SenticNet 5: Discovering Conceptual Primitives for Sentiment Analysis by Means of Context Embeddings
By Erik Cambria, Soujanya Poria, Devamanyu Hazarika, Kenneth Kwok. AAAI Conference on Artificial Intelligence, 2018
408 citations recorded by the source corpus.
With the recent development of deep learning, research in AI has gained new vigor and prominence. While machine learning has succeeded in revitalizing many research fields, such as computer vision, speech recognition, and medical diagnosis, we are yet to witness impressive progress in natural language understanding. One of the reasons behind this unmatched expectation is that, while a bottom-up approach is feasible for pattern recognition, reasoning and understanding often require a top-down approach. In this work, we couple sub-symbolic and symbolic AI to automatically discover conceptual primitives from text and link them to commonsense concepts and named entities in a new three-level knowledge representation for sentiment analysis. In particular, we employ recurrent neural networks to infer primitives by lexical substitution and use them for grounding common and commonsense knowledge by means of multi-dimensional scaling.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/f48c054ffee13a0df48975ba0cd8fb93872080ef
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
- Soujanya Poria
- Erik Cambria
- Devamanyu Hazarika
- Navonil Majumder
- Louis-philippe Morency
- Amir Zadeh
- Rada Mihalcea
- Alexander Gelbukh
Citations in the corpus
- KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis (2020, background): “In this domain-specific scenario, commonsense knowledge provides a dynamic way to enhance the context and help models understand sentiment-bearing terms and opinion targets through its structural relations (Cambria et al., 2018).”
- A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “SenticNet [184] learns conceptual primitives for sentiment analysis, which can also be used as a commonsense knowledge source.”
- Recent trends in deep learning based personality detection (2019, methodology): “Audio features such asMFCC, ZCR, spectral energy distribution and speaking rate are extracted using OpenSMILE (Eyben et al. 2010) and SenticNet is used for polarity detection from text.”
- SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis (2020, neutral): “, WordNet-Affect [55], SentiWordNet [3], and SenticNet [10].”
- Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos (2018, background): “…been instrumental in the progress of multiple research problems, e.g., question-answering (Weston et al., 2014; Sukhbaatar et al., 2015; Kumar et al., 2016), machine translation (Bahdanau et al., 2014), speech recognition (Graves et al., 2014), and common-sense reasoning (Cambria et al., 2018).”
- A survey on empathetic dialogue systems (2020, background): “Additionally, commonsense computing [130] aims o develop large-scale commonsense knowledge bases, e.g., Conceptet [131] and SenticNet [132] , that can be automatically built and upated over time.”
- Transformer models for text-based emotion detection: a review of BERT-based approaches (2021, methodology): “They extracted psycholinguistic features using the Mairesse (Mairesse et al. 2007), SenticNet (Cambria et al. 2018), NRC Emotion Lexicon (Mohammad and Tur-ney 2013), the VAD lexicon (Mohammad 2018) and the Readability.”