skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models
The field of relation extraction (RE) is experiencing a notable shift towards generative relation extraction (GRE), leveraging the capabilities of large language models (LLMs). However, we discovered that traditional relation extraction (RE) metrics like precision and recall fall short in evaluating GRE methods. This shortfall arises because these metrics rely on exact matching with human-annotated reference relations, while GRE methods often produce diverse and semantically accurate relations that differ from the references. To fill this gap, we introduce GENRES for a multidimensional assessment in terms of the topic similarity, uniqueness, granularity, factualness, and completeness of the GRE results. With GENRES, we empirically identified that (1) precision/recall fails to justify the performance of GRE methods; (2) human-annotated referential relations can be incomplete; (3) prompting LLMs with a fixed set of relations or entities can cause hallucinations. Next, we conducted a human evaluation of GRE methods that shows GENRES is consistent with human preferences for RE quality. Last, we made a comprehensive evaluation of fourteen leading LLMs using GENRES across document, bag, and sentence level RE datasets, respectively, to set the benchmark for future research in GRE.  more » « less
Award ID(s):
1956151
PAR ID:
10541808
Author(s) / Creator(s):
; ; ; ;
Editor(s):
Duh, Kevin; G'omez-Adorno, Helena; Bethard, Steven
Publisher / Repository:
Association for Computational Linguistics
Date Published:
Edition / Version:
1
Page Range / eLocation ID:
2820 to 2837
Subject(s) / Keyword(s):
RE Evaluation Generative Relation Extraction Large Language Models
Format(s):
Medium: X
Location:
Mexico City, Mexico
Sponsoring Org:
National Science Foundation
More Like this
  1. (, Springer)
    Proc. 2023 European Conf. on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (Ed.)
    Automated relation extraction without extensive human-annotated data is a crucial yet challenging task in text mining. Existing studies typically use lexical patterns to label a small set of high-precision relation triples and then employ distributional methods to enhance detection recall. This precision-first approach works well for common relation types but struggles with unconventional and infrequent ones. In this work, we propose a recall-first approach that first leverages high-recall patterns (e.g., a per:siblings relation normally requires both the head and tail entities in the person type) to provide initial candidate relation triples with weak labels and then clusters these candidate relation triples in a latent spherical space to extract high-quality weak supervisions. Specifically, we present a novel framework, RCLUS, where each relation triple is represented by its head/tail entity type and the shortest dependency path between the entity mentions. RCLUS first applies high-recall patterns to narrow down each relation type’s candidate space. Then, it embeds candidate relation triples in a latent space and conducts spherical clustering to further filter out noisy candidates and identify high-quality weakly-labeled triples. Finally, RCLUS leverages the above-obtained triples to prompt-tune a pre-trained language model and utilizes it for improved extraction coverage. We conduct extensive experiments on three public datasets and demonstrate that RCLUS outperforms the weakly-supervised baselines by a large margin and achieves generally better performance than fully-supervised methods in low-resource settings. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, Bioengineering)
    This work introduces TrialSieve, a novel framework for biomedical information extraction that enhances clinical meta-analysis and drug repurposing. By extending traditional PICO (Patient, Intervention, Comparison, Outcome) methodologies, TrialSieve incorporates hierarchical, treatment group-based graphs, enabling more comprehensive and quantitative comparisons of clinical outcomes. TrialSieve was used to annotate 1609 PubMed abstracts, 170,557 annotations, and 52,638 final spans, incorporating 20 unique annotation categories that capture a diverse range of biomedical entities relevant to systematic reviews and meta-analyses. The performance (accuracy, precision, recall, F1-score) of four natural-language processing (NLP) models (BioLinkBERT, BioBERT, KRISSBERT, PubMedBERT) and the large language model (LLM), GPT-4o, was evaluated using the human-annotated TrialSieve dataset. BioLinkBERT had the best accuracy (0.875) and recall (0.679) for biomedical entity labeling, whereas PubMedBERT had the best precision (0.614) and F1-score (0.639). Error analysis showed that NLP models trained on noisy, human-annotated data can match or, in most cases, surpass human performance. This finding highlights the feasibility of fully automating biomedical information extraction, even when relying on imperfectly annotated datasets. An annotator user study (n = 39) revealed significant (p < 0.05) gains in efficiency and human annotation accuracy with the unique TrialSieve tree-based annotation approach. In summary, TrialSieve provides a foundation to improve automated biomedical information extraction for frontend clinical research. 
