25 papers with code • 7 benchmarks • 5 datasets
Chinese named entity recognition is a subtask of information extraction that seeks to locate and classify named entities mentioned in unstructured text into pre-defined categories such as person names, organizations, locations, medical codes, time expressions, quantities, monetary values, percentages, etc. from Chinese text (Source: Adapted from Wikipedia).
Recently, pre-trained models have achieved state-of-the-art results in various language understanding tasks, which indicates that pre-training on large-scale corpora may play a crucial role in natural language processing.
Ranked #1 on Chinese Sentence Pair Classification on NLPCC-DBQA
We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration).
Ranked #3 on Chinese Sentiment Analysis on ChnSentiCorp Dev
The Bidirectional long short-term memory networks (BiLSTM) have been widely used as an encoder in models solving the named entity recognition (NER) task.
Ranked #8 on Chinese Named Entity Recognition on Resume NER
We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon.
Ranked #10 on Chinese Named Entity Recognition on Resume NER
In this paper, we introduce the NER dataset from CLUE organization (CLUENER2020), a well-defined fine-grained dataset for named entity recognition in Chinese.
Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information.
Ranked #2 on Chinese Named Entity Recognition on MSRA
Moreover, it is shown that reasonable performance can be obtained when ZEN is trained on a small corpus, which is important for applying pre-training techniques to scenarios with limited data.
Ranked #1 on Chinese Sentiment Analysis on ChnSentiCorp Dev (F1 metric)
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 Word Segmentation on PKU
This method avoids designing a complicated sequence modeling architecture, and for any neural NER model, it requires only subtle adjustment of the character representation layer to introduce the lexicon information.
Ranked #6 on Chinese Named Entity Recognition on Resume NER
Instead of treating the task of NER as a sequence labeling problem, we propose to formulate it as a machine reading comprehension (MRC) task.
Ranked #1 on Nested Mention Recognition on ACE 2004 (using extra training data)