Chinese NER Using Lattice LSTM (P18-1)

Copied to clipboard

Challenge: Chinese named entity recognition (NER) is a fundamental task in information extraction.
Approach: They propose a lattice-structured LSTM model for Chinese named entity recognition (NER) model leverages word and word sequence information to encode a sequence of input characters and all potential words that match a lexicon.
Outcome: The proposed model outperforms word-based and character-based models on Chinese NER datasets.

Similar Papers

An Encoding Strategy Based Word-Character LSTM for Chinese NER (N19-1)

Copied to clipboard

Challenge: Existing word-based model can not be trained in batches due to its DAG structure.
Approach: They propose a lattice model that integrates word information into the start or end characters of a word and integrates it into a fixed-sized representation for efficient batch training.
Outcome: The proposed model outperforms other state-of-the-art models on benchmark datasets and shows that it can be trained in batches without a shortcut path.
Simplify the Usage of Lexicon in Chinese NER (2020.acl-main)

Copied to clipboard

Challenge: Named entity recognition (NER) is concerned with the identification of named entities in unstructured text.
Approach: They propose a method for incorporating word lexicon into character representations . experimental results show method can be easily incorporated with pre-trained models .
Outcome: The proposed method achieves 6.15 times faster inference speed and better performance on four benchmark Chinese NER datasets.
Subword Encoding in Lattice LSTM for Chinese Word Segmentation (N19-1)

Copied to clipboard

Challenge: Using subwords, Chinese word segmentation models use character combination information to disambiguate characters.
Approach: They propose a subword-based neural word segmentor that integrates character embeddings into a Lattice LSTM network over a character sequence.
Outcome: The proposed model can utilize abundant character combination information, which is effective to disambiguate characters.
State-of-the-art Chinese Word Segmentation with Bi-LSTMs (D18-1)

Copied to clipboard

Challenge: A wide variety of neural-network architectures have been proposed for the task of Chinese word segmentation.
Approach: They propose a bidirectional LSTM model with standard deep learning techniques and best practices for the task of Chinese word segmentation.
Outcome: The proposed model outperforms models based on standard deep learning techniques and best practices on Chinese word segmentation datasets.
FLAT: Chinese NER Using Flat-Lattice Transformer (2020.acl-main)

Copied to clipboard

Challenge: Named entity recognition (NER) models are difficult to use because of the complex nature of the lattice structure and the low inference speed.
Approach: They propose a character-word lattice structure that converts lattics into flat structures consisting of spans.
Outcome: The proposed model outperforms other lexicon-based models on four datasets and is highly parallel.
Porous Lattice Transformer Encoder for Chinese NER (2020.coling-main)

Copied to clipboard

Challenge: Existing methods to integrate word boundary information into character-level Chinese NER are inefficient and lack semantic interaction.
Approach: They propose an extension of transformer encoder that is tailored for ChineseNER to incorporate lexicons into character-level Chinese NER by lattices.
Outcome: The proposed extension performs 11.4 times faster than state-of-the-art methods while retaining the rich long-term dependencies.
Lattice Transformer for Speech Translation (P19-1)

Copied to clipboard

Challenge: Recent advances in sequence modeling have highlighted the strengths of the transformer architecture.
Approach: They propose a general lattice transformer for speech translation where the input is the output of the automatic speech recognition (ASR) they propose 'controllable' lattica attention mechanism to consume latent representations.
Outcome: The proposed model outperforms baseline and lattice LSTM on the Chinese-English translation task.
Lattice-Based Transformer Encoder for Neural Machine Translation (P19-1)

Copied to clipboard

Challenge: Neural machine translation (NMT) takes deterministic sequences for source representations. However, word-level or subword-level segmentation has multiple choices to split a source sequence with different word segmentors or different subword vocabulary sizes.
Approach: They propose lattice-based encoders to explore effective word or subword representations in an automatic way during training.
Outcome: The proposed encoders can explore effective word or subword representation in an automatic way during training.
Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context (2021.emnlp-main)

Copied to clipboard

Challenge: Existing datasets for word prediction with long-range context have not been tested.
Approach: They propose automatic and manual selection strategies tailored to Chinese to ensure that target words can only be predicted with long-term context.
Outcome: The proposed model is 45 points behind human in terms of top-1 word prediction accuracy.
Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese (2021.acl-short)

Copied to clipboard

Challenge: Neural semantic parsers have obtained acceptable results in parsing DRSs . previous studies have focused on parse of DRS in English, but have focused only on a few languages .
Approach: They propose to use character sequences as input to map meaning representations to string format.
Outcome: The proposed models learn the meaning of a series of semantic phenomena by taking sentences as input and outputting the corresponding DRSs, without the aid of any extra linguistic information.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations