@inproceedings{roussinov-etal-2020-recognizing,
    title = "Recognizing Semantic Relations by Combining Transformers and Fully Connected Models",
    author = "Roussinov, Dmitri  and
      Sharoff, Serge  and
      Puchnina, Nadezhda",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.lrec-1.715/",
    pages = "5838--5845",
    language = "eng",
    ISBN = "979-10-95546-34-4",
    abstract = "Automatically recognizing an existing semantic relation (e.g. {\textquotedblleft}is a{\textquotedblright}, {\textquotedblleft}part of{\textquotedblright}, {\textquotedblleft}property of{\textquotedblright}, {\textquotedblleft}opposite of{\textquotedblright} etc.) between two words (phrases, concepts, etc.) is an important task affecting many NLP applications and has been subject of extensive experimentation and modeling. Current approaches to automatically telling if a relation exists between two given concepts X and Y can be grouped into two types: 1) those modeling word-paths connecting X and Y in text and 2) those modeling distributional properties of X and Y separately, not necessary in the proximity to each other. Here, we investigate how both types can be improved and combined. We suggest a distributional approach that is based on an attention-based transformer. We have also developed a novel word path model that combines useful properties of a convolutional network with a fully connected language model. While our transformer-based approach works better, both our models significantly outperform the state-of-the-art within their classes of approaches. We also demonstrate that combining the two approaches results in additional gains since they use somewhat different data sources."
}