Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization
التدرج التدرج التدرج التدريجي التابع الاتساق الواقعية لتلخيص مبادرة
317
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
اكتسبت أنظمة تلخيص الجماع العصبي تقدما كبيرا في السنوات الأخيرة.ومع ذلك، غالبا ما تنتج تلخيص التلوث في كثير من الأحيان بيانات غير متناسقة أو حقائق كاذبة.كيفية توليد الملخصات التجريدية بشكل كبير تلقائيافي هذه الورقة، اقترحنا نهجا فعالا معزز بيانات تكبير البيانات الفعالة لتشكيل مجموعة بيانات الاتساق الواقعية.بناء على مجموعة البيانات الاصطناعية، ندرب نموذجا للتقييم التي لا يمكن أن تجعل تمييز التناسق الواقعي الدقيق والقوي فحسب، بل قادرا أيضا على جعل الأخطاء الواقعية القابلة للتفسير تتبعها توزيع التدرج السابق على توزيع الرمز المميز.توضح إجراء التجارب والتحليل في ملخصات التلخيص المشروح العام ومجموعات بيانات الاتساق واقعية نهجنا فعال ومعقول.
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 summaries? 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.
References used
https://aclanthology.org/
rate research
Read More
Automatic abstractive summaries are found to often distort or fabricate facts in the article. This inconsistency between summary and original text has seriously impacted its applicability. We propose a fact-aware summarization model FASum to extract
and integrate factual relations into the summary generation process via graph attention. We then design a factual corrector model FC to automatically correct factual errors from summaries generated by existing systems. Empirical results show that the fact-aware summarization can produce abstractive summaries with higher factual consistency compared with existing systems, and the correction model improves the factual consistency of given summaries via modifying only a few keywords.
We propose the first general-purpose gradient-based adversarial attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix
, hence enabling gradient-based optimization. We empirically demonstrate that our white-box attack attains state-of-the-art attack performance on a variety of natural language tasks, outperforming prior work in terms of adversarial success rate with matching imperceptibility as per automated and human evaluation. Furthermore, we show that a powerful black-box transfer attack, enabled by sampling from the adversarial distribution, matches or exceeds existing methods, while only requiring hard-label outputs.
Factual inconsistencies existed in the output of abstractive summarization models with original documents are frequently presented. Fact consistency assessment requires the reasoning capability to find subtle clues to identify whether a model-generat
ed summary is consistent with the original document. This paper proposes a fine-grained two-stage Fact Consistency assessment framework for Summarization models (SumFC). Given a document and a summary sentence, in the first stage, SumFC selects the top-K most relevant sentences with the summary sentence from the document. In the second stage, the model performs fine-grained consistency reasoning at the sentence level, and then aggregates all sentences' consistency scores to obtain the final assessment result. We get the training data pairs by data synthesis and adopt contrastive loss of data pairs to help the model identify subtle cues. Experiment results show that SumFC has made a significant improvement over the previous state-of-the-art methods. Our experiments also indicate that SumFC distinguishes detailed differences better.
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.
Nonlinear conjugate gradient (CG) method holds an important role in solving large-scale unconstrained optimization problems. In this paper, we suggest a new modification of CG coefficient �� that satisfies sufficient descent condition and possesses global convergence property under strong Wolfe line search. The numerical results show that our new method is more efficient compared with other CG formulas tested.
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
