lists need to be assigned labels precisely so that their statistical information is then used to build an extraction model. However, previous studies have not considered completely both the format and content of field values when performing the text segmentation and assigning labels. By viewing the problem of assigning labels for text segments as the problem of membership checking in set theory, we identify and propose a dyadic representation of semantic relations between a text segment and an attribute by using its extensional and intensional representations. We incorporate those representations to define a novel format-enhanced labelling technique to assign labels for text segments.Secondly, the labels of identical concepts with differing sequences in an input list are iii often located in similar positions but the positions of the labels may vary somewhat in different sequences. However, until this point, there has been no information extraction system designed to capture the distribution of labels in differing positions in order to enhance extraction results. To capture the positional information of labels, we are proposing a proximitybased positional model, which is combined with a sequential model to improve the quality of the label-refinement phase in our framework.Thirdly, in order to reduce dependence on the overlap between knowledge bases and input lists, we exploit structural similarity between t...

show abstract

Convolution kernels on constituent, dependency and sequential structures for relation extraction

Cited by 67 publications

References 30 publications

Supervised semantic relation mining from linguistically noisy text documents

Supervised semantic relation mining from linguistically noisy text documents

Medical Relation Extraction with Manifold Models

Entity Extraction from Unstructured Data on the Web

Contact Info

Product

Resources

About