Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNo NLP Task Should be an Island: Multi-disciplinarity for Diversity in News Recommender Systems
لا ينبغي أن تكون مهمة NLP جزيرة: متعددة التصديعات للتنوع في أنظمة أوصي الأخبار
535
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتم تعريف معالجة اللغة الطبيعية (NLP) بواسطة مهام محددة منفصلة، مع كل الأدبيات الخاصة بها، ومشاركات البيانات القياسية، والتعاريف.في ورقة الموضع هذه، نجادل بأننا لمشكلة معقدة مثل تهديد الديمقراطية من قبل أنظمة الموافقة على الأخبار غير المتنوعة، من المهم مراعاة هدف أعلى، هدف معياري وآثاره.اقترح الخبراء في الأخلاقيات والعلوم السياسية والدراسات الإعلامية أن أنظمة التوصية الإخبارية يمكن استخدامها لدعم الديمقراطية التداولية.نحن نفكر في دور NLP في أنظمة التوصية مع مراعاة هذا الهدف المحدد وإظهار أن هذه النظرية للديمقراطية تساعد على تحديد المهام والتقنيات NLP التي يمكن أن تدعم هذا الهدف، وما الذي لا يزال العمل يجب القيام به.يؤدي ذلك إلى توصيات لباحثي NLP العاملين في هذه المشكلة المحددة وكذلك الباحثين الذين يعملون على مشاكل متعددة التخصصات المعقدة الأخرى.
Natural Language Processing (NLP) is defined by specific, separate tasks, with each their own literature, benchmark datasets, and definitions. In this position paper, we argue that for a complex problem such as the threat to democracy by non-diverse news recommender systems, it is important to take into account a higher-order, normative goal and its implications. Experts in ethics, political science and media studies have suggested that news recommendation systems could be used to support a deliberative democracy. We reflect on the role of NLP in recommendation systems with this specific goal in mind and show that this theory of democracy helps to identify which NLP tasks and techniques can support this goal, and what work still needs to be done. This leads to recommendations for NLP researchers working on this specific problem as well as researchers working on other complex multidisciplinary problems.
References used
https://aclanthology.org/
rate research
Read More
Vector representations have become a central element in semantic language modelling, leading to mathematical overlaps with many fields including quantum theory. Compositionality is a core goal for such representations: given representations for wet'
and fish', how should the concept wet fish' be represented? This position paper surveys this question from two points of view. The first considers the question of whether an explicit mathematical representation can be successful using only tools from within linear algebra, or whether other mathematical tools are needed. The second considers whether semantic vector composition should be explicitly described mathematically, or whether it can be a model-internal side-effect of training a neural network. A third and newer question is whether a compositional model can be implemented on a quantum computer. Given the fundamentally linear nature of quantum mechanics, we propose that these questions are related, and that this survey may help to highlight candidate operations for future quantum implementation.
This paper describes the Air Force Research Laboratory (AFRL) machine translation sys- tems and the improvements that were developed during the WMT21 evaluation campaign. This year, we explore various methods of adapting our baseline models from WMT20 and again measure improvements in performance on the Russian--English language pair.
HCI and NLP traditionally focus on different evaluation methods. While HCI involves a small number of people directly and deeply, NLP traditionally relies on standardized benchmark evaluations that involve a larger number of people indirectly. We pre
sent five methodological proposals at the intersection of HCI and NLP and situate them in the context of ML-based NLP models. Our goal is to foster interdisciplinary collaboration and progress in both fields by emphasizing what the fields can learn from each other.
Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against peop
le with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.
The SemEval 2021 task 5: Toxic Spans Detection is a task of identifying considered-toxic spans in text, which provides a valuable, automatic tool for moderating online contents. This paper represents the second-place method for the task, an ensemble
of two approaches. While one approach relies on combining different embedding methods to extract diverse semantic and syntactic representations of words in context; the other utilizes extra data with a slightly customized Self-training, a semi-supervised learning technique, for sequence tagging problems. Both of our architectures take advantage of a strong language model, which was fine-tuned on a toxic classification task. Although experimental evidence indicates higher effectiveness of the first approach than the second one, combining them leads to our best results of 70.77 F1-score on the test dataset.
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
