Fortunately, Discourse Markers Can Enhance Language Models for Sentiment Analysis


  • Liat Ein-Dor IBM Research AI
  • Ilya Shnayderman IBM
  • Artem Spector IBM
  • Lena Dankin IBM Research AI
  • Ranit Aharonov IBM Research and Pangea Therapeutics
  • Noam Slonim IBM



Speech & Natural Language Processing (SNLP)


In recent years, pretrained language models have revolutionized the NLP world, while achieving state of the art performance in various downstream tasks. However, in many cases, these models do not perform well when labeled data is scarce and the model is expected to perform in the zero or few shot setting. Recently, several works have shown that continual pretraining or performing a second phase of pretraining (inter-training) which is better aligned with the downstream task, can lead to improved results, especially in the scarce data setting. Here, we propose to leverage sentiment-carrying discourse markers to generate large-scale weakly-labeled data, which in turn can be used to adapt language models for sentiment analysis. Extensive experimental results show the value of our approach on various benchmark datasets, including the finance domain. Code, models and data are available at




How to Cite

Ein-Dor, L., Shnayderman, I., Spector, A., Dankin, L., Aharonov, R., & Slonim, N. (2022). Fortunately, Discourse Markers Can Enhance Language Models for Sentiment Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 10608-10617.



AAAI Technical Track on Speech and Natural Language Processing