COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs

• URL: http://arxiv.org/abs/2010.05953v2
• Date: Thu, 16 Dec 2021 18:57:18 GMT
• Title: COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
• Authors: Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, Yejin Choi
• Abstract summary: We show that manually constructed commonsense knowledge graphs (CSKGs) will never achieve the coverage necessary to be applicable in all situations encountered by NLP agents. We propose ATOMIC 2020, a new CSKG of general-purpose commonsense knowledge containing knowledge that is not readily available in pretrained language models. We evaluate its properties in comparison with other leading CSKGs, performing the first large-scale pairwise study of commonsense knowledge resources.
• Score: 82.8453695903687
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent years have brought about a renewed interest in commonsense representation and reasoning in the field of natural language understanding. The development of new commonsense knowledge graphs (CSKG) has been central to these advances as their diverse facts can be used and referenced by machine learning models for tackling new and challenging tasks. At the same time, there remain questions about the quality and coverage of these resources due to the massive scale required to comprehensively encompass general commonsense knowledge. In this work, we posit that manually constructed CSKGs will never achieve the coverage necessary to be applicable in all situations encountered by NLP agents. Therefore, we propose a new evaluation framework for testing the utility of KGs based on how effectively implicit knowledge representations can be learned from them. With this new goal, we propose ATOMIC 2020, a new CSKG of general-purpose commonsense knowledge containing knowledge that is not readily available in pretrained language models. We evaluate its properties in comparison with other leading CSKGs, performing the first large-scale pairwise study of commonsense knowledge resources. Next, we show that ATOMIC 2020 is better suited for training knowledge models that can generate accurate, representative knowledge for new, unseen entities and events. Finally, through human evaluation, we show that the few-shot performance of GPT-3 (175B parameters), while impressive, remains ~12 absolute points lower than a BART-based knowledge model trained on ATOMIC 2020 despite using over 430x fewer parameters.

Related papers

• Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution [48.86322922826514]
  This paper defines a new task of Knowledge-aware Language Model Attribution (KaLMA) First, we extend attribution source from unstructured texts to Knowledge Graph (KG), whose rich structures benefit both the attribution performance and working scenarios. Second, we propose a new Conscious Incompetence" setting considering the incomplete knowledge repository. Third, we propose a comprehensive automatic evaluation metric encompassing text quality, citation quality, and text citation alignment.
  arXiv  Detail & Related papers  (2023-10-09T11:45:59Z)
• Rethinking Language Models as Symbolic Knowledge Graphs [7.192286645674803]
  Symbolic knowledge graphs (KGs) play a pivotal role in knowledge-centric applications such as search, question answering and recommendation. We construct nine qualitative benchmarks that encompass a spectrum of attributes including symmetry, asymmetry, hierarchy, bidirectionality, compositionality, paths, entity-centricity, bias and ambiguity.
  arXiv  Detail & Related papers  (2023-08-25T21:25:08Z)
• ComFact: A Benchmark for Linking Contextual Commonsense Knowledge [31.19689856957576]
  We propose the new task of commonsense fact linking, where models are given contexts and trained to identify situationally-relevant commonsense knowledge from KGs. Our novel benchmark, ComFact, contains 293k in-context relevance annotations for commonsense across four stylistically diverse datasets.
  arXiv  Detail & Related papers  (2022-10-23T09:30:39Z)
• BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models [65.51390418485207]
  We propose a new approach of harvesting massive KGs of arbitrary relations from pretrained LMs. With minimal input of a relation definition, the approach efficiently searches in the vast entity pair space to extract diverse accurate knowledge. We deploy the approach to harvest KGs of over 400 new relations from different LMs.
  arXiv  Detail & Related papers  (2022-06-28T19:46:29Z)
• Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models [89.98762327725112]
  Commonsense reasoning in natural language is a desired ability of artificial intelligent systems. For solving complex commonsense reasoning tasks, a typical solution is to enhance pre-trained language models(PTMs) with a knowledge-aware graph neural network(GNN) encoder. Despite the effectiveness, these approaches are built on heavy architectures, and can't clearly explain how external knowledge resources improve the reasoning capacity of PTMs.
  arXiv  Detail & Related papers  (2022-05-04T01:27:36Z)
• Low-resource Learning with Knowledge Graphs: A Comprehensive Survey [34.18863318808325]
  Machine learning methods often rely on a number of labeled samples for training. Low-resource learning aims to learn robust prediction models with no enough resources. Knowledge Graph (KG) is becoming more and more popular for knowledge representation.
  arXiv  Detail & Related papers  (2021-12-18T21:40:50Z)
• DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding [19.478288026844893]
  Knowledge-Enhanced Pre-trained Language Models (KEPLMs) are pre-trained models with relation triples injecting from knowledge graphs to improve language understanding abilities. Previous studies integrate models with knowledge encoders for representing knowledge retrieved from knowledge graphs. We propose a novel KEPLM named DKPLM that Decomposes Knowledge injection process of the Pre-trained Language Models in pre-training, fine-tuning and inference stages.
  arXiv  Detail & Related papers  (2021-12-02T08:19:42Z)
• DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge [42.08569149041291]
  We propose an alternative commonsense knowledge acquisition framework DISCOS. DISCOS populates expensive commonsense knowledge to more affordable linguistic knowledge resources. We can acquire 3.4M ATOMIC-like inferential commonsense knowledge by populating ATOMIC on the core part of ASER.
  arXiv  Detail & Related papers  (2021-01-01T03:30:38Z)
• All About Knowledge Graphs for Actions [82.39684757372075]
  We propose a better understanding of knowledge graphs (KGs) that can be utilized for zero-shot and few-shot action recognition. We study three different construction mechanisms for KGs: action embeddings, action-object embeddings, visual embeddings. We present extensive analysis of the impact of different KGs on different experimental setups.
  arXiv  Detail & Related papers  (2020-08-28T01:44:01Z)
• Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers [54.417299589288184]
  We investigate models for complementing the distributional knowledge of BERT with conceptual knowledge from ConceptNet and its corresponding Open Mind Common Sense (OMCS) corpus. Our adapter-based models substantially outperform BERT on inference tasks that require the type of conceptual knowledge explicitly present in ConceptNet and OMCS.
  arXiv  Detail & Related papers  (2020-05-24T15:49:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.