    more » « less
  3. ; ; ; ; ; ; ; ; (, Journal of the American Medical Informatics Association)
    Abstract ObjectiveSNOMED CT provides a standardized terminology for clinical concepts, allowing cohort queries over heterogeneous clinical data including Electronic Health Records (EHRs). While it is intuitive that missing and inaccurate subtype (or is-a) relations in SNOMED CT reduce the recall and precision of cohort queries, the extent of these impacts has not been formally assessed. This study fills this gap by developing quantitative metrics to measure these impacts and performing statistical analysis on their significance. Material and MethodsWe used the Optum de-identified COVID-19 Electronic Health Record dataset. We defined micro-averaged and macro-averaged recall and precision metrics to assess the impact of missing and inaccurate is-a relations on cohort queries. Both practical and simulated analyses were performed. Practical analyses involved 407 missing and 48 inaccurate is-a relations confirmed by domain experts, with statistical testing using Wilcoxon signed-rank tests. Simulated analyses used two random sets of 400 is-a relations to simulate missing and inaccurate is-a relations. ResultsWilcoxon signed-rank tests from both practical and simulated analyses (P-values < .001) showed that missing is-a relations significantly reduced the micro- and macro-averaged recall, and inaccurate is-a relations significantly reduced the micro- and macro-averaged precision. DiscussionThe introduced impact metrics can assist SNOMED CT maintainers in prioritizing critical hierarchical defects for quality enhancement. These metrics are generally applicable for assessing the quality impact of a terminology’s subtype hierarchy on its cohort query applications. ConclusionOur results indicate a significant impact of missing and inaccurate is-a relations in SNOMED CT on the recall and precision of cohort queries. Our work highlights the importance of high-quality terminology hierarchy for cohort queries over EHR data and provides valuable insights for prioritizing quality improvements of SNOMED CT's hierarchy. 
    more » « less
  4. ; ; ; ; ; ; ; (, Digital Discovery)
    Accurate and comprehensive material databases extracted from research papers are crucial for ma- terials science and engineering, but their development requires significant human effort. With large language models (LLMs) transforming the way humans interact with text, LLMs provide an oppor- tunity to revolutionize data extraction. In this study, we demonstrate a simple and efficient method for extracting materials data from full-text research papers leveraging the capabilities of LLMs com- bined with human supervision. This approach is particularly suitable for mid-sized databases and requires minimal to no coding or prior knowledge about the extracted property. It offers high recall and nearly perfect precision in the resulting database. The method is easily adaptable to new and superior language models, ensuring continued utility. We show this by evaluating and comparing its performance on GPT-3 and GPT-3.5/4 (which underlie ChatGPT), as well as free alternatives such as BART and DeBERTaV3. We provide a detailed analysis of the method’s performance in extracting sentences containing bulk modulus data, achieving up to 90% precision at 96% recall, depending on the amount of human effort involved. We further demonstrate the method’s broader effectiveness by developing a database of critical cooling rates for metallic glasses over twice the size of previous human curated databases. 
    more » « less
  5. ; ; (, Interspeech)
    Training emotion recognition models has relied heavily on human annotated data, which present diversity, quality, and cost challenges. In this paper, we explore the potential of Large Language Models (LLMs), specifically GPT-4, in automating or assisting emotion annotation. We compare GPT-4 with supervised models and/or humans in three aspects: agreement with human annotations, alignment with human perception, and impact on model training. We find that common metrics that use aggregated human annotations as ground truth can underestimate GPT-4's performance, and our human evaluation experiment reveals a consistent preference for GPT-4 annotations over humans across multiple datasets and evaluators. Further, we investigate the impact of using GPT-4 as an annotation filtering process to improve model training. Together, our findings highlight the great potential of LLMs in emotion annotation tasks and underscore the need for refined evaluation methodologies. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email