Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings

By Nanyun Peng, Mark Dredze. Conference on Empirical Methods in Natural Language Processing, 2015

374 citations recorded by the source corpus.

We consider the task of named entity recognition for Chinese social media. The long line of work in Chinese NER has focused on formal domains, and NER for social media has been largely restricted to English. We present a new corpus of Weibo messages annotated for both name and nominal mentions. Additionally, we evaluate three types of neural embeddings for representing Chinese text. Finally, we propose a joint training objective for the embeddings that makes use of both (NER) labeled and unlabeled raw text. Our methods yield a 9% improvement over a stateof-the-art baseline.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/d64561879a2fbd3d39a5e876a667ffa4561eed80

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Generalize Across Tasks: Efficient Algorithms for Linear Representation Learning (2019, background): “It is also common to seed NLP algorithms with word embeddings and then optimize the embedding for the particular downstream task at hand (e.g. Peng and Dredze, 2015).”
Named Entity Recognition for Social Media Texts with Semantic Augmentation (2020, methodology): “In doing so, for each token x i ∈ X , we use pre-trained word embeddings (e.g., GloVe for English and Tencent Embedding for Chinese) to extract the top m words that are most similar to x i based on cosine similarities and denote them as Afterwards, we use another embedding matrix to map all extracte”
A Comprehensive Overview of Large Language Models (2023, neutral): “Type Datasets/Benchmarks Multi-Task MMLU [242], SuperGLUE [3], BIG-bench [243], GLUE [244], BBH [243], CUGE [245], ZeroCLUE [246], FewCLUE [247], Blended Skill Talk [248], HELM [249], KLUE-STS [250] Language Understanding CoQA [251], WiC [252], Wikitext103 [253], PG19 [254], LCQMC [255], QQP [256], ”
TENER: Adapting Transformer Encoder for Named Entity Recognition (2019, methodology): “(5) Weibo NER was built based on text in Chinese social media Sina Weibo (Peng and Dredze, 2015), and it contained 4 kinds of entities.”
Unified Named Entity Recognition as Word-Word Relation Classification (2021, background): “In Table 9, we present the detailed statistics of 14 datasets, including CoNLL-2003 and OntoNotes 5.0 for English ﬂat NER, OntoNotes 4.0, MSRA, Weibo, and Resume for Chinese ﬂat NER, ACE 2004, ACE2005, and GENIA for English overlapped NER, ACE 2004 and ACE 2005 for Chinese overlapped NER, CADEC, ShA”
Chinese NER Using Lattice LSTM (2018, methodology): “, 2005), where segmentation information has been used as soft features for NER (Zhao and Kit, 2008; Peng and Dredze, 2015; He and Sun, 2017a), and joint segmentation and NER has been investigated using dual decomposition (Xu et al.”
Multi-task Domain Adaptation for Sequence Tagging (2016, neutral): “…news CWS data comes from the SIGHAN 2005 shared task ( SighanCWS ) (Emerson, 2005), news NER data comes from the SIGHAN 2006 shared task ( SighanNER ) (Levow, 2006), social CWS data ( WeiboSeg ) created by Zhang et al. (2013), and social NER data ( Wei-boNER ) created by Peng and Dredze (2015).”
A general framework for information extraction using dynamic span graphs (2019, methodology): “, 2013; Yang and Mitchell, 2016)) and multi-task learning (Peng and Dredze, 2015; Peng et al., 2017; Luan et al., 2018a, 2017a) as methods to share representational strength across related information extraction tasks.”