Knowledge-Guided Paraphrase Identification

Wang, Haoyu; Ma, Fenglong; Wang, Yaqing; Gao, Jing

doi:10.18653/v1/2021.findings-emnlp.72

Cited by 8 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other datasets mentioned in the reviewed papers include the 2012 corpus annotated for events, temporal expressions and temporal relations [55], and the de-identification datasets of i2b2 2014 [56]. Three studies utilized data from the 2019 n2c2/OHNLP track on clinical semantic textual similarity [57, 58, 59], and one study tackled the 2022 n2c2 challenge, focusing on medication extraction and event/context classification [60].…”

Section: Resultsmentioning

confidence: 99%

Large Language Models to process, analyze, and synthesize biomedical texts – a scoping review

Doneva,

Qin,

Sick

et al. 2024

Preprint

View full text Add to dashboard Cite

The advent of large language models (LLMs) such as BERT and, more recently, GPT, is transforming our approach of analyzing and understanding biomedical texts. To stay informed about the latest advancements in this area, there is a need for up-to-date summaries on the impact of LLM on Natural Language Processing (NLP) in the biomedical field. Thus, this scoping review aims to provide a detailed overview of the current state of biomedical NLP research and its applications, with a special focus on the evolving role of LLMs. We conducted a systematic search of PubMed, EMBASE, and Google Scholar for studies and conference proceedings published from 2017 to December 19, 2023, that develop or utilize LLMs for NLP tasks in biomedicine. From 13,823 references, we selected 199 publications and conference proceedings for our review. LLMs are being applied to a wide array of tasks in the biomedical field, including knowledge management, text mining, drug discovery, and evidence synthesis. Prominent among these tasks are text classification, relation extraction, and named entity recognition. Although BERT-based models remain prevalent, the use of GPT-based models has substantially increased since 2023.

show abstract

Section: Resultsmentioning

confidence: 99%

Large Language Models to process, analyze, and synthesize biomedical texts – a scoping review

Doneva,

Qin,

Sick

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Then, question-answering-based models are built to treat attributes as questions and values as answers [57,61,69]. Multimodal fusion utilizing product images as visual features are learned to integrate visual semantics for products [10,20,36,41,42,60,62,80]. Some studies formulate AVE as a multi-label classification task to extract multiple aspects for the products [5,11,21].…”

Section: Related Work 21 Attribute Value Extractionmentioning

confidence: 99%

“…<color: red>) from e-Commerce product descriptions, which provides a better search and recommendation experience for customers. Existing studies on AVE mainly focus on supervised-learning models such as sequence labeling [29,73], extractive question answering [57,61] and multi-modal learning [20,41,60,62] models. These supervised learning models are trained to only predict seen attribute value pairs.…”

Section: Introductionmentioning

confidence: 99%

Multi-Label Zero-Shot Product Attribute-Value Extraction

Gong,

Eldardiry

2024

Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

E-commerce platforms should provide detailed product descriptions (attribute values) for effective product search and recommendation. However, attribute value information is typically not available for new products. To predict unseen attribute values, large quantities of labeled training data are needed to train a traditional supervised learning model. Typically, it is difficult, time-consuming, and costly to manually label large quantities of new product profiles. In this paper, we propose a novel method to efficiently and effectively extract unseen attribute values from new products in the absence of labeled data (zero-shot setting). We propose HyperPAVE, a multilabel zero-shot attribute value extraction model that leverages inductive inference in heterogeneous hypergraphs. In particular, our proposed technique constructs heterogeneous hypergraphs to capture complex higher-order relations (i.e. user behavior information) to learn more accurate feature representations for graph nodes. Furthermore, our proposed HyperPAVE model uses an inductive link prediction mechanism to infer future connections between unseen nodes. This enables HyperPAVE to identify new attribute values without the need for labeled training data. We conduct extensive experiments with ablation studies on different categories of the MAVE dataset. The results demonstrate that our proposed HyperPAVE model significantly outperforms existing classificationbased, generation-based large language models for attribute value extraction in the zero-shot setting. CCS CONCEPTS• Computing methodologies → Information extraction.

show abstract

“…External knowledge graph integration . Recently, several efforts have attempted to leverage the KG for downstream tasks such as recommendation ( Sun et al , 2018 ; Wang et al , 2019a , b ), information extraction ( Liang et al , 2020 ; Wang et al , 2018 ) and drug interaction prediction ( Celebi et al , 2019 ; Karim et al , 2019 ; Lin et al , 2020 ). For drug interaction prediction, Takeda et al (2017) integrate the pharmacokinetic (PK) or pharmacodynamic (PD) side-effect when predicting drug interaction and Li et al (2015) develop a Bayesian network to combine molecular similarity and drug side-effect similarity to predict the drug effect.…”

Section: Related Workmentioning

confidence: 99%

SumGNN: multi-typed drug interaction prediction via efficient knowledge graph summarization

Huang

Zhang

et al. 2021

Bioinformatics

View full text Add to dashboard Cite

Motivation Thanks to the increasing availability of drug-drug interactions (DDI) datasets and large biomedical knowledge graphs (KGs), accurate detection of adverse DDI using machine learning models becomes possible. However, it remains largely an open problem how to effectively utilize large and noisy biomedical KG for DDI detection. Due to its sheer size and amount of noise in KGs, it is often less beneficial to directly integrate KGs with other smaller but higher quality data (e.g., experimental data). Most of existing approaches ignore KGs altogether. Some tries to directly integrate KGs with other data via graph neural networks with limited success. Furthermore most previous works focus on binary DDI prediction whereas the multi-typed DDI pharmacological effect prediction is more meaningful but harder task. Results To fill the gaps, we propose a new method SumGNN: knowledge summarization graph neural network, which is enabled by a subgraph extraction module that can efficiently anchor on relevant subgraphs from a KG, a self-attention based subgraph summarization scheme to generate reasoning path within the subgraph, and a multi-channel knowledge and data integration module that utilizes massive external biomedical knowledge for significantly improved multi-typed DDI predictions. SumGNN outperforms the best baseline by up to 5.54%, and performance gain is particularly significant in low data relation types. In addition, SumGNN provides interpretable prediction via the generated reasoning paths for each prediction. Availability The code is available in the supplementary. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Knowledge-Guided Paraphrase Identification

Cited by 8 publications

References 19 publications

Large Language Models to process, analyze, and synthesize biomedical texts – a scoping review

Large Language Models to process, analyze, and synthesize biomedical texts – a scoping review

Multi-Label Zero-Shot Product Attribute-Value Extraction

SumGNN: multi-typed drug interaction prediction via efficient knowledge graph summarization

Contact Info

Product

Resources

About