Relation extraction: advancements through deep learning and entity-related features

Zhao, Yuchao; Yuan, Xiangbo; Yuan, Yunhao; Deng, Shaoxiong; Quan, Jun

doi:10.1007/s13278-023-01095-8

Cited by 7 publications

(2 citation statements)

References 30 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This gives them strong generalization ability, adaptability, and scalability. However, training or fine-tuning them for downstream applications such as RE requires labeled data (Zhao et al, 2023 ). Since we have limited labeled data, supervised methods such as those mentioned above cannot be applied in our study.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised literature mining approaches for extracting relationships pertaining to habitats and reproductive conditions of plant species

Gabud,

Lapitan,

Mariano

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

IntroductionFine-grained, descriptive information on habitats and reproductive conditions of plant species are crucial in forest restoration and rehabilitation efforts. Precise timing of fruit collection and knowledge of species' habitat preferences and reproductive status are necessary especially for tropical plant species that have short-lived recalcitrant seeds, and those that exhibit complex reproductive patterns, e.g., species with supra-annual mass flowering events that may occur in irregular intervals. Understanding plant regeneration in the way of planning for effective reforestation can be aided by providing access to structured information, e.g., in knowledge bases, that spans years if not decades as well as covering a wide range of geographic locations. The content of such a resource can be enriched with literature-derived information on species' time-sensitive reproductive conditions and location-specific habitats.MethodsWe sought to develop unsupervised approaches to extract relationships pertaining to habitats and their locations, and reproductive conditions of plant species and corresponding temporal information. Firstly, we handcrafted rules for a traditional rule-based pattern matching approach. We then developed a relation extraction approach building upon transformer models, i.e., the Text-to-Text Transfer Transformer (T5), casting the relation extraction problem as a question answering and natural language inference task. We then propose a novel unsupervised hybrid approach that combines our rule-based and transformer-based approaches.ResultsEvaluation of our hybrid approach on an annotated corpus of biodiversity-focused documents demonstrated an improvement of up to 15 percentage points in recall and best performance over solely rule-based and transformer-based methods with F1-scores ranging from 89.61 to 96.75% for reproductive condition - temporal expression relations, and ranging from 85.39% to 89.90% for habitat - geographic location relations. Our work shows that even without training models on any domain-specific labeled dataset, we are able to extract relationships between biodiversity concepts from literature with satisfactory performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Unsupervised literature mining approaches for extracting relationships pertaining to habitats and reproductive conditions of plant species

Gabud,

Lapitan,

Mariano

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…With the emergence of DL, models that employ neural architectures such as convolutional neural networks (CNNs) (Liu et al, 2013;dos Santos et al, 2015), recurrent neural networks (RNN) (Vu et al, 2016;Zhang and Wang, 2015), graph convolutional networks (GCN) (Zhu et al, 2019), attention-based neural networks (Wang et al, 2016;Xiao and Liu, 2016), and transformer-based language models (Vaswani et al, 2017;Le Guillarme and Thuiller, 2022) have been utilized for RE tasks. However, similar to traditional ML models, training or fine-tuning DL models for downstream applications such as RE also requires labeled data (Zhao et al, 2023).…”

Section: Related Workmentioning

confidence: 99%

A Hybrid of Rule-based and Transformer-based Approaches for Relation Extraction in Biodiversity Literature

Gabud,

Lapitan,

Mariano

et al. 2023

Proceedings of the 2nd Workshop on Pattern-Based Approaches to NLP in the Age of Deep Learning

View full text Add to dashboard Cite

Relation extraction (RE) is one of the tasks behind many relevant natural language processing (NLP) applications. Exploiting the information hidden in millions of scholarly articles by leveraging NLP, specifically RE, systems could benefit studies in specialized domains, e.g. biomedicine and biodiversity. Although deep learning (DL)-based methods have shown state-of-the-art performance in many NLP tasks including RE, DL for domain-specific RE systems has been hindered by the lack of expertlabeled datasets which are typically required to train such methods. In this paper, we take advantage of the zero-shot (i.e., not requiring any labeled data) capability of pattern-based methods for RE using a rule-based approach, combined with templates for natural language inference (NLI) transformer models. We present our hybrid method for RE that exploits the advantages of both methods, i.e., interpretability of rules and transferability of transformers. Evaluated on a corpus of biodiversity literature with annotated relations, our hybrid method demonstrated an improvement of up to 15 percentage points in recall and best performance over solely rule-based and transformer-based methods with F1-scores ranging from 89.61% to 96.75% for reproductive condition -temporal expression relations, and ranging from 85.39% to 89.90% for habitat -geographic location relations.

show abstract

Joint Entity Relation Extraction Based on LSTM via Attention Mechanism

Cao,

Shao

2023

Arab J Sci Eng

View full text Add to dashboard Cite

Relation extraction: advancements through deep learning and entity-related features

Cited by 7 publications

References 30 publications

Unsupervised literature mining approaches for extracting relationships pertaining to habitats and reproductive conditions of plant species

Unsupervised literature mining approaches for extracting relationships pertaining to habitats and reproductive conditions of plant species

A Hybrid of Rule-based and Transformer-based Approaches for Relation Extraction in Biodiversity Literature

Joint Entity Relation Extraction Based on LSTM via Attention Mechanism

Contact Info

Product

Resources

About