Neural ParsCit: a deep learning-based reference string parser

Prasad, Animesh; Kaur, Manpreet; Kan, Min-Yen

doi:10.1007/s00799-018-0242-1

Cited by 47 publications

(36 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We get 332,793 papers having 1,508,560 citation links. For extraction of citation context, we used Parscit (Prasad et al, 2018). For the papers for which abstract was not available in the DBLP dataset, we use the one extracted by Parscit.…”

Section: Methodsmentioning

confidence: 99%

Scalable, Semi-Supervised Extraction of Structured Information from Scientific Literature

Agrawal¹,

Mittal²,

Pudi³

2019

Proceedings of the Workshop on Extracting Structured Knowledge From Scientific Publications

View full text Add to dashboard Cite

As scientific communities grow and evolve, there is a high demand for improved methods for finding relevant papers, comparing papers on similar topics and studying trends in the research community. All these tasks involve the common problem of extracting structured information from scientific articles. In this paper, we propose a novel, scalable, semi-supervised method for extracting relevant structured information from the vast available raw scientific literature. We extract the fundamental concepts of aim, method and result from scientific articles and use them to construct a knowledge graph. Our algorithm makes use of domain-based word embedding and the bootstrap framework. Our experiments show the domain independence of our algorithm and that our system achieves precision and recall comparable to the state of the art. We also show the research trends of two distinct communities-computational linguistics and computer vision.

show abstract

Section: Methodsmentioning

confidence: 99%

Scalable, Semi-Supervised Extraction of Structured Information from Scientific Literature

Agrawal¹,

Mittal²,

Pudi³

2019

Proceedings of the Workshop on Extracting Structured Knowledge From Scientific Publications

View full text Add to dashboard Cite

show abstract

“…The intuition behind an entity-based approach is that there exists a reference publication for a named entity mentioned in the citation context. For instance, this can be a data set ("CiteSeer x [37]"), a tool ("Neural ParsCit [23]"), or a (scientific) concept ("Semantic Web [37]"). In a more loose sense this can also include publications being referred to as examples ("approaches to contextaware citation recommendation [5-7,10-12,14,16]").…”

Section: Entity-based Recommendationmentioning

confidence: 99%

Semantic Modelling of Citation Contexts for Context-Aware Citation Recommendation

Saier

Färber

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

New research is being published at a rate, at which it is infeasible for many scholars to read and assess everything possibly relevant to their work. In pursuit of a remedy, efforts towards automated processing of publications, like semantic modelling of papers to facilitate their digital handling, and the development of information filtering systems, are an active area of research. In this paper, we investigate the benefits of semantically modelling citation contexts for the purpose of citation recommendation. For this, we develop semantic models of citation contexts based on entities and claim structures. To assess the effectiveness and conceptual soundness of our models, we perform a large offline evaluation on several data sets and furthermore conduct a user study. Our findings show that the models can outperform a non-semantic baseline model and do, indeed, capture the kind of information they're conceptualized for.

show abstract

“…This deficiency can be overcome with the help of Deep Neural Networks which are considered to be more effective in obtaining an accurate and generalized representation of the data. Prasad et al [16] exploited this approach by employing a Long Short Term Memory (LSTM) neural network model to represent tokens. Afterward, CRF model was trained on the extracted features, where this method showed strong performance over manually defined features.…”

Section: Reference Segmentationmentioning

confidence: 99%

“…Several reasons, among which literature search and recommendation, necessitates making these references available and linked to their citations in a network. Therefore, different techniques have been developed to automatically detect, extract and segment these references [13,16,19].…”

Section: Introductionmentioning

confidence: 99%

“…More specifically, references are assumed to appear in one section, while each reference string has a unique title, a unique page range and a unique source. Also, Neural Networks are also employed to segment reference strings [16], by replacing the words with their numerical representation as an input of the CRF model. Considering the correlation between the two steps, the result of segmentation highly depends on the result of the extraction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An End-to-End Approach for Extracting and Segmenting High-Variance References from PDF Documents

Boukhers

Ambhore

Staab

2019

2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)

View full text Add to dashboard Cite

This paper addresses the problem of extracting and segmenting references from PDF documents. The novelty of the presented approach lies in its capability to discover highly varying references mainly in terms of content, length and location in the document. Unlike existing works, the proposed method does not follow the classical pipeline that consists of sequential phases. It rather learns the different characteristics of references to be used in a coherent scheme that reduces the error accumulation by following a probabilistic approach. Contrary to conventional references, mentioning the sources of information in some publications, such as those of social science, is not subject to the same specifications such as being located in a unique reference section. Therefore, the proposed method aims to extract references of highly varying reference characteristics by relaxing the restrictions of existing methods. Additionally, we present in this paper a new challenging dataset of annotated references in German social science publications. The main purpose of this work is to serve the indexation of missing references by extracting them from challenging publications such as those of German social science. The effectiveness of the presented methods in terms of both extraction and segmentation is evaluated on different datasets, including the German social science set.

show abstract

Neural ParsCit: a deep learning-based reference string parser

Cited by 47 publications

References 17 publications

Scalable, Semi-Supervised Extraction of Structured Information from Scientific Literature

Scalable, Semi-Supervised Extraction of Structured Information from Scientific Literature

Semantic Modelling of Citation Contexts for Context-Aware Citation Recommendation

An End-to-End Approach for Extracting and Segmenting High-Variance References from PDF Documents

Contact Info

Product

Resources

About