Do you want to publish a course? Click here

Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases

استخراج الأساس المنطقي على مستوى الفقرة من خلال التنظيم: دراسة حالة عن المحكمة الأوروبية لحالات حقوق الإنسان

351   0   0   0.0 ( 0 )
 Publication date 2021
and research's language is English
 Created by Shamra Editor




Ask ChatGPT about the research

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 satisfy 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.



References used
https://aclanthology.org/
rate research

Read More

In the last few years the world faced many political, economical, ideological and military changes, leading to the emergence of a new international situation. These changes had their effects on the international relations especially in the method o f dealing with different issues and problems. They also affected on applying the principles on which the international law is based such as sovereignty, equality in sovereignty, the principles of human rights and the principle of not interfering in the internal affairs of other countries. On these bases a new international map is formed with the emergence of one political and economical pole. As a consequence, the world has lost its strategic balance and the onepole trend has dominated the international relations and has manifested itself in the international decision-making and the current world issues. This, in turn, has compromised the role of the United Nations and other international government and non-government organizations that comprise the human rights organizations on the bases that what happened in Iraq and happening in Libya are considered a human disaster in all measures. Through the trespasses that the United States has committed, and still committing, by jumping over the international legitimacy and the contradictions in the unrealistic justifications for waging wars and military actions and the consequent violations of internationally admitted human rights through international treaties, for all these, the United States is considered part of most of them.
The issue of human rights is one of the most important issues that are still on the stage at all times and permanently, especially on the political scene and these are the ones that have taken the lead and are the subject of global and domestic atten tion, so we find at the global level and in particular after the end of the Second World War a need has emerged For global peace and the need to work to create a kind of international balance, in addition to seeking by a number of people to achieve independence and work to build the national state, the bodies and organizations of the international community have emerged and they are concerned with human rights and fundamental freedoms and these are the ones that have emerged from many of Declarations and many international agreements in most areas related to human rights, and we find that at the local level, Egypt has not failed to participate in all efforts and all international forums that have discussed issues related to human rights, and the principle of respect for human rights is one of the most important criteria for defining relationships and defining international transactions and measuring The political development of any society, and the evaluation of political systems as well as economic and social systems has become subject to the extent to which these systems are achieving in order to achieve many goals. The rights and freedoms have even turned into one of the important measures for growth, and consequently, international concern for human rights has become one of the main distinguishing features of the contemporary international system.
We present the task of Automated Punishment Extraction (APE) in sentencing decisions from criminal court cases in Hebrew. Addressing APE will enable the identification of sentencing patterns and constitute an important stepping stone for many follow up legal NLP applications in Hebrew, including the prediction of sentencing decisions. We curate a dataset of sexual assault sentencing decisions and a manually-annotated evaluation dataset, and implement rule-based and supervised models. We find that while supervised models can identify the sentence containing the punishment with good accuracy, rule-based approaches outperform them on the full APE task. We conclude by presenting a first analysis of sentencing patterns in our dataset and analyze common models' errors, indicating avenues for future work, such as distinguishing between probation and actual imprisonment punishment. We will make all our resources available upon request, including data, annotation, and first benchmark models.
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 us ers 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.

suggested questions

comments
Fetching comments Fetching comments
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا