Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDecision-Focused Summarization
تلخيص يركز على القرار
233
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
عادة ما يتم تغريم الصلة في التلخيص بناء على معلومات نصية وحدها، دون دمج الأفكار حول قرار معين. نتيجة لذلك، لدعم تحليل المخاطر لسرطان البنكرياس، قد تشمل ملخصات الملاحظات الطبية معلومات غير ذات صلة مثل إصابة الركبة. نقترح مشكلة جديدة، ويلخص تركز في القرار، حيث الهدف هو تلخيص المعلومات ذات الصلة لاتخاذ قرار. نستفيد من نموذج تنبؤي يتخذ القرار بناء على النص الكامل لتوفير رؤى قيمة حول كيفية استنتاج القرار من النص. لبناء ملخص، ثم حدد جمل تمثيلية تؤدي إلى قرارات نموذجية مماثلة مثل استخدام النص الكامل أثناء المحاسبة عن عدم التكرار النصي. لتقييم طريقةنا (Decsum)، نبني اختبار المهمة لتلخيص المراجعات العشرة الأولى لمطعم لدعم التنبؤ بتصنيفها في المستقبل على Yelp. تفوق Decsum بشكل كبير على أساليب تلخيص النص فقط وأساليب التفسير القائمة على النماذج في الإخلاص والتمثيل. نوضح كذلك أن Decsum هو الطريقة الوحيدة التي تمكن البشر من تفوق فرصة عشوائية في التنبؤ بالمطعم الذي سيتم تصنيفه بشكل أفضل في المستقبل.
Relevance in summarization is typically de- fined based on textual information alone, without incorporating insights about a particular decision. As a result, to support risk analysis of pancreatic cancer, summaries of medical notes may include irrelevant information such as a knee injury. We propose a novel problem, decision-focused summarization, where the goal is to summarize relevant information for a decision. We leverage a predictive model that makes the decision based on the full text to provide valuable insights on how a decision can be inferred from text. To build a summary, we then select representative sentences that lead to similar model decisions as using the full text while accounting for textual non-redundancy. To evaluate our method (DecSum), we build a testbed where the task is to summarize the first ten reviews of a restaurant in support of predicting its future rating on Yelp. DecSum substantially outperforms text-only summarization methods and model-based explanation methods in decision faithfulness and representativeness. We further demonstrate that DecSum is the only method that enables humans to outperform random chance in predicting which restaurant will be better rated in the future.
References used
https://aclanthology.org/
rate research
Read More
تسببت الزيادة الكبيرة في كمية المعلومات المتاحة في الانترنت من مختلف المصادر في السنوات الأخيرة إلى صعوبة الوصول والبحث في النصوص الكبيرة عن المعلومة المطلوبة بسرعة وكفاءة وكان من الصعب جداً استخراج تلاخيص النصوص بشكل يدوي وذلك بسبب النمو الهائل للمع
لومات بشكل يومي لذلك أصبح من الضروري استخراج التلاخيص تلقائياً من نص واحد أو عدة نصوص لذلك سنتطرق في بحثنا إلى أهم الأساليب والطرق في عمليات التلخيص في الأعوام السابق
We consider the problem of topic-focused abstractive summarization, where the goal is to generate an abstractive summary focused on a particular topic, a phrase of one or multiple words. We hypothesize that the task of generating topic-focused summar
ies can be improved by showing the model what it must not focus on. We introduce a deep reinforcement learning approach to topic-focused abstractive summarization, trained on rewards with a novel negative example baseline. We define the input in this problem as the source text preceded by the topic. We adapt the CNN-Daily Mail and New York Times summarization datasets for this task. We then show through experiments on existing rewards that the use of a negative example baseline can outperform the use of a self-critical baseline, in Rouge, BERTScore, and human evaluation metrics.
In this paper, we focus on improving the quality of the summary generated by neural abstractive dialogue summarization systems. Even though pre-trained language models generate well-constructed and promising results, it is still challenging to summar
ize the conversation of multiple participants since the summary should include a description of the overall situation and the actions of each speaker. This paper proposes self-supervised strategies for speaker-focused post-correction in abstractive dialogue summarization. Specifically, our model first discriminates which type of speaker correction is required in a draft summary and then generates a revised summary according to the required type. Experimental results show that our proposed method adequately corrects the draft summaries, and the revised summaries are significantly improved in both quantitative and qualitative evaluations.
The amount of information available online can be overwhelming for users to digest, specially when dealing with other users' comments when making a decision about buying a product or service. In this context, opinion summarization systems are of grea
t value, extracting important information from the texts and presenting them to the user in a more understandable manner. It is also known that the usage of semantic representations can benefit the quality of the generated summaries. This paper aims at developing opinion summarization methods based on Abstract Meaning Representation of texts in the Brazilian Portuguese language. Four different methods have been investigated, alongside some literature approaches. The results show that a Machine Learning-based method produced summaries of higher quality, outperforming other literature techniques on manually constructed semantic graphs. We also show that using parsed graphs over manually annotated ones harmed the output. Finally, an analysis of how important different types of information are for the summarization process suggests that using Sentiment Analysis features did not improve summary quality.
Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments. To alleviate this issue, recent work has proposed evaluation metrics which rely on question
answering models to assess whether a summary contains all the relevant information in its source document. Though promising, the proposed approaches have so far failed to correlate better than ROUGE with human judgments. In this paper, we extend previous approaches and propose a unified framework, named QuestEval. In contrast to established metrics such as ROUGE or BERTScore, QuestEval does not require any ground-truth reference. Nonetheless, QuestEval substantially improves the correlation with human judgments over four evaluation dimensions (consistency, coherence, fluency, and relevance), as shown in extensive experiments.
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
