English semantic dependency parsing models are trained on [DM data introduced in SemEval-2014 task 8](https://catalog.ldc.upenn.edu/LDC2016T10), while Chinese models are trained on [NEWS domain data of corpora from SemEval-2016 Task 9](https://github.com/HIT-SCIR/SemEval-2016).

Our data preprocessing steps follow [Second_Order_SDP](https://github.com/wangxinyu0922/Second_Order_SDP).

'biaffine-sdp-zh': 'semeval16.biaffine.sdp.lstm.tag-char-lemma',

'vi-sdp-en': 'dm.vi.sdp.lstm.tag-char-lemma',

'vi-sdp-zh': 'semeval16.vi.sdp.lstm.tag-char-lemma',

}

MODEL = {n: f"{SRC['github']}/v{__version__}/{m}.zip" for n, m in NAME.items()}

CONFIG = {n: f"{SRC['github']}/v{__version__}/{m}.ini" for n, m in NAME.items()}

parser.add_argument('--device', '-d', default='-1', help='ID of GPU to use')

parser.add_argument('--seed', '-s', default=1, type=int, help='seed for generating random numbers')

parser.add_argument('--threads', '-t', default=16, type=int, help='max num of threads')

parser.add_argument("--local_rank", type=int, default=-1, help='node rank for distributed training')

args, unknown = parser.parse_known_args()

args, unknown = parser.parse_known_args(unknown, args)