Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction
Mapre: نهج رسم خرائط فعال للدلية لاستخراج علاقة الموارد المنخفضة
298
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أظهرت نماذج استخراج العلاقات العصبية نتائج واعدة في السنوات الأخيرة؛ومع ذلك، فإن أداء النموذج يسقط بشكل كبير منحت فقط بعض عينات التدريب فقط.تعمل الأعمال الحديثة التي تحاول الاستفادة من التقدم في سلطة قليلة التعلم لحل مشكلة الموارد المنخفضة، حيث تقوم بتدريب نماذج الملصقات الملائمة لمقارنة أوجه التشابه الدلالي بشكل مباشر بين جمل السياق في مساحة التضمين.ومع ذلك، فإن المعلومات التي تدرك الملصقات، أي علبة العلاقة التي تحتوي على المعرفة الدلالية المتعلقة بالعلاقة نفسها، مهملة في كثير من الأحيان للتنبؤ.في هذا العمل، نقترح إطارا للنظر في معلومات رسم الخرائط الدلالية الملمع والملصقات على حد سواء لاستخراج العلاقات المتعلقة بالموارد المنخفضة.نظهر أن دمج النوعين المذكورين أعلاه من تعيين معلومات التعيين في كلا المحالمان والضبط بشكل جيد يمكن أن يحسن بشكل كبير من أداء النموذج على مهام استخراج العلاقات المتعلقة بالموارد المنخفضة.
Neural relation extraction models have shown promising results in recent years; however, the model performance drops dramatically given only a few training samples. Recent works try leveraging the advance in few-shot learning to solve the low resource problem, where they train label-agnostic models to directly compare the semantic similarities among context sentences in the embedding space. However, the label-aware information, i.e., the relation label that contains the semantic knowledge of the relation itself, is often neglected for prediction. In this work, we propose a framework considering both label-agnostic and label-aware semantic mapping information for low resource relation extraction. We show that incorporating the above two types of mapping information in both pretraining and fine-tuning can significantly improve the model performance on low-resource relation extraction tasks.
References used
https://aclanthology.org/
rate research
Read More
Low-resource Relation Extraction (LRE) aims to extract relation facts from limited labeled corpora when human annotation is scarce. Existing works either utilize self-training scheme to generate pseudo labels that will cause the gradual drift problem
, or leverage meta-learning scheme which does not solicit feedback explicitly. To alleviate selection bias due to the lack of feedback loops in existing LRE learning paradigms, we developed a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate the gradient descent direction on labeled data and bootstrap its optimization capability through trial and error. We also propose a framework called GradLRE, which handles two major scenarios in low-resource relation extraction. Besides the scenario where unlabeled data is sufficient, GradLRE handles the situation where no unlabeled data is available, by exploiting a contextualized augmentation method to generate data. Experimental results on two public datasets demonstrate the effectiveness of GradLRE on low resource relation extraction when comparing with baselines.
A bigger is better'' explosion in the number of parameters in deep neural networks has made it increasingly challenging to make state-of-the-art networks accessible in compute-restricted environments. Compression techniques have taken on renewed impo
rtance as a way to bridge the gap. However, evaluation of the trade-offs incurred by popular compression techniques has been centered on high-resource datasets. In this work, we instead consider the impact of compression in a data-limited regime. We introduce the term low-resource double bind to refer to the co-occurrence of data limitations and compute resource constraints. This is a common setting for NLP for low-resource languages, yet the trade-offs in performance are poorly studied. Our work offers surprising insights into the relationship between capacity and generalization in data-limited regimes for the task of machine translation. Our experiments on magnitude pruning for translations from English into Yoruba, Hausa, Igbo and German show that in low-resource regimes, sparsity preserves performance on frequent sentences but has a disparate impact on infrequent ones. However, it improves robustness to out-of-distribution shifts, especially for datasets that are very distinct from the training distribution. Our findings suggest that sparsity can play a beneficial role at curbing memorization of low frequency attributes, and therefore offers a promising solution to the low-resource double bind.
In this paper we explore a very simple neural approach to mapping orthography to phonetic transcription in a low-resource context. The basic idea is to start from a baseline system and focus all efforts on data augmentation. We will see that some techniques work, but others do not.
Low-resource languages can be understood as languages that are more scarce, less studied, less privileged, less commonly taught and for which there are less resources available (Singh, 2008; Cieri et al., 2016; Magueresse et al., 2020). Natural Langu
age Processing (NLP) research and technology mainly focuses on those languages for which there are large data sets available. To illustrate differences in data availability: there are 6 million Wikipedia articles available for English, 2 million for Dutch, and merely 82 thousand for Albanian. The scarce data issue becomes increasingly apparent when large parallel data sets are required for applications such as Neural Machine Translation (NMT). In this work, we investigate to what extent translation between Albanian (SQ) and Dutch (NL) is possible comparing a one-to-one (SQ↔AL) model, a low-resource pivot-based approach (English (EN) as pivot) and a zero-shot translation (ZST) (Johnson et al., 2016; Mattoni et al., 2017) system. From our experiments, it results that the EN-pivot-model outperforms both the direct one-to-one and the ZST model. Since often, small amounts of parallel data are available for low-resource languages or settings, experiments were conducted using small sets of parallel NL↔SQ data. The ZST appeared to be the worst performing models. Even when the available parallel data (NL↔SQ) was added, i.e. in a few-shot setting (FST), it remained the worst performing system according to the automatic (BLEU and TER) and human evaluation.
State-of-the-art abstractive summarization models generally rely on extensive labeled data, which lowers their generalization ability on domains where such data are not available. In this paper, we present a study of domain adaptation for the abstrac
tive summarization task across six diverse target domains in a low-resource setting. Specifically, we investigate the second phase of pre-training on large-scale generative models under three different settings: 1) source domain pre-training; 2) domain-adaptive pre-training; and 3) task-adaptive pre-training. Experiments show that the effectiveness of pre-training is correlated with the similarity between the pre-training data and the target domain task. Moreover, we find that continuing pre-training could lead to the pre-trained model's catastrophic forgetting, and a learning method with less forgetting can alleviate this issue. Furthermore, results illustrate that a huge gap still exists between the low-resource and high-resource settings, which highlights the need for more advanced domain adaptation methods for the abstractive summarization task.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
