@inproceedings{kulikov-etal-2019-importance,
    title = "Importance of Search and Evaluation Strategies in Neural Dialogue Modeling",
    author = "Kulikov, Ilia  and
      Miller, Alexander  and
      Cho, Kyunghyun  and
      Weston, Jason",
    editor = "van Deemter, Kees  and
      Lin, Chenghua  and
      Takamura, Hiroya",
    booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
    month = oct # "–" # nov,
    year = "2019",
    address = "Tokyo, Japan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W19-8609/",
    doi = "10.18653/v1/W19-8609",
    pages = "76--87",
    abstract = "We investigate the impact of search strategies in neural dialogue modeling. We first compare two standard search algorithms, greedy and beam search, as well as our newly proposed iterative beam search which produces a more diverse set of candidate responses. We evaluate these strategies in realistic full conversations with humans and propose a model-based Bayesian calibration to address annotator bias. These conversations are analyzed using two automatic metrics: log-probabilities assigned by the model and utterance diversity. Our experiments reveal that better search algorithms lead to higher rated conversations. However, finding the optimal selection mechanism to choose from a more diverse set of candidates is still an open question."
}