Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAbstractive Document Summarization with Word Embedding Reconstruction
تلخيص وثائق المبادرة مع كلمة إعادة بناء كلمة
298
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
حققت نماذج التسلسل العصبي (SEQ2SEQ) ونماذج بيرت تحسينات كبيرة في تلخيص وثائق المبادرة (الإعلانات) دون ومع مسبق التدريب، على التوالي.ومع ذلك، فإنهم يحضرون في بعض الأحيان مرارا وتكرارا عبارات المصدر غير مهم بينما يتجاهل عن طريق الخطأ تلك المهمة.نقدم آليات إعادة الإعمار على مستويين لتخفيف هذه المشكلة.يعيد إعادة تعيين مستوى التسلسل على مستوى التسلسل الوثيقة بأكملها من الطبقة المخفية من الملخص المستهدف، في حين أن كلمة تضمين المستوى يعيد إعادة إنشاء واحد من متوسط كلمة Word للمصدر في الجانب المستهدف لضمان إدراج أكبر قدر ممكن من المعلومات الهامة في الملخصبقدر الإمكان.بناء على افتراض تقيس تدابير تردد الوثيقة العكسية (IDF) مدى أهمية كلمة كلمة، فإننا نستفيد إلى زيادة أوزان جيش الدفاع الإسرائيلي في إعادة بناء مستوى التضمين لدينا.تؤدي الأطر المقترحة إلى تحسينات واعدة لمقاييس الحمر والتصنيف البشري على مجموعات بيانات تلخيص CNN / Daily البريدية وحكم الأخبار.
Neural sequence-to-sequence (Seq2Seq) models and BERT have achieved substantial improvements in abstractive document summarization (ADS) without and with pre-training, respectively. However, they sometimes repeatedly attend to unimportant source phrases while mistakenly ignore important ones. We present reconstruction mechanisms on two levels to alleviate this issue. The sequence-level reconstructor reconstructs the whole document from the hidden layer of the target summary, while the word embedding-level one rebuilds the average of word embeddings of the source at the target side to guarantee that as much critical information is included in the summary as possible. Based on the assumption that inverse document frequency (IDF) measures how important a word is, we further leverage the IDF weights in our embedding-level reconstructor. The proposed frameworks lead to promising improvements for ROUGE metrics and human rating on both the CNN/Daily Mail and Newsroom summarization datasets.
References used
https://aclanthology.org/
rate research
Read More
Word embedding is essential for neural network models for various natural language processing tasks. Since the word embedding usually has a considerable size, in order to deploy a neural network model having it on edge devices, it should be effective
ly compressed. There was a study for proposing a block-wise low-rank approximation method for word embedding, called GroupReduce. Even if their structure is effective, the properties behind the concept of the block-wise word embedding compression were not sufficiently explored. Motivated by this, we improve GroupReduce in terms of word weighting and structuring. For word weighting, we propose a simple yet effective method inspired by the term frequency-inverse document frequency method and a novel differentiable method. Based on them, we construct a discriminative word embedding compression algorithm. In the experiments, we demonstrate that the proposed algorithm more effectively finds word weights than competitors in most cases. In addition, we show that the proposed algorithm can act like a framework through successful cooperation with quantization.
Extracting the most important part of legislation documents has great business value because the texts are usually very long and hard to understand. The aim of this article is to evaluate different algorithms for text summarization on EU legislation
documents. The content contains domain-specific words. We collected a text summarization dataset of EU legal documents consisting of 1563 documents, in which the mean length of summaries is 424 words. Experiments were conducted with different algorithms using the new dataset. A simple extractive algorithm was selected as a baseline. Advanced extractive algorithms, which use encoders show better results than baseline. The best result measured by ROUGE scores was achieved by a fine-tuned abstractive T5 model, which was adapted to work with long texts.
Sarcasm detection is of great importance in understanding people's true sentiments and opinions. Many online feedbacks, reviews, social media comments, etc. are sarcastic. Several researches have already been done in this field, but most researchers
studied the English sarcasm analysis compared to the researches are done in Arabic sarcasm analysis because of the Arabic language challenges. In this paper, we propose a new approach for improving Arabic sarcasm detection. Our approach is using data augmentation, contextual word embedding and random forests model to get the best results. Our accuracy in the shared task on sarcasm and sentiment detection in Arabic was 0.5189 for F1-sarcastic as the official metric using the shared dataset ArSarcasmV2 (Abu Farha, et al., 2021).
Large scale pretrained models have demonstrated strong performances on several natural language generation and understanding benchmarks. However, introducing commonsense into them to generate more realistic text remains a challenge. Inspired from pre
vious work on commonsense knowledge generation and generative commonsense reasoning, we introduce two methods to add commonsense reasoning skills and knowledge into abstractive summarization models. Both methods beat the baseline on ROUGE scores, demonstrating the superiority of our models over the baseline. Human evaluation results suggest that summaries generated by our methods are more realistic and have fewer commonsensical errors.
Modern natural language understanding models depend on pretrained subword embeddings, but applications may need to reason about words that were never or rarely seen during pretraining. We show that examples that depend critically on a rarer word are
more challenging for natural language inference models. Then we explore how a model could learn to use definitions, provided in natural text, to overcome this handicap. Our model's understanding of a definition is usually weaker than a well-modeled word embedding, but it recovers most of the performance gap from using a completely untrained word.
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
