@inproceedings{poerner-schutze-2019-multi,
    title = "Multi-View Domain Adapted Sentence Embeddings for Low-Resource Unsupervised Duplicate Question Detection",
    author = {Poerner, Nina  and
      Sch{\"u}tze, Hinrich},
    editor = "Inui, Kentaro  and
      Jiang, Jing  and
      Ng, Vincent  and
      Wan, Xiaojun",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D19-1173/",
    doi = "10.18653/v1/D19-1173",
    pages = "1630--1641",
    abstract = "We address the problem of Duplicate Question Detection (DQD) in low-resource domain-specific Community Question Answering forums. Our multi-view framework MV-DASE combines an ensemble of sentence encoders via Generalized Canonical Correlation Analysis, using unlabeled data only. In our experiments, the ensemble includes generic and domain-specific averaged word embeddings, domain-finetuned BERT and the Universal Sentence Encoder. We evaluate MV-DASE on the CQADupStack corpus and on additional low-resource Stack Exchange forums. Combining the strengths of different encoders, we significantly outperform BM25, all single-view systems as well as a recent supervised domain-adversarial DQD method."
}