paper-with-me

홈 › Papers

Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?

2023-11-15 · Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

Knowledge graphs (KGs) consist of links that describe relationships between entities. Due to the difficulty of manually enumerating all relationships between entities, automatically completing them is essential for KGs. Knowledge Graph Completion (KGC) is a task that infers unseen relationships between entities in a KG. Traditional embedding-based KGC methods, such as RESCAL, TransE, DistMult, ComplEx, RotatE, HAKE, HousE, etc., infer missing links using only the knowledge from training data. In contrast, the recent Pre-trained Language Model (PLM)-based KGC utilizes knowledge obtained during pre-training. Therefore, PLM-based KGC can estimate missing links between entities by reusing memorized knowledge from pre-training without inference. This approach is problematic because building KGC models aims to infer unseen links between entities. However, conventional evaluations in KGC do not consider inference and memorization abilities separately. Thus, a PLM-based KGC method, which achieves high performance in current KGC evaluations, may be ineffective in practical applications. To address this issue, we analyze whether PLM-based KGC methods make inferences or merely access memorized knowledge. For this purpose, we propose a method for constructing synthetic datasets specified in this analysis and conclude that PLMs acquire the inference abilities required for KGC through pre-training, even though the performance improvements mostly come from textual information of entities and relations.

📄 PDF Abstract BibTeX arXiv:2311.09109

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graph CompletionKnowledge GraphsLanguage ModelingLanguage ModellingMemorization

Methods 이 논문이 사용한 방법론

Self-Adversarial Negative Sampling 설명 없음
RESCAL RESCAL
RotatE RotatE is a method for generating graph embeddings which is able to model and infer various relation patterns including: symmetry/antisymmetry, inversion, and composition.…
TransE TransE is an energy-based model that produces knowledge base embeddings. It models relationships by interpreting them as translations operating on the low-dimensional…

Similar Papers 제목 키워드 기반

Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data

2020-10-09 · EMNLP (insights) 2020 11 · William Huang, Haokun Liu, Samuel R. Bowman

A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdworkers to create an evaluation task---whil…

counterfactualNatural Language InferenceNatural Language UnderstandingReading Comprehension

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study

2026-06-19 · Alfarizy Alfarizy, Hung Truong Thanh Nguyen, René Richard, Roozbeh Razavi-Far 외 arxiv

Mixture-of-Experts (MoE) language models are often described as ideal for resource-constrained inference. Each token activates only a small subset of experts, so the per-token compute cost, in floating-point operations (…

Real-Time Violence Detection Using CNN-LSTM

2021-07-15 · Mann Patel

Violence rates however have been brought down about 57% during the span of the past 4 decades yet it doesn't change the way that the demonstration of violence actually happens, unseen by the law. Violence can be mass con…

Are Language Models Actually Useful for Time Series Forecasting?

2024-06-22 · Mingtian Tan, Mike A. Merrill, Vinayak Gupta, Tim Althoff 외

Large language models (LLMs) are being applied to time series forecasting. But are language models actually useful for time series? In a series of ablation studies on three recent and popular LLM-based time series foreca…

Time SeriesTime Series Forecasting

Comment on "Modeling rapid language learning by distilling Bayesian priors into artificial neural networks"

2026-08-13 · Orr Well, Idan Tarshish, Nur Lan, Roni Katzir arxiv

McCoy & Griffiths (2025, henceforth M&G) suggest that a Bayesian prior can be distilled into Artificial Neural Networks (ANNs) through Model-Agnostic Meta-Learning (MAML, Finn et al., 2017). They support this empirically…