Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization
Adaptsum: نحو تكيف مجال الموارد المنخفضة لتلخيص مبادرة
281
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعتمد نماذج التلخيص المبخرية للحديث عن الفن بشكل عام على بيانات مسامحة واسعة النطاق، مما أدنى من قدرة تعميمها على المجالات التي لا تتوفر فيها هذه البيانات. في هذه الورقة، نقدم دراسة لتكييف المجال لمهمة تلخيص الجماع عبر ست مجالات مستهدفة متنوعة في إعداد الموارد المنخفضة. على وجه التحديد، نقوم بالتحقيق في المرحلة الثانية من التدريب المسبق على النماذج الإدارية على نطاق واسع تحت ثلاثة إعدادات مختلفة: 1) التدريب قبل التدريب مسبقا؛ 2) ما قبل التكيف مع المجال و 3) ما قبل التدرب في المهام. تشير التجارب إلى أن فعالية التدريب المسبق مرتبط مع التشابه بين بيانات ما قبل التدريب ومهمة المجال المستهدف. علاوة على ذلك، نجد أن التدريب المستمر المستمر يمكن أن يؤدي إلى النسيان الكارثي في النموذج المدرب مسبقا، وسيلة التعلم ذات النسيان الأقل يمكن تخفيف هذه المشكلة. علاوة على ذلك، توضح النتائج أن الفجوة الضخمة لا تزال موجودة بين إعدادات الموارد المنخفضة والموارد عالية، والتي تبرز الحاجة إلى طرق تكيف مجال أكثر تقدما لمهمة تلخيص التلخيص.
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 abstractive 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.
References used
https://aclanthology.org/
rate research
Read More
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.
A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently reiterated in a
set of documents related to a particular topic, resulting in an endorsement effect that increases information salience. In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization. Our method generates a synopsis from each document, which serves as an endorser to identify salient content from other documents. Strongly endorsed text segments are used to enrich a neural encoder-decoder model to consolidate them into an abstractive summary. The method has a great potential to learn from fewer examples to identify salient content, which alleviates the need for costly retraining when the set of documents is dynamically adjusted. Through extensive experiments on benchmark multi-document summarization datasets, we demonstrate the effectiveness of our proposed method over strong published baselines. Finally, we shed light on future research directions and discuss broader challenges of this task using a case study.
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.
Abstractive summarization, the task of generating a concise summary of input documents, requires: (1) reasoning over the source document to determine the salient pieces of information scattered across the long document, and (2) composing a cohesive t
ext by reconstructing these salient facts into a shorter summary that faithfully reflects the complex relations connecting these facts. In this paper, we adapt TP-Transformer (Schlag et al., 2019), an architecture that enriches the original Transformer (Vaswani et al., 2017) with the explicitly compositional Tensor Product Representation (TPR), for the task of abstractive summarization. The key feature of our model is a structural bias that we introduce by encoding two separate representations for each token to represent the syntactic structure (with role vectors) and semantic content (with filler vectors) separately. The model then binds the role and filler vectors into the TPR as the layer output. We argue that the structured intermediate representations enable the model to take better control of the contents (salient facts) and structures (the syntax that connects the facts) when generating the summary. Empirically, we show that our TP-Transformer outperforms the Transformer and the original TP-Transformer significantly on several abstractive summarization datasets based on both automatic and human evaluations. On several syntactic and semantic probing tasks, we demonstrate the emergent structural information in the role vectors and the performance gain by information specificity of the role vectors and improved syntactic interpretability in the TPR layer outputs.(Code and models are available at https://github.com/jiangycTarheel/TPT-Summ)
Neural abstractive summarization systems have gained significant progress in recent years. However, abstractive summarization often produce inconsisitent statements or false facts. How to automatically generate highly abstract yet factually correct s
ummaries? In this paper, we proposed an efficient weak-supervised adversarial data augmentation approach to form the factual consistency dataset. Based on the artificial dataset, we train an evaluation model that can not only make accurate and robust factual consistency discrimination but is also capable of making interpretable factual errors tracing by backpropagated gradient distribution on token embeddings. Experiments and analysis conduct on public annotated summarization and factual consistency datasets demonstrate our approach effective and reasonable.
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
