ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
By Robyn Speer, Joshua Chin, Catherine Havasi. 2016
3,335 citations recorded by the source corpus.
Machine learning about language can be improved by supplying it with specific knowledge and sources of external information. We present here a new version of the linked open data resource ConceptNet that is particularly well suited to be used with modern NLP techniques such as word embeddings. ConceptNet is a knowledge graph that connects words and phrases of natural language with labeled edges. Its knowledge is collected from many sources that include expert-created resources, crowd-sourcing, and games with a purpose. It is designed to represent the general knowledge involved in understanding language, improving natural language applications by allowing the application to better understand the meanings behind the words people use. When ConceptNet is combined with word embeddings acquired from distributional semantics (such as word2vec), it provides applications with understanding that they would not acquire from distributional semantics alone, nor from narrower resources such as WordNet or DBPedia. We demonstrate this with state-of-the-art results on intrinsic evaluations of word relatedness that translate into improvements on applications of word vectors, including solving SAT-style analogies.
Subfields: Artificial Intelligence, Molecular Biology, Evaluation & Benchmarks, Knowledge Graphs & Representation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Yejin Choi
- Jianfeng Gao
- Percy Liang
- Luke S. Zettlemoyer
- Noah A. Smith
- Hannaneh Hajishirzi
- Graham Neubig
In Molecular Biology
- Xiang Ren
- Percy Liang
- Iryna Gurevych
- Mohit Bansal
- Christopher D. Manning
- Yoav Goldberg
- Yejin Choi
- Noah A. Smith
In Evaluation & Benchmarks
- Yejin Choi
- Mohit Bansal
- Hannaneh Hajishirzi
- Ashish Sabharwal
- Samuel R. Bowman
- Jonathan Berant
- Daniel Khashabi
- Chitta Baral
In Knowledge Graphs & Representation
- Yejin Choi
- Xiang Ren
- Ronan Le Bras
- Mohit Bansal
- Adyasha Maharana
- Jure Leskovec
- Chandra Bhagavatula
- Michihiro Yasunaga
Citations in the corpus
- SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (2018, methodology): “ConceptNet knowledge base (Speer et al., 2017).”
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering (2018, methodology): “This suggests that ConceptNet is either not a good source of knowledge for our task, or only a subset of its relations should be considered.”
- Improving Question Answering with External Knowledge (2019, background): “We argue that questions in the ARC-Challenge tend to require more external knowledge for reasoning, similar to the observation of Sugawara et al. (2018) (30.0% vs. 20.0%).”
- CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge (2019, methodology): “, 2014) and 300d Numberbatch CONCEPTNET node embeddings (Speer et al., 2017), which are kept fixed at training time.”
- Knowledge Enhanced Contextual Word Representations (2019, methodology): “However, the method could be extended to commonsense KBs such as ConceptNet (Speer et al., 2017) or domain specific ones (e.g., UMLS; Bodenreider, 2004).”
- STaR: Bootstrapping Reasoning With Reasoning (2022, methodology): “CommonsenseQA The multiple-choice commonsense reasoning task, CommonsenseQA [10] (CQA), is constructed from ConceptNet, a semantic graph of concepts and their relationships with over a million nodes [28].”
- CommonsenseQA 2.0: Exposing the Limits of AI through Gamification (2021, methodology): “(false); and 73K automaticallygenerated yes/no questions from CONCEPTNET triplets, where we transform triplets to assertions with a manually-constructed template for each CONCEPTNET relation.”
- Symbolic Knowledge Distillation: from General Language Models to Commonsense Models (2021, background): “ConceptNet (Speer et al., 2017) focuses on taxonomic knowledge and physical commonsense, much of which is authored by humans or compiled from such sources.”
- AdapterFusion: Non-Destructive Task Composition for Transfer Learning (2020, neutral): “Commonsense QA (Talmor et al., 2019) is a multiple choice data set based on ConceptNet (Speer et al., 2017), which requires reasoning over general knowledge.”
- Learning How to Ask: Querying LMs with Mixtures of Soft Prompts (2021, methodology): “The relations we learn to predict are T-REx original (Elsahar et al., 2018), T-REx extended (Shin et al., 2020), Google-RE (Orr, 2013), and ConceptNet (Speer et al., 2017)—or rather, the subsets that were used by the LAMA and AutoPrompt papers.”
- An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA (2021, methodology): “Previous studies (Wang et al. 2015; Narasimhan and Schwing 2018; Wang et al. 2017; Narasimhan, Lazebnik, and Schwing 2018; Zhu et al. 2020; Li, Wang, and Zhu 2020; Marino et al. 2021; Wu et al. 2021) proposed various ways of retrieving and using the knowledge, and considered it necessary to use mult”
- Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution (2020, background): “To cover the diverse topic meme is referencing from, we will also need a sizeable knowledge graph like wiki-data or ConceptNet[12] to compensate for it.”
- Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets (2019, background): “Questions were written by crowdworkers, who try to bridge between two concepts extracted from CONCEPTNET (Speer et al., 2017) # examples # annotators MNLI (matched) 402,517 380 OPENBOOKQA 5,457 84 COMMONSENSEQA 11,096 132”
- The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task (2017, methodology): “This research was supported in part by Darpa CwC program through ARO (W911NF-15-1-0543), Samsung GRO, NSF IIS1524371, and gifts from Google and Facebook.”
- CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning (2020, methodology): “We first conduct part-of-speech tagging over all sentences in the corpora such that words in sentences can be matched to the concept vocabulary of ConceptNet.”
- COMET: Commonsense Transformers for Automatic Knowledge Graph Construction (2019, methodology): “(2016), consists of tuples obtained from the Open Mind Common Sense (OMCS) entries in ConceptNet 5 (Speer et al., 2017).”
- Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources (2021, methodology): “We also compare ConceptNet (Speer et al., 2017) and GenericsKB (Bhakthavatsalam et al., 2020) on the “ Religion ” category and find similar polarized perceptions of certain groups, despite a much larger percentage range for GenericsKB. triples in ConceptNet is 4.5% (4.6k triples) for sentiment and…”