Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userExploring Multitask Learning for Low-Resource Abstractive Summarization
استكشاف التعلم المتعدد التواجد للحصول على تلخيص مبادرة الموارد المنخفضة
324
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تستكشف هذه الورقة تأثير استخدام التعلم المتعدد التواجد لتلخيص الجماع في سياق كورسا التدريب الصغيرة.على وجه الخصوص، نحن ندمج أربع مهام مختلفة (تلخيص استخراجي، ونمذجة اللغة، والكشف عن المفهوم، والكشف عن الصياغة على حد سواء بشكل فردي ومزيج، بهدف تعزيز المهمة المستهدفة المتمثلة في تلخيص الجماع عبر التعلم المتعدد.نظرا لأنه بالنسبة للعديد من مجموعات المهام، فإن نموذج مدرب في إعداد متعدد الأيتاكف يتفوق على نموذج مدرب فقط في تلخيص الجماع، مع عدم تقديم بيانات تلخيص إضافية.بالإضافة إلى ذلك، نقوم بعمل بحث شامل والعثور على أن بعض المهام (E.G. الكشف عن الصياغة) تستفيد باستمرار تلخيص الجماعي، ليس فقط عند الجمع مع المهام الأخرى ولكن أيضا عند استخدام بهيئات مختلفة وتدريب كورسا.
This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language modeling, concept detection, and paraphrase detection) both individually and in combination, with the goal of enhancing the target task of abstractive summarization via multitask learning. We show that for many task combinations, a model trained in a multitask setting outperforms a model trained only for abstractive summarization, with no additional summarization data introduced. Additionally, we do a comprehensive search and find that certain tasks (e.g. paraphrase detection) consistently benefit abstractive summarization, not only when combined with other tasks but also when using different architectures and training corpora.
References used
https://aclanthology.org/
rate research
Read More
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.
We study generating abstractive summaries that are faithful and factually consistent with the given articles. A novel contrastive learning formulation is presented, which leverages both reference summaries, as positive training data, and automaticall
y generated erroneous summaries, as negative training data, to train summarization systems that are better at distinguishing between them. We further design four types of strategies for creating negative samples, to resemble errors made commonly by two state-of-the-art models, BART and PEGASUS, found in our new human annotations of summary errors. Experiments on XSum and CNN/Daily Mail show that our contrastive learning framework is robust across datasets and models. It consistently produces more factual summaries than strong comparisons with post error correction, entailment-based reranking, and unlikelihood training, according to QA-based factuality evaluation. Human judges echo the observation and find that our model summaries correct more errors.
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.
We translate a closed text that is known in advance and available in many languages into a new and severely low resource language. Most human translation efforts adopt a portionbased approach to translate consecutive pages/chapters in order, which ma
y not suit machine translation. We compare the portion-based approach that optimizes coherence of the text locally with the random sampling approach that increases coverage of the text globally. Our results show that the random sampling approach performs better. When training on a seed corpus of ∼1,000 lines from the Bible and testing on the rest of the Bible (∼30,000 lines), random sampling gives a performance gain of +11.0 BLEU using English as a simulated low resource language, and +4.9 BLEU using Eastern Pokomchi, a Mayan language. Furthermore, we compare three ways of updating machine translation models with increasing amount of human post-edited data through iterations. We find that adding newly post-edited data to training after vocabulary update without self-supervision performs the best. We propose an algorithm for human and machine to work together seamlessly to translate a closed text into a severely low resource language.
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.
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
