Dependency issue: it requires (a lot of) training data and it is domain-dependent.
Consistency issue: different training and/or tweaking lead to different results.
Transparency issue: the reasoning process is uninterpretable (black-box algorithms).
Sentic computing (Cambria and Hussain 2015) addresses these issues in the context of natural language processing (NLP) by coupling machine learning with linguistics and commonsense reasoning. In particular, we apply an ensemble of commonsense-driven linguistic patterns and statistical NLP: the former are triggered when prior knowledge is available, the latter is used as backup plan when both semantics and sentence structure are unknown. Machine learning, in fact, is only useful to make a good guessbecause it only encodes correlation and...
- Cambria, E., Chandra, P., Sharma, A., & Hussain, A. (2010). Do not feel the trolls. In ISWC. ShanghaiGoogle Scholar
- Cambria, E., Olsher, D., & Kwok, K. (2012c). Sentic activation: A two-level affective common sense reasoning framework. In AAAI (pp. 186–192). Toronto.Google Scholar
- Cambria, E., Fu, J., Bisio, F., & Poria, S. (2015a). AffectiveSpace 2: Enabling affective intuition for concept-level sentiment analysis. In AAAI (pp. 508–514). Austin.Google Scholar
- Cambria, E., Rajagopal, D., Kwok, K., & Sepulveda, J. (2015b). GECKA: Game engine for commonsense knowledge acquisition. In FLAIRS (pp. 282–287).Google Scholar
- Cambria, E., Poria, S., Hazarika, D., & Kwok, K. (2018). SenticNet 5: Discovering conceptual primitives for sentiment analysis by means of context embeddings. In AAAI (pp. 1795-1802). New Orleans.Google Scholar
- Cavallari, S., Zheng, V., Cai, H., Chang, K., & Cambria, E. (2017). Learning community embedding with community detection and node embedding on graphs. In CIKM (pp. 377–386). Singapore.Google Scholar
- Ma, Y., Cambria, E., & Gao, S. (2016). Label embedding for zero-shot fine-grained named entity typing. In COLING (pp. 171–180). Osaka.Google Scholar
- Ma, Y., Peng, H., & Cambria, E. (2018). Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM. In AAAI (pp. 5876-5883). New Orleans.Google Scholar
- Poria, S., Cambria, E., Hazarika, D., & Vij, P. (2016). A deeper look into sarcastic tweets using deep convolutional neural networks. In COLING (pp. 1601–1612). Osaka.Google Scholar
- Xing, F., Cambria, E., & Welsch, R. (2018). Natural language based financial forecasting: A survey. Artificial Intelligence Review. https://doi.org/10.1007/s10462-017-9588-9.
- Young, T., Cambria, E., Chaturvedi, I., Zhou, H., Biswas, S., & Huang, M. (2018). Augmenting end-to-end dialog systems with commonsense knowledge. In AAAI (pp. 4970-4977). New Orleans.Google Scholar
- Zadeh, A., Liang, P. P., Poria, S., Vij, P., Cambria, E., & Morency, L.-P. (2018). Multi-attention recurrent network for human communication comprehension. In AAAI (pp. 5642-5649). New Orleans.Google Scholar