DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection
원문 초록
While transformers demonstrate impressive performance on many knowledge intensive (KI) tasks, their ability to serve as implicit knowledge bases (KBs) remains limited, as shown on several slot-filling, question-answering (QA), fact verification, and entity-linking tasks. In this paper, we implement an efficient, data-programming technique that enriches training data with KB-derived context and improves transformer utilization of encoded knowledge when fine-tuning for a particular QA task, namely answer sentence selection (AS2). Our method outperforms state of the art transformer approach on WikiQA and TrecQA, two widely studied AS2 benchmarks, increasing by 2.0% p@1, 1.3% MAP, 1.1% MRR, and 4.4% p@1, 0.9% MAP, 2.4% MRR, respectively. To demonstrate our improvements in an industry setting, we additionally evaluate our approach on a proprietary dataset of Alexa QA pairs, and show increase of 2.3% F1 and 2.0% MAP. We additionally find that these improvements remain even when KB context is omitted at inference time, allowing for the use of our models within existing transformer workflows without additional latency or deployment costs.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Semantic similarity estimation for domain specific data using BERT and other techniques
Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering
MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering
StressTest: Can YOUR Speech LM Handle the Stress?
NegVQA: Can Vision Language Models Understand Negation?
토론
이 논문과 연결된 포럼 글이 아직 없습니다.