• Corpus ID: 543240

Scientific Literature Retrieval based on Terminological Paraphrases using Predicate Argument Tuple

  title={Scientific Literature Retrieval based on Terminological Paraphrases using Predicate Argument Tuple},
  author={Sung-Pil Choi and Sa-kwang Song and Hanmin Jung and Michaela Geierhos and Sung-Hyon Myaeng},
The conceptual condensability of technical terms permits us to use them as effective queries to search scientific databases. However, authors often employ alternative expressions to represent the meanings of specific terms, in other words, Terminological Paraphrases (TPs) in the literature for certain reasons. In this paper, we propose an effective way to retrieve “de facto relevance documents” which only contain those TPs and cannot be searched by conventional models in an environment with… 

Figures and Tables from this paper

Finding hidden relevant documents buried in scientific documents by terminological paraphrases

An effective way to retrieve “de facto relevant documents” which only contain those TPs and cannot be searched by conventional models in an environment with only controlled vocabularies is proposed by adapting Predicate Argument Tuple (PAT).

Design of a Knowledge Framework for Structured Journalism Service based on Scientific Column Database

A scientific infographic service platform based on the knowledge-base is defined by offering its detailed structure, methods and characteristics, which shows a progressive future direction for science journalism service.

What Did You Mean? - Facing the Challenges of User-generated Software Requirements

This work conducts ontology-based requirement extraction and similarity retrieval based on requirement descriptions that are gathered from App marketplaces by simultaneously resolving ambiguity, vagueness, and underspecification in natural language.

Activity-Centric Architecture of Scientific Knowledge Extraction , Integration and Exploitation for R & D Trends Analyzing

This paper proposes an activity-centric architecture that has modules and activities for the extraction and exploitation of the scientific knowledge and can establish and develop many instantiated system architectures optimized for particular domains or requirements.



Analysis of Sentential Paraphrase Patterns and Errors through Predicate-Argument Tuple-based Approximate Alignment

A model for recognizing sentential paraphrases through Predicate-Argument Tuple (PAT)-based approximate alignment between two texts is proposed and error analysis revealed various paraphrase patterns not being solved by the proposed system.

The effect of textual variation on concept based information retrieval.

  • A. Aronson
  • Computer Science
    Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium
  • 1996
Experiments with a concept based information retrieval system which relies on a program called MetaMap to account for textual variation in the process of mapping biomedical text such as MEDLINE bibliographic citations to the UMLS Metathesaurus confirm that the effort expended in handling textual variation is well-spent for at least one type of concept basedInformation retrieval.

Evaluation of Stemming, Query Expansion and Manual Indexing Approaches for the Genomic Task

This paper describes the participation in TREC-2005 for the ad hoc Genomic track, in which five different stemming approaches to performing domainspecific searches within a MEDLINE subset are evaluated, and how the use of various query expansion techniques can impairs retrieval performance is illustrated.

Evaluation of query expansion using MeSH in PubMed

Experimental results suggest that query expansion using MeSH in PubMed can generally improve retrieval performance, but the improvement may not affect end PubMed users in realistic situations.

Query Expansion and MEDLINE

Evaluation of an inference network-based retrieval model

Network representations show promise as mechanisms for inferring probable relationships between documents and queries and have been used in information retrieval since at least the early 1960s.

Relevance Models in Information Retrieval

A simple statistical model for capturing the notion of topical relevance in information retrieval, called a relevance model, is developed and extensive evaluations of the relevance model approach are described on the TREC ad-hoc retrieval and cross-language tasks.

A Language Modeling Approach to Information Retrieval

This work proposes an approach to retrieval based on probabilistic language modeling and integrates document indexing and document retrieval into a single model, which significantly outperforms standard tf.idf weighting on two different collections and query sets.

Feature Forest Models for Probabilistic HPSG Parsing

The feature forest model is proposed as a solution to the problem of probabilistic modeling of complex data structures including typed feature structures, and methods for representing HPSG syntactic structures and predicate-argument structures with feature forests are described.

Simplicity is Better: Revisiting Single Kernel PPI Extraction

In-depth analyses of the kernel reveal that the keys to the improvement are the tree pruning method and consideration of tree kernel decay factors, which are able to achieve the best performance among the state-of-the-art methods.