首页/论文/2005.00206

arXiv 2005.002062020-05-01cs.AIcs.CL

TransOMCS: From Linguistic Graphs to Commonsense Knowledge

The Hong Kong University of Science and Technology（香港科技大学）；Allen Institute for AI（艾伦人工智能研究所）；University of Pennsylvania（宾夕法尼亚大学）

Hongming Zhang, Daniel Khashabi, Yangqiu Song, Dan Roth

备注：: Accepted by IJCAI 2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Commonsense knowledge acquisition is a key problem for artificial intelligence. Conventional methods of acquiring commonsense knowledge generally require laborious and costly human annotations, which are not feasible on a large scale. In this paper, we explore a practical way of mining commonsense knowledge from linguistic graphs, with the goal of transferring cheap knowledge obtained with linguistic patterns into expensive commonsense knowledge. The result is a conversion of ASER [Zhang et al., 2020], a large-scale selectional preference knowledge resource, into TransOMCS, of the same representation as ConceptNet [Liu and Singh, 2004] but two orders of magnitude larger. Experimental results demonstrate the transferability of linguistic knowledge to commonsense knowledge and the effectiveness of the proposed approach in terms of quantity, novelty, and quality. TransOMCS is publicly available at: https://github.com/HKUST-KnowComp/TransOMCS.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

CogNet: Bridging Linguistic Knowledge, World Knowledge and Commonsense Knowledge

National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

In this paper, we present CogNet, a knowledge base (KB) dedicated to integrating three types of knowledge: (1) linguistic knowledge from FrameNet, which schematically describes situations, objects and events. (2) world knowledge from YAGO, Freebase, DBpedia and Wikidata, which provides explicit knowledge about specific instances. (3) commonsense knowledge from ConceptNet, which describes implicit general facts. To model these different types of knowledge consistently, we introduce a three-level unified frame-styled representation architecture. To integrate free-form commonsense knowledge with …

2021-03-03cs.AIcs.CL

KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning

Beijing Institute of Technology（北京理工大学）

Reasoning is a critical ability towards complete visual understanding. To develop machine with cognition-level visual understanding and reasoning abilities, the visual commonsense reasoning (VCR) task has been introduced. In VCR, given a challenging question about an image, a machine must answer correctly and then provide a rationale justifying its answer. The methods adopting the powerful BERT model as the backbone for learning joint representation of image content and natural language have shown promising improvements on VCR. However, none of the existing methods have utilized commonsense kn…

2020-12-13cs.AIcs.CL

RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge

University of Southern California（南加州大学）

Question: I have five fingers but I am not alive. What am I? Answer: a glove. Answering such a riddle-style question is a challenging cognitive process, in that it requires complex commonsense reasoning abilities, an understanding of figurative language, and counterfactual reasoning skills, which are all important abilities for advanced natural language understanding (NLU). However, there are currently no dedicated datasets aiming to test these abilities. Herein, we present RiddleSense, a new multiple-choice question answering task, which comes with the first large dataset (5.7k examples) for …

2021-07-04cs.AIcs.CL

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities

CSE, HKUST（香港科技大学计算机科学与工程系）

Commonsense knowledge acquisition and reasoning have long been a core artificial intelligence problem. However, in the past, there has been a lack of scalable methods to collect commonsense knowledge. In this paper, we propose to develop principles for collecting commonsense knowledge based on selectional preference. We generalize the definition of selectional preference from one-hop linguistic syntactic relations to higher-order relations over linguistic graphs. Unlike previous commonsense knowledge definition (e.g., ConceptNet), selectional preference (SP) knowledge only relies on statistica…

2022-01-16cs.AIcs.CL

Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization

University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）

While much research has been done in text-to-image synthesis, little work has been done to explore the usage of linguistic structure of the input text. Such information is even more important for story visualization since its inputs have an explicit narrative structure that needs to be translated into an image sequence (or visual story). Prior work in this domain has shown that there is ample room for improvement in the generated image sequence in terms of visual quality, consistency and relevance. In this paper, we first explore the use of constituency parse trees using a Transformer-based re…

2021-10-21cs.AIcs.CLcs.CV

DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge

Huawei Noah’s Ark Lab（华为诺亚方舟实验室）

Commonsense knowledge is crucial for artificial intelligence systems to understand natural language. Previous commonsense knowledge acquisition approaches typically rely on human annotations (for example, ATOMIC) or text generation models (for example, COMET.) Human annotation could provide high-quality commonsense knowledge, yet its high cost often results in relatively small scale and low coverage. On the other hand, generation models have the potential to automatically generate more knowledge. Nonetheless, machine learning models often fit the training data well and thus struggle to generat…

2021-02-18cs.AIcs.CL

更多相关论文收起更多论文

面向预训练语言模型的常识知识迁移

Commonsense Knowledge Transfer for Pre-trained Language Models

ETH Zurich（苏黎世联邦理工学院）；Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）

本文提出常识知识迁移框架，利用通用文本查询神经常识知识模型，并通过常识掩码填充与关系预测两个自监督目标增强预训练语言模型，在常识推理下游任务尤其少样本场景中取得稳定提升。

