@inproceedings{sundararaman-etal-2020-methods,
    title = "Methods for Numeracy-Preserving Word Embeddings",
    author = "Sundararaman, Dhanasekar  and
      Si, Shijing  and
      Subramanian, Vivek  and
      Wang, Guoyin  and
      Hazarika, Devamanyu  and
      Carin, Lawrence",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.emnlp-main.384",
    doi = "10.18653/v1/2020.emnlp-main.384",
    pages = "4742--4753",
    abstract = "Word embedding models are typically able to capture the semantics of words via the distributional hypothesis, but fail to capture the numerical properties of numbers that appear in the text. This leads to problems with numerical reasoning involving tasks such as question answering. We propose a new methodology to assign and learn embeddings for numbers. Our approach creates Deterministic, Independent-of-Corpus Embeddings (the model is referred to as DICE) for numbers, such that their cosine similarity reflects the actual distance on the number line. DICE outperforms a wide range of pre-trained word embedding models across multiple examples of two tasks: (i) evaluating the ability to capture numeration and magnitude; and (ii) to perform list maximum, decoding, and addition. We further explore the utility of these embeddings in downstream tasks, by initializing numbers with our approach for the task of magnitude prediction. We also introduce a regularization approach to learn model-based embeddings of numbers in a contextual setting.",
}