@inproceedings{fu-etal-2018-case,
    title = "A Case Study on Learning a Unified Encoder of Relations",
    author = "Fu, Lisheng  and
      Min, Bonan  and
      Nguyen, Thien Huu  and
      Grishman, Ralph",
    editor = "Xu, Wei  and
      Ritter, Alan  and
      Baldwin, Tim  and
      Rahimi, Afshin",
    booktitle = "Proceedings of the 2018 {EMNLP} Workshop W-{NUT}: The 4th Workshop on Noisy User-generated Text",
    month = nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/W18-6126/",
    doi = "10.18653/v1/W18-6126",
    pages = "202--207",
    abstract = "Typical relation extraction models are trained on a single corpus annotated with a pre-defined relation schema. An individual corpus is often small, and the models may often be biased or overfitted to the corpus. We hypothesize that we can learn a better representation by combining multiple relation datasets. We attempt to use a shared encoder to learn the unified feature representation and to augment it with regularization by adversarial training. The additional corpora feeding the encoder can help to learn a better feature representation layer even though the relation schemas are different. We use ACE05 and ERE datasets as our case study for experiments. The multi-task model obtains significant improvement on both datasets."
}