Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases
Negater: اكتشاف غير مخالف للسلبيات في قواعد المعرفة المنطقية
359
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تدوين المعرفة المنطقية في الآلات هو هدف طويل الأطول من الذكاء الاصطناعي. في الآونة الأخيرة، تم إحراز تقدم كبير نحو هذا الهدف مع تقنيات بناء قاعدة المعرفة التلقائية (KB). ومع ذلك، فإن هذه التقنيات تركز في المقام الأول على اكتساب بيانات KB الإيجابية (TRUE)، على الرغم من أن البيانات السلبية (الخاطئة) غالبا ما تكون مهمة أيضا للمنطق التمييزي على متن العموم KBS. كخطوة أولى نحو الأخير، تقترح هذه الورقة NEGATER، وهو إطار يصنف السلبيات المحتملة في العمولة KBS باستخدام نموذج لغة سياقي (LM). الأهم من ذلك، حيث لا تحتوي معظم KBS على السلبيات، تعتمد Negater فقط على المعرفة الإيجابية في LM ولا تتطلب أمثلة سلبية للحقيقة. توضح التجارب أنه مقارنة بنهج تكبير البيانات المتعاقبة متعددة النزاع، فإن نطاط غلة السلبيات التي تعتبر أكثر حكما متماسكا ومفيدا --- تؤدي إلى تحسينات دقة ذات دلالة إحصائية في مهمة استكمال KB صعبة وتؤكد أن المعرفة الإيجابية في LMS يمكن إعادة -العرضة "لتوليد المعرفة السلبية.
Codifying commonsense knowledge in machines is a longstanding goal of artificial intelligence. Recently, much progress toward this goal has been made with automatic knowledge base (KB) construction techniques. However, such techniques focus primarily on the acquisition of positive (true) KB statements, even though negative (false) statements are often also important for discriminative reasoning over commonsense KBs. As a first step toward the latter, this paper proposes NegatER, a framework that ranks potential negatives in commonsense KBs using a contextual language model (LM). Importantly, as most KBs do not contain negatives, NegatER relies only on the positive knowledge in the LM and does not require ground-truth negative examples. Experiments demonstrate that, compared to multiple contrastive data augmentation approaches, NegatER yields negatives that are more grammatical, coherent, and informative---leading to statistically significant accuracy improvements in a challenging KB completion task and confirming that the positive knowledge in LMs can be re-purposed'' to generate negative knowledge.
References used
https://aclanthology.org/
rate research
Read More
Semantic Web is a new revolution in the world of the Web, where information and
data become viable for logical processing by computer programs. Where they are
transformed into meaningful data network. Although Semantic Web is considered the
future
of World Wide Web, the Arabic research and studies are still relatively rare in this
field. Therefore, this paper gives a reference study of Semantic Web and the different
methods to explore the knowledge and discover useful information from the vast amount
of data provided by the web. It gives a programming example like application of some of
these techniques provided by the Semantic Web and methods to discover the knowledge of
it. This simplified programming example provides services related to higher education
Syrian government, such as information about the Syrian public universities like the name
of the university (Syrian Virtual University, Tishreen, Aleppo, Damascus, and Al Baath),
address of the university, its web site, number of students and a summary of the university,
which helps intelligent agents to find those services dynamically.
Warning: this paper contains content that may be offensive or upsetting. Commonsense knowledge bases (CSKB) are increasingly used for various natural language processing tasks. Since CSKBs are mostly human-generated and may reflect societal biases, i
t is important to ensure that such biases are not conflated with the notion of commonsense. Here we focus on two widely used CSKBs, ConceptNet and GenericsKB, and establish the presence of bias in the form of two types of representational harms, overgeneralization of polarized perceptions and representation disparity across different demographic groups in both CSKBs. Next, we find similar representational harms for downstream models that use ConceptNet. Finally, we propose a filtering-based approach for mitigating such harms, and observe that our filtered-based approach can reduce the issues in both resources and models but leads to a performance drop, leaving room for future work to build fairer and stronger commonsense models.
This paper presents the preliminary results of an ongoing project that analyzes the growing body of scientific research published around the COVID-19 pandemic. In this research, a general-purpose semantic model is used to double annotate a batch of 5
00 sentences that were manually selected from the CORD-19 corpus. Afterwards, a baseline text-mining pipeline is designed and evaluated via a large batch of 100,959 sentences. We present a qualitative analysis of the most interesting facts automatically extracted and highlight possible future lines of development. The preliminary results show that general-purpose semantic models are a useful tool for discovering fine-grained knowledge in large corpora of scientific documents.
Recent methods based on pre-trained language models have shown strong supervised performance on commonsense reasoning. However, they rely on expensive data annotation and time-consuming training. Thus, we focus on unsupervised commonsense reasoning.
We show the effectiveness of using a common framework, Natural Language Inference (NLI), to solve diverse commonsense reasoning tasks. By leveraging transfer learning from large NLI datasets, and injecting crucial knowledge from commonsense sources such as ATOMIC 2020 and ConceptNet, our method achieved state-of-the-art unsupervised performance on two commonsense reasoning tasks: WinoWhy and CommonsenseQA. Further analysis demonstrated the benefits of multiple categories of knowledge, but problems about quantities and antonyms are still challenging.
A hyperbole is an intentional and creative exaggeration not to be taken literally. Despite its ubiquity in daily life, the computational explorations of hyperboles are scarce. In this paper, we tackle the under-explored and challenging task: sentence
-level hyperbole generation. We start with a representative syntactic pattern for intensification and systematically study the semantic (commonsense and counterfactual) relationships between each component in such hyperboles. We then leverage commonsense and counterfactual inference to generate hyperbole candidates based on our findings from the pattern, and train neural classifiers to rank and select high-quality hyperboles. Automatic and human evaluations show that our generation method is able to generate hyperboles with high success rate, intensity, funniness, and creativity.
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
