Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts
Nnect Co-Nnect: إطار للكشف عن مسارات معرفة المنطقية كصفات عن المعرفة الضمنية في النصوص
388
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا العمل، نستفيد المعرفة المنوية في شكل مسارات المعرفة لإقامة صلات بين الجمل، كشكل من أشكال تفسير المعرفة الضمنية. يمكن أن تكون هذه الاتصالات مباشرة (مسارات مفردة) أو تتطلب مفاهيم وسيطة (مسارات Multihop). لبناء مثل هذه المسارات تجمع بين نوعين نموذجيين في إطار مشترك نسميه Nnect: مصنف علاقة يتنبأ بالاتصالات المباشرة بين المفاهيم؛ ونموذج التنبؤ المستهدف الذي يولد مفاهيم مستهدفة أو متوسطة بالنظر إلى مفهوم مصدر وعلاقة، والتي نستخدمها لإنشاء مسارات Multihop. على عكس العمل السابق الذي يعتمد بشكل حصري على مصادر المعرفة الثابتة، فإننا نستفيد من نماذج اللغة المصنعة للمعرفة المخزنة في Congalnet، لتوليد مسارات المعرفة بشكل حيوي، كشروح من المعرفة الضمنية التي تربط الجمل في النصوص. كمساهمة مركزية نقوم بتصميم إعدادات التقييم اليدوية والآلية لتقييم جودة المسارات التي تم إنشاؤها. نقوم بإجراء تقييمات على رقمين جدليين وإظهار أن هناك مزيج من النوعين النموذجيين يولد مسارات معارف ذات مغزى وعالية الجودة بين الجمل التي تكشف عن المعرفة الضمنية المنقولة في النص.
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.
References used
https://aclanthology.org/
rate research
Read More
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.
Empathy is the link between self and others. Detecting and understanding empathy is a key element for improving human-machine interaction. However, annotating data for detecting empathy at a large scale is a challenging task. This paper employs multi
-task training with knowledge distillation to incorporate knowledge from available resources (emotion and sentiment) to detect empathy from the natural language in different domains. This approach yields better results on an existing news-related empathy dataset compared to strong baselines. In addition, we build a new dataset for empathy prediction with fine-grained empathy direction, seeking or providing empathy, from Twitter. We release our dataset for research purposes.
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.
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.
Detecting stance on Twitter is especially challenging because of the short length of each tweet, the continuous coinage of new terminology and hashtags, and the deviation of sentence structure from standard prose. Fine-tuned language models using lar
ge-scale in-domain data have been shown to be the new state-of-the-art for many NLP tasks, including stance detection. In this paper, we propose a novel BERT-based fine-tuning method that enhances the masked language model for stance detection. Instead of random token masking, we propose using a weighted log-odds-ratio to identify words with high stance distinguishability and then model an attention mechanism that focuses on these words. We show that our proposed approach outperforms the state of the art for stance detection on Twitter data about the 2020 US Presidential election.
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
