في السنوات الأخيرة، تم تطبيق نماذج قليلة بالرصاص بنجاح في مجموعة متنوعة من مهام NLP.هان وآخرون.(2018) أدخل إطارا متعدد الطلقات التعلم لتصنيف العلاقة، ومنذ ذلك الحين، تجاوزت عدة نماذج الأداء البشري في هذه المهمة، مما يؤدي إلى الانطباع بأن التصنيف القليل من الطلقات يتم حلها.في هذه الورقة، نلقي نظرة أعمق على فعالية نماذج التصنيف القليلة القليلة في إعداد استخراج العلاقات الأكثر شيوعا، وإظهار أن مقاييس التقييم القليلة النموذجية تحجب تقلب واسع في الأداء عبر العلاقات.على وجه الخصوص، نجد أن نماذج تصنيف العلاقات بين الفنون القليلة تعتمد بشكل مفرط على معلومات نوع الكيان، واقتراح تعديلات على روتين التدريب لتشجيع النماذج على التمييز بشكل أفضل بين العلاقات التي تنطوي على أنواع كيانات مماثلة.
In recent years, few-shot models have been applied successfully to a variety of NLP tasks. Han et al. (2018) introduced a few-shot learning framework for relation classification, and since then, several models have surpassed human performance on this task, leading to the impression that few-shot relation classification is solved. In this paper we take a deeper look at the efficacy of strong few-shot classification models in the more common relation extraction setting, and show that typical few-shot evaluation metrics obscure a wide variability in performance across relations. In particular, we find that state of the art few-shot relation classification models overly rely on entity type information, and propose modifications to the training routine to encourage models to better discriminate between relations involving similar entity types.
References used
https://aclanthology.org/
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tun
Most prior work on task-oriented dialogue systems is restricted to supporting domain APIs. However, users may have requests that are out of the scope of these APIs. This work focuses on identifying such user requests. Existing methods for this task m
Most recent studies for relation extraction (RE) leverage the dependency tree of the input sentence to incorporate syntax-driven contextual information to improve model performance, with little attention paid to the limitation where high-quality depe
Few-shot relation extraction (FSRE) focuses on recognizing novel relations by learning with merely a handful of annotated instances. Meta-learning has been widely adopted for such a task, which trains on randomly generated few-shot tasks to learn gen
Argument pair extraction (APE) aims to extract interactive argument pairs from two passages of a discussion. Previous work studied this task in the context of peer review and rebuttal, and decomposed it into a sequence labeling task and a sentence re