• Publications
  • Influence
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
TLDR
A new version of the linked open data resource ConceptNet is presented that is particularly well suited to be used with modern NLP techniques such as word embeddings, 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.
Representing General Relational Knowledge in ConceptNet 5
TLDR
The latest iteration of ConceptNet 5 is presented, including its fundamental design decisions, ways to use it, and evaluations of its coverage and accuracy.
ConceptNet 3 : a Flexible , Multilingual Semantic Network for Common Sense Knowledge
TLDR
ConceptNet 3 is presented, which improves the acquisition of new knowledge in ConceptNet and facilitates turning edges of the network back into natural language, and it is shown how its modular design helps it adapt to different data sets and languages.
New Avenues in Opinion Mining and Sentiment Analysis
TLDR
The history, current use, and future of opinion mining and sentiment analysis are discussed, along with relevant techniques and tools.
ConceptNet 5: A Large Semantic Network for Relational Knowledge
TLDR
The latest iteration of ConceptNet is presented, ConceptNet 5, with a focus on its fundamental design decisions and ways to interoperate with it.
SenticNet: A Publicly Available Semantic Resource for Opinion Mining
TLDR
SenticNet is a publicly available resource for opinion mining built exploiting AI and Semantic Web techniques and uses dimensionality reduction to infer the polarity of common sense concepts and hence provide a public resource for mining opinions from natural language text at a semantic, rather than just syntactic, level.
AnalogySpace: Reducing the Dimensionality of Common Sense Knowledge
TLDR
Analogy Space is presented, which accomplishes this by forming the analogical closure of a semantic network through dimensionality reduction, which self-organizes concepts around dimensions that can be seen as making distinctions such as "good vs. bad" or "easy vs. hard".
SenticNet 2: A Semantic and Affective Resource for Opinion Mining and Sentiment Analysis
TLDR
By providing the semantics and sentics associated with over 14,000 concepts, SenticNet 2 represents one of the most comprehensive semantic resources for the development of affect-sensitive applications in fields such as social data mining, multimodal affective HCI, and social media marketing.
Digital Intuition: Applying Common Sense Using Dimensionality Reduction
TLDR
A method that uses singular value decomposition to aid in the integration of systems or representations, and can be harnessed to find and exploit correlations between different resources, enabling commonsense reasoning over a broader domain.
...
1
2
3
4
5
...