Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022)最新文献

Knowledge-Augmented Language Models for Cause-Effect Relation Classification 用于因果关系分类的知识增强语言模型

Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022) Pub Date : 2021-12-16 DOI: 10.18653/v1/2022.csrr-1.6

Pedram Hosseini, David A. Broniatowski, Mona T. Diab

引用次数: 8

Bridging the Gap between Recognition-level Pre-training and Commonsensical Vision-language Tasks 弥合识别级预训练和常识视觉语言任务之间的差距

Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.csrr-1.4

Yue Wan, Yueen Ma, Haoxuan You, Zhecan Wang, Shih-Fu Chang

{"title":"Bridging the Gap between Recognition-level Pre-training and Commonsensical Vision-language Tasks","authors":"Yue Wan, Yueen Ma, Haoxuan You, Zhecan Wang, Shih-Fu Chang","doi":"10.18653/v1/2022.csrr-1.4","DOIUrl":"https://doi.org/10.18653/v1/2022.csrr-1.4","url":null,"abstract":"Large-scale visual-linguistic pre-training aims to capture the generic representations from multimodal features, which are essential for downstream vision-language tasks. Existing methods mostly focus on learning the semantic connections between visual objects and linguistic content, which tend to be recognitionlevel information and may not be sufficient for commonsensical reasoning tasks like VCR. In this paper, we propose a novel commonsensical vision-language pre-training framework to bridge the gap. We first augment the conventional image-caption pre-training datasets with commonsense inferences from a visuallinguistic GPT-2. To pre-train models on image, caption and commonsense inferences together, we propose two new tasks: masked commonsense modeling (MCM) and commonsense type prediction (CTP). To reduce the shortcut effect between captions and commonsense inferences, we further introduce the domain-wise adaptive masking that dynamically adjusts the masking ratio. Experimental results on downstream tasks, VCR and VQA, show the improvement of our pre-training strategy over previous methods. Human evaluation also validates the relevance, informativeness, and diversity of the generated commonsense inferences. Overall, we demonstrate the potential of incorporating commonsense knowledge into the conventional recognition-level visual-linguistic pre-training.","PeriodicalId":166496,"journal":{"name":"Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117246049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cloze Evaluation for Deeper Understanding of Commonsense Stories in Indonesian 加深对印尼语常识性故事理解的完形填空评价

Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.csrr-1.2

Fajri Koto, Timothy Baldwin, Jey Han Lau

引用次数: 3

Identifying relevant common sense information in knowledge graphs 识别知识图中相关的常识信息

Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.csrr-1.1

Guy Aglionby, Simone Tuefel

引用次数: 3

Psycholinguistic Diagnosis of Language Models’ Commonsense Reasoning 语言模型常识性推理的心理语言学诊断

Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.csrr-1.3

Yan Cong

{"title":"Psycholinguistic Diagnosis of Language Models’ Commonsense Reasoning","authors":"Yan Cong","doi":"10.18653/v1/2022.csrr-1.3","DOIUrl":"https://doi.org/10.18653/v1/2022.csrr-1.3","url":null,"abstract":"Neural language models have attracted a lot of attention in the past few years. More and more researchers are getting intrigued by how language models encode commonsense, specifically what kind of commonsense they understand, and why they do. This paper analyzed neural language models’ understanding of commonsense pragmatics (i.e., implied meanings) through human behavioral and neurophysiological data. These psycholinguistic tests are designed to draw conclusions based on predictive responses in context, making them very well suited to test word-prediction models such as BERT in natural settings. They can provide the appropriate prompts and tasks to answer questions about linguistic mechanisms underlying predictive responses. This paper adopted psycholinguistic datasets to probe language models’ commonsense reasoning. Findings suggest that GPT-3’s performance was mostly at chance in the psycholinguistic tasks. We also showed that DistillBERT had some understanding of the (implied) intent that’s shared among most people. Such intent is implicitly reflected in the usage of conversational implicatures and presuppositions. Whether or not fine-tuning improved its performance to human-level depends on the type of commonsense reasoning.","PeriodicalId":166496,"journal":{"name":"Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127520766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6