@inproceedings{choi-etal-2018-element,
    title = "Element-wise Bilinear Interaction for Sentence Matching",
    author = "Choi, Jihun  and
      Kim, Taeuk  and
      Lee, Sang-goo",
    editor = "Nissim, Malvina  and
      Berant, Jonathan  and
      Lenci, Alessandro",
    booktitle = "Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/S18-2012/",
    doi = "10.18653/v1/S18-2012",
    pages = "107--112",
    abstract = "When we build a neural network model predicting the relationship between two sentences, the most general and intuitive approach is to use a Siamese architecture, where the sentence vectors obtained from a shared encoder is given as input to a classifier. For the classifier to work effectively, it is important to extract appropriate features from the two vectors and feed them as input. There exist several previous works that suggest heuristic-based function for matching sentence vectors, however it cannot be said that the heuristics tailored for a specific task generalize to other tasks. In this work, we propose a new matching function, ElBiS, that learns to model element-wise interaction between two vectors. From experiments, we empirically demonstrate that the proposed ElBiS matching function outperforms the concatenation-based or heuristic-based matching functions on natural language inference and paraphrase identification, while maintaining the fused representation compact."
}