@inproceedings{liu-etal-2018-recurrent,
    title = "Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis",
    author = "Liu, Fei  and
      Cohn, Trevor  and
      Baldwin, Timothy",
    editor = "Walker, Marilyn  and
      Ji, Heng  and
      Stent, Amanda",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/N18-2045/",
    doi = "10.18653/v1/N18-2045",
    pages = "278--283",
    abstract = "While neural networks have been shown to achieve impressive results for sentence-level sentiment analysis, targeted aspect-based sentiment analysis (TABSA) {---} extraction of fine-grained opinion polarity w.r.t. a pre-defined set of aspects {---} remains a difficult task. Motivated by recent advances in memory-augmented models for machine reading, we propose a novel architecture, utilising external {\textquotedblleft}memory chains{\textquotedblright} with a delayed memory update mechanism to track entities. On a TABSA task, the proposed model demonstrates substantial improvements over state-of-the-art approaches, including those using external knowledge bases."
}