5 papers with code • 2 benchmarks • 0 datasets
Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data.
Ranked #1 on Dependency Parsing on NLPCC-2019
However, due to the lack of rich pictographic evidence in glyphs and the weak generalization ability of standard computer vision models on character data, an effective way to utilize the glyph information remains to be found.
Ranked #1 on Chinese Sentence Pair Classification on XNLI (Accuracy metric)
During the past decades, due to the lack of sufficient labeled data, most studies on cross-domain parsing focus on unsupervised domain adaptation, assuming there is no target-domain training data.
In the training of transition-based dependency parsers, an oracle is used to predict a transition sequence for a sentence and its gold tree.
Shi, Huang, and Lee (2017) obtained state-of-the-art results for English and Chinese dependency parsing by combining dynamic-programming implementations of transition-based dependency parsers with a minimal set of bidirectional LSTM features.