Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTowards Human-Centered Summarization: A Case Study on Financial News
نحو التلخصات التي تركز على الإنسان: دراسة حالة عن الأخبار المالية
353
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نماذج تلخيص التعلم العميق الأخيرة (DL) تتفوق بشكل كبير من منهجيات التلخصات التقليدية، وتوليد ملخصات عالية الجودة. على الرغم من نجاحهم، لا تزال هناك مشكلات مفتوحة مهمة، مثل المشاركة المحدودة والثقة للمستخدمين في العملية برمتها. من أجل التغلب على هذه القضايا، نعيد النظر في مهمة التلخيص من منظور متمركز الإنسان. نقترح دمج واجهة المستخدم بنموذج DL الأساسي، بدلا من معالجة التلخيص كامرأة معزولة من المستخدم النهائي. نقدم نظام جديد، حيث يمكن للمستخدم المشاركة بنشاط في عملية التلخيص بأكملها. كما يمكننا المستخدم من جمع الأفكار في العوامل المسببة التي تدفع سلوك النموذج، واستغلال آلية اهتمام الذات. نحن نركز على المجال المالي، من أجل إظهار كفاءة نماذج DL العامة للتطبيقات الخاصة بالمجال. يتخذ عملنا خطوة أولى نحو نهج تصميم مشترك للواجهة النموذجية، حيث تتطور نماذج DL على طول احتياجات المستخدمين، مما يمهد الطريق نحو واجهات تلخيص نص الحاسوب البشري.
Recent Deep Learning (DL) summarization models greatly outperform traditional summarization methodologies, generating high-quality summaries. Despite their success, there are still important open issues, such as the limited engagement and trust of users in the whole process. In order to overcome these issues, we reconsider the task of summarization from a human-centered perspective. We propose to integrate a user interface with an underlying DL model, instead of tackling summarization as an isolated task from the end user. We present a novel system, where the user can actively participate in the whole summarization process. We also enable the user to gather insights into the causative factors that drive the model's behavior, exploiting the self-attention mechanism. We focus on the financial domain, in order to demonstrate the efficiency of generic DL models for domain-specific applications. Our work takes a first step towards a model-interface co-design approach, where DL models evolve along user needs, paving the way towards human-computer text summarization interfaces.
References used
https://aclanthology.org/
rate research
Read More
In this position paper, we present a research agenda and ideas for facilitating exposure to diverse viewpoints in news recommendation. Recommending news from diverse viewpoints is important to prevent potential filter bubble effects in news consumpti
on, and stimulate a healthy democratic debate.To account for the complexity that is inherent to humans as citizens in a democracy, we anticipate (among others) individual-level differences in acceptance of diversity. We connect this idea to techniques in Natural Language Processing, where distributional language models would allow us to place different users and news articles in a multidimensional space based on semantic content, where diversity is operationalized as distance and variance. In this way, we can model individual latitudes of diversity'' for different users, and thus personalize viewpoint diversity in support of a healthy public debate. In addition, we identify technical, ethical and conceptual issues related to our presented ideas. Our investigation describes how NLP can play a central role in diversifying news recommendations.
Interpretability or explainability is an emerging research field in NLP. From a user-centric point of view, the goal is to build models that provide proper justification for their decisions, similar to those of humans, by requiring the models to sati
sfy additional constraints. To this end, we introduce a new application on legal text where, contrary to mainstream literature targeting word-level rationales, we conceive rationales as selected paragraphs in multi-paragraph structured court cases. We also release a new dataset comprising European Court of Human Rights cases, including annotations for paragraph-level rationales. We use this dataset to study the effect of already proposed rationale constraints, i.e., sparsity, continuity, and comprehensiveness, formulated as regularizers. Our findings indicate that some of these constraints are not beneficial in paragraph-level rationale extraction, while others need re-formulation to better handle the multi-label nature of the task we consider. We also introduce a new constraint, singularity, which further improves the quality of rationales, even compared with noisy rationale supervision. Experimental results indicate that the newly introduced task is very challenging and there is a large scope for further research.
The aim of this research is to investigate the effect of preparing the
financial statements through International Accounting Standard /29/ on
the financial analysis through ratios, since the increase in the inflation
rate affects social and econom
ic aspects, the purchasing power of cash
had been decreased, so the financial statement of the listed companies
in the Syrian Stock Exchange didn't show the right position of these
companies because it didn't take into consideration the changes in
purchasing power even they are in compliance with International
Financial Reporting Standards (IFRS), so it wouldn't be possible to rely
on it for making decision, when use the financial analysis which is one of
the methods to help the financial statement user for their decision.
ROUGE is a widely used evaluation metric in text summarization. However, it is not suitable for the evaluation of abstractive summarization systems as it relies on lexical overlap between the gold standard and the generated summaries. This limitation
becomes more apparent for agglutinative languages with very large vocabularies and high type/token ratios. In this paper, we present semantic similarity models for Turkish and apply them as evaluation metrics for an abstractive summarization task. To achieve this, we translated the English STSb dataset into Turkish and presented the first semantic textual similarity dataset for Turkish as well. We showed that our best similarity models have better alignment with average human judgments compared to ROUGE in both Pearson and Spearman correlations.
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.
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
