TSE-NER: An Iterative Approach for Long-Tail Entity Extraction in Scientific Publications

Mesbah, Sepideh; Lofi, Christoph; Torre, Manuel Valle; Bozzon, Alessandro; Houben, Geert‐Jan

doi:10.1007/978-3-030-00671-6_8

Cited by 16 publications

(27 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As outlined in the previous section, a core design feature of TSE-NER is the heuristic filter step in each iteration, which is designed to filter out named entities which are most likely misrecognized (this can easily happen as the used training data is noisy due to the strong reliance on heuristics). While it was shown in [12] that this filter step indeed increases the precision of the overall approach, it does also impact the recall negatively. For example, this could happen by filtering out true positives, i.e.…”

Section: Collaborative Crowd Feedbackmentioning

confidence: 99%

“…In this section we will summarize TSE-NER, an iterative five-step low-cost approach for training NER/NET classifiers for long-tail entity types. For more detailed information on this approach, refer to [12]. The approach is summarized in the following five steps:…”

Section: Tse-ner: An Iterative Approach For Long-tail Entity Extractionmentioning

confidence: 99%

“…Interested readers can refer to [12] for detailed explanation. As those heuristics are rather basic in their nature, we discuss in the next section if filtering can be supported by human feedback.…”

Section: Heuristic Filteringmentioning

confidence: 99%

“…Recently, TSE-NER [12] was presented, an iterative approach for entity extraction in scientific publications. The approach starts with a small seed set of known entity instances; for each type it is sufficient to have one or two domain experts denote between 5 to 50 known entities.…”

Section: Introductionmentioning

confidence: 99%

“…These sets are then heuristically expanded and annotated to generate training data to train a new traditional NER classifier, and heuristically filtered to remove likely false positives to create the entity set for the next iteration. As results of experiments in [12] have shown, this approach is hampered by the simplicity and unreliability of the heuristics used for expanding, but especially by those used for filtering the current iteration's entity set. Nonetheless, the approach promises a lot of potential if these heuristics can be improved by bringing intelligently human judgment in the loop.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Coner: A Collaborative Approach for Long-Tail Named Entity Recognition in Scientific Publications

Vliegenthart

Mesbah

Lofi

et al. 2019

Digital Libraries for Open Knowledge

Self Cite

View full text Add to dashboard Cite

Named Entity Recognition (NER) for rare long-tail entities as e.g., often found in domain-specific scientific publications is a challenging task, as typically the extensive training data and test data for finetuning NER algorithms is lacking. Recent approaches presented promising solutions relying on training NER algorithms in an iterative weaklysupervised fashion, thus limiting human interaction to only providing a small set of seed terms. Such approaches heavily rely on heuristics in order to cope with the limited training data size. As these heuristics are prone to failure, the overall achievable performance is limited. In this paper, we therefore introduce a collaborative approach which incrementally incorporates human feedback on the relevance of extracted entities into the training cycle of such iterative NER algorithms. This approach, called Coner, allows to still train new domain specific rare long-tail NER extractors with low costs, but with ever increasing performance while the algorithm is actively used in an application.

show abstract

Section: Collaborative Crowd Feedbackmentioning

confidence: 99%

Section: Tse-ner: An Iterative Approach For Long-tail Entity Extractionmentioning

confidence: 99%

Section: Heuristic Filteringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Coner: A Collaborative Approach for Long-Tail Named Entity Recognition in Scientific Publications

Vliegenthart

Mesbah

Lofi

et al. 2019

Digital Libraries for Open Knowledge

Self Cite

View full text Add to dashboard Cite

show abstract

Concept Focus: Semantic Meta-Data for Describing MOOC Content

Mesbah

Chen

Torre

et al. 2018

Lifelong Technology-Enhanced Learning

Self Cite

View full text Add to dashboard Cite

MOOCs promised to herald a new age of open education. However, efficient access to MOOC content is still hard, thus unnecessarily complicating many use cases like efficient re-use of material, or tailored access for lifelong learning scenarios. One of the reasons for this lack of accessibility is the shortage of meaningful semantic metadata describing MOOC content and the resulting learning experience. In this paper, we explore Concept Focus, a new type of meta-data for describing a perceptual facet of modern video-based MOOCs, capturing how focused a learning resource is topic-wise, which is often an indicator of clarity and understandability. We provide the theoretical foundations of Concept Focus and outline a methodical workflow of how to automatically compute it for MOOC lectures. Furthermore, we show that the learners' consumption behavior is correlated with a MOOC lecture's Concept Focus, thus underlining that this type of meta-data is indeed relevant for user-centric querying, personalizing or even designing the MOOC experience. For showing this, we performed an extensive study with real-life MOOCs and 12,849 learners over the duration of three months.

show abstract

A review on method entities in the academic literature: extraction, evaluation, and application

Wang

Zhang

2022

Scientometrics

View full text Add to dashboard Cite

In scientific research, the method is an indispensable means to solve scientific problems and a critical research object. With the advancement of sciences, many scientific methods are being proposed, modified, and used in academic literature. The authors describe details of the method in the abstract and body text, and key entities in academic literature reflecting names of the method are called method entities. Exploring diverse method entities in a tremendous amount of academic literature helps scholars understand existing methods, select the appropriate method for research tasks, and propose new methods.Furthermore, the evolution of method entities can reveal the development of a discipline and facilitate knowledge discovery. Therefore, this article offers a systematic review of methodological and empirical works focusing on extracting method entities from full-text academic literature and efforts to build knowledge services using these extracted method entities. Definitions of key concepts involved in this review were first proposed. Based on these definitions, we systematically reviewed the approaches and indicators to extract and evaluate method entities, with a strong focus on the pros and cons of each approach. We also surveyed how extracted method entities are used to build new applications. Finally, limitations in existing works as well as potential next steps were discussed.

show abstract

TSE-NER: An Iterative Approach for Long-Tail Entity Extraction in Scientific Publications

Cited by 16 publications

References 23 publications

Coner: A Collaborative Approach for Long-Tail Named Entity Recognition in Scientific Publications

Coner: A Collaborative Approach for Long-Tail Named Entity Recognition in Scientific Publications

Concept Focus: Semantic Meta-Data for Describing MOOC Content

A review on method entities in the academic literature: extraction, evaluation, and application

Contact Info

Product

Resources

About