Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction

Sainz, Oscar; Lacalle, Oier López de; Labaka, Gorka; Barrena, Ander; Agirre, Eneko

doi:10.18653/v1/2021.emnlp-main.92

Cited by 50 publications

(64 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lu et al [ 10 ] built a few-shot learning-based classifier by limiting training samples for food recognition. Sainz et al [ 11 ] proposed a method of label verbalization and entailment for effective zero and few-shot relation extraction.…”

Section: Introductionmentioning

confidence: 99%

An Entity Relationship Extraction Model Based on BERT-BLSTM-CRF for Food Safety Domain

Zhang

Dong

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Dealing with food safety issues in time through online public opinion incidents can reduce the impact of incidents and protect human health effectively. Therefore, by the smart technology of extracting the entity relationship of public opinion events in the food field, the knowledge graph of the food safety field is constructed to discover the relationship between food safety issues. To solve the problem of multi-entity relationships in food safety incident sentences for few-shot learning, this paper adopts the pipeline-type extraction method. Entity relationship is extracted from Bidirectional Encoder Representation from Transformers (BERTs) joined Bidirectional Long Short-Term Memory (BLSTM), namely, the BERT-BLSTM network model. Based on the entity relationship types extracted from the BERT-BLSTM model and the introduction of Chinese character features, an entity pair extraction model based on the BERT-BLSTM-conditional random field (CRF) is established. In this paper, several common deep neural network models are compared with the BERT-BLSTM-CRF model with a food public opinion events dataset. Experimental results show that the precision of the entity relationship extraction model based on BERT-BLSTM-CRF is 3.29%∼23.25% higher than that of other models in the food public opinion events dataset, which verifies the validity and rationality of the model proposed in this paper.

show abstract

Section: Introductionmentioning

confidence: 99%

An Entity Relationship Extraction Model Based on BERT-BLSTM-CRF for Food Safety Domain

Zhang

Dong

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Li et al (2022) further improve this strategy by incorporating NLI with learning-to-rank, leading to a robust system for ultra-fine entity typing (Choi et al, 2018). Similar idea of leveraging NLI as indirect supervision signal is applied by Sainz et al (2021), which focuses on low-resource RE task. As discussed, the objective of RE aligns well with that of a summarization task.…”

Section: Related Workmentioning

confidence: 99%

“…The templates seek to form short summaries that describe the relations between two entities, and will be used for models' training and inference. Semantic templates are also leveraged in Sainz et al (2021), where the templates are used as hypotheses for NLI-based RE.…”

Section: Relation and Sentence Conversionmentioning

confidence: 99%

“…SURE requires manually designed templates of relations for both training and inference. To minimize manual effort and give a fair comparison to prior work, we adopt the same relation verbalization templates from Sainz et al (2021). They restrict the influence of human effort by limiting the time for creating the templates and build 2 templates in average for each relation.…”

Section: Relation and Sentence Conversionmentioning

confidence: 99%

“…It represents another challenge for RE models that rely on large-scale relation annotations to be applied in real-word applications. Existing literature finds that classification models have drastically degraded performance under low-resource scenarios (Sainz et al, 2021). Therefore, label efficiency is a vital issue when adopting prior methods in real application scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Summarization as Indirect Supervision for Relation Extraction

Lu¹,

Hsu²,

Zhou³

et al. 2022

Preprint

View full text Add to dashboard Cite

Relation extraction (RE) models have been challenged by their reliance on training data with expensive annotations. Considering that summarization tasks aim at acquiring concise expressions of synoptical information from the longer context, these tasks naturally align with the objective of RE, i.e., extracting a kind of synoptical information that describes the relation of entity mentions. We present SURE, which converts RE into a summarization formulation. SURE leads to more precise and resource-efficient RE based on indirect supervision from summarization tasks. To achieve this goal, we develop sentence and relation conversion techniques that essentially bridge the formulation of summarization and RE tasks. We also incorporate constraint decoding techniques with Trie scoring to further enhance summarization-based RE with robust inference. Experiments on three RE datasets demonstrate the effectiveness of SURE in both full-dataset and low-resource settings, showing that summarization is a promising source of indirect supervision to improve RE models.

show abstract

Serial and Parallel Recurrent Convolutional Neural Networks for Biomedical Named Entity Recognition

Yang

et al. 2019

Database Systems for Advanced Applications

View full text Add to dashboard Cite

In this study, we aim to reduce generation latency for Named Entity Recognition (NER) with Large Language Models (LLMs). The main cause of high latency in LLMs is the sequential decoding process, which autoregressively generates all labels and mentions for NER, significantly increase the sequence length. To this end, we introduce Parallel Decoding in LLM for NER (PaDeLLM-NER), a approach that integrates seamlessly into existing generative model frameworks without necessitating additional modules or architectural modifications. PaDeLLM-NER allows for the simultaneous decoding of all mentions, thereby reducing generation latency. Experiments reveal that PaDeLLM-NER significantly increases inference speed that is 1.76 to 10.22 times faster than the autoregressive approach for both English and Chinese. Simultaneously it maintains the quality of predictions as evidenced by the performance that is on par with the state-of-the-art across various datasets.* Code is available at URL masked for anonymous review.* https://huggingface.co/meta-llama/Llama-2-7b * https://huggingface.co/baichuan-inc/ Baichuan2-7B-Base

show abstract

Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction

Cited by 50 publications

References 26 publications

An Entity Relationship Extraction Model Based on BERT-BLSTM-CRF for Food Safety Domain

An Entity Relationship Extraction Model Based on BERT-BLSTM-CRF for Food Safety Domain

Summarization as Indirect Supervision for Relation Extraction

Serial and Parallel Recurrent Convolutional Neural Networks for Biomedical Named Entity Recognition

Contact Info

Product

Resources

About