Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
المحامون غير شريفة؟تحديد الأضرار التمثيلية في موارد المعرفة المنطقية
291
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تحذير: تحتوي هذه الورقة على محتوى قد يكون مسيء أو مزعجا.تستخدم قواعد المعرفة المنطقية (CSKB) بشكل متزايد لمختلف مهام معالجة اللغة الطبيعية.نظرا لأن CSCBS هي في الغالب التي تم إنشاؤها في الغالب وقد تعكس التحيزات المجتمعية، من المهم التأكد من عدم الخلط بين هذه التحيزات بمفهوم المنطقية.نحن هنا نركز على اثنين من CSCBS واستخدامه على نطاق واسع، والفصح والنهاهي والنهاهي، وتأسيس وجود التحيز في شكل نوعين من الأضرار التمثيلية، والانتعاش في التصورات الاستقطابية وتفاوت التمثيل في مختلف المجموعات الديموغرافية في كلا CSCBS.بعد ذلك، نجد أضرارا تمثيلية مماثلة للنماذج المصب التي تستخدم المفاهيم.أخيرا، نقترح نهجا قائم على الترشيح لتخفيف هذه الأضرار، ويلاحظ أن نهجنا المستندات المرتبطا يمكن أن يقلل من المشكلات في كل من الموارد والنماذج ولكن يؤدي إلى انخفاض الأداء، مغادرة المجال للعمل في المستقبل لبناء نماذج المنطقية أكثر عدالة وأقوىوبعد
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, it 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.
References used
https://aclanthology.org/
rate research
Read More
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.
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.
Abstract To develop commonsense-grounded NLP applications, a comprehensive and accurate commonsense knowledge graph (CKG) is needed. It is time-consuming to manually construct CKGs and many research efforts have been devoted to the automatic construc
tion of CKGs. Previous approaches focus on generating concepts that have direct and obvious relationships with existing concepts and lack an capability to generate unobvious concepts. In this work, we aim to bridge this gap. We propose a general graph-to-paths pretraining framework that leverages high-order structures in CKGs to capture high-order relationships between concepts. We instantiate this general framework to four special cases: long path, path-to-path, router, and graph-node-path. Experiments on two datasets demonstrate the effectiveness of our methods. The code will be released via the public GitHub repository.
In this work we leverage commonsense knowledge in form of knowledge paths to establish connections between sentences, as a form of explicitation of implicit knowledge. Such connections can be direct (singlehop paths) or require intermediate concepts
(multihop paths). To construct such paths we combine two model types in a joint framework we call Co-nnect: a relation classifier that predicts direct connections between concepts; and a target prediction model that generates target or intermediate concepts given a source concept and a relation, which we use to construct multihop paths. Unlike prior work that relies exclusively on static knowledge sources, we leverage language models finetuned on knowledge stored in ConceptNet, to dynamically generate knowledge paths, as explanations of implicit knowledge that connects sentences in texts. As a central contribution we design manual and automatic evaluation settings for assessing the quality of the generated paths. We conduct evaluations on two argumentative datasets and show that a combination of the two model types generates meaningful, high-quality knowledge paths between sentences that reveal implicit knowledge conveyed in text.
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.
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
