@inproceedings{derby-etal-2018-representation,
    title = "Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model",
    author = "Derby, Steven  and
      Miller, Paul  and
      Murphy, Brian  and
      Devereux, Barry",
    editor = "Linzen, Tal  and
      Chrupa{\l}a, Grzegorz  and
      Alishahi, Afra",
    booktitle = "Proceedings of the 2018 {EMNLP} Workshop {B}lackbox{NLP}: Analyzing and Interpreting Neural Networks for {NLP}",
    month = nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W18-5449/",
    doi = "10.18653/v1/W18-5449",
    pages = "362--364",
    abstract = "Performance in language modelling has been significantly improved by training recurrent neural networks on large corpora. This progress has come at the cost of interpretability and an understanding of how these architectures function, making principled development of better language models more difficult. We look inside a state-of-the-art neural language model to analyse how this model represents high-level lexico-semantic information. In particular, we investigate how the model represents words by extracting activation patterns where they occur in the text, and compare these representations directly to human semantic knowledge."
}