Few-Shot, No Problem: Descriptive Continual Relation Extraction

Authors: Nguyen Xuan Thanh, Anh Duc Le, Quyen Tran, Thanh-Thien Le, Linh Ngo Van, Thien Huu Nguyen

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on multiple datasets demonstrate that our method significantly advances the state-of-the-art by maintaining robust performance across sequential tasks, effectively addressing catastrophic forgetting.
Researcher Affiliation Collaboration 1Oraichain Labs, 2Hanoi University of Science and Technology, 3Vin AI Research, 4University of Oregon
Pseudocode Yes Algorithm 1 outlines the end-to-end training process at each task T j, with Φj 1 denoting the model after training on the previous j 1 tasks. In line with memory-based continual learning methods, we maintain a memory buffer Mj 1 that stores a few representative samples from all previous tasks T 1, . . . , T j 1, along with a relation description set Ej 1 that holds the descriptions of all previously encountered relations.
Open Source Code No The paper does not contain any explicit statement about providing access to source code or a link to a code repository.
Open Datasets Yes We conduct experiments using two pre-trained language models, BERT (Devlin et al. 2019) and LLM2Vec (Behnam Ghader et al. 2024), on two widely used benchmark datasets for Relation Extraction: Few Rel (Han et al. 2018) and TACRED (Zhang et al. 2017).
Dataset Splits Yes In Few-Shot Continual Relation Extraction (FCRE), a model must continuously assimilate new knowledge from a sequential series of tasks. For each t-th task, the model undergoes training on the dataset Dt = {(xt i, yt i)}N K i=1 . Here, N represents the number of relations in the task Rt, and K denotes the limited number of samples per relation, reflecting the few-shot learning scenario. This type of task setup is referred to as N-way-K-shot (Chen, Wu, and Shi 2023a).
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running the experiments.
Software Dependencies No The paper mentions using BERT and LLM2Vec as pre-trained language models but does not provide specific version numbers for any software dependencies or libraries used in their implementation.
Experiment Setup Yes The soft prompt phrase length is set to 3 tokens, meaning n0, n1, n2 and n3 correspond to the values of 3, 6, 9, and 12, respectively.