2023-06-04cs.AIcs.CLcs.LG

Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation

Indian Institute of Technology Patna（印度理工学院巴特那分校）；National Institute of Technology Karnataka, Surathkal（卡纳塔克国家理工学院苏拉特卡尔校区）

Grounding dialogue on external knowledge and interpreting linguistic patterns in dialogue history context, such as ellipsis, anaphora, and co-references is critical for dialogue comprehension and generation. In this paper, we present a novel open-domain dialogue generation model which effectively utilizes the large-scale commonsense and named entity based knowledge in addition to the unstructured topic-specific knowledge associated with each utterance. We enhance the commonsense knowledge with named entity-aware structures using co-references. Our proposed model utilizes a multi-hop attention …

2022-05-27cs.AIcs.CL

通过概念化获取并建模抽象常识知识

Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization

The Hong Kong University of Science and Technology（香港科技大学）

针对现有常识建模方法难以覆盖多样实体情境知识的问题，本研究提出基于概念化的抽象常识知识获取框架，结合ATOMIC、Probase构建抽象常识知识图谱，验证了其在常识推理等下游任务的有效性。

2024-05-18cs.AIcs.CL

基于常识推理和知识的场景描述图从图像到句子

From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge

Arizona State University（亚利桑那州立大学）；University of Maryland, College Park（马里兰大学帕克分校）

在本文中，我们提出了图像的语言描述的建设。这是通过使用自动构建的知识库从视觉场景中提取场景描述图（SDG）来实现的。SDG是通过愿景和推理构建的。具体而言，常识推理应用于（a）从给定图像上的现有感知方法获得的检测，（b）使用图像注释的自然语言处理构建的“常识”知识库，以及（c）来自诸如WordNet的资源的词汇本体知识。基于Amazon Mechanical Turk（AMT）的Flickr 8 k、Flickr 30 k和MS-COCO数据集的评估表明，在大多数情况下，通过我们的方法获得的SDG自动构建的句子比最近最先进的基于图像标题的方法更相关、更全面地描述了图像。我们的图像-句子对齐评估结果也可以与最近的最先进的方法相媲美。

2015-11-10cs.AIcs.CLcs.CV

Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations

National University of Singapore（新加坡国立大学）

Visual relationship detection aims to reason over relationships among salient objects in images, which has drawn increasing attention over the past few years. Inspired by human reasoning mechanisms, it is believed that external visual commonsense knowledge is beneficial for reasoning visual relationships of objects in images, which is however rarely considered in existing methods. In this paper, we propose a novel approach named Relational Visual-Linguistic Bidirectional Encoder Representations from Transformers (RVL-BERT), which performs relational reasoning with both visual and language comm…

2021-04-05cs.AIcs.CLcs.CV

时间常识推理与获取综述

An Overview Of Temporal Commonsense Reasoning and Acquisition

University of Innsbruck（因斯布鲁克大学）

本文综述时间常识推理与获取研究，指出大语言模型虽能生成正确句子但推理浅层，通过多种增强手段提升性能仍难及人类，强调谨慎解读评估结果并合理设计数据集与指标。

2023-11-16cs.AIcs.CLcs.LG

Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge

University of Science and Technology of China（中国科学技术大学）；York University（约克大学）；National Research Council Canada（加拿大国家研究委员会）；iFLYTEK Research（科大讯飞研究院）

In this paper, we propose commonsense knowledge enhanced embeddings (KEE) for solving the Pronoun Disambiguation Problems (PDP). The PDP task we investigate in this paper is a complex coreference resolution task which requires the utilization of commonsense knowledge. This task is a standard first round test set in the 2016 Winograd Schema Challenge. In this task, traditional linguistic features that are useful for coreference resolution, e.g. context and gender information, are no longer effective anymore. Therefore, the KEE models are proposed to provide a general framework to make use of co…

2016-12-22cs.AI

通过视频域中的因果动作-效应建模实现隐含可供性获取

Implicit Affordance Acquisition via Causal Action-Effect Modeling in the Video Domain

University of Stuttgart（斯图加特大学）

该研究为从视觉域获取可供性常识知识，构建CAE数据集并提出MAM、MEM两项预训练任务，经实验验证方法有效，且预训练模型在零样本物理推理任务上优于FLAVA等基线模型。

2023-12-18cs.AIcs.CL

Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis

Wuhan University（武汉大学）；JD Explore Academy（京东探索研究院）；Kunming University of Science and Technology（昆明理工大学）

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To better comprehend long complicated sentences and obtain accurate aspect-specific information, linguistic and commonsense knowledge are generally required in this task. However, most current methods employ complicated and inefficient approaches to incorporate external knowledge, e.g., directly searching the graph nodes. Additionally, the complementarity between external knowledge and linguistic information has not been thoroughly studied. To this end, we propose a knowledge graph augmented network KGAN, whic…

2023-03-14cs.AIcs.CL