A Joint Model for Named Entity Recognition With Sentence-Level Entity Type Attentions

2021 ◽  
Vol 29 ◽  
pp. 1438-1448
Author(s):  
Tao Qian ◽  
Meishan Zhang ◽  
Yinxia Lou ◽  
Daiwen Hua
Keyword(s):  
Named Entity Recognition ◽  
Joint Model ◽  
Entity Recognition ◽  
Named Entity ◽  
Sentence Level

scholarly journals An ERNIE-Based Joint Model for Chinese Named Entity Recognition

2020 ◽  
Vol 10 (16) ◽  
pp. 5711
Author(s):  
Yu Wang ◽  
Yining Sun ◽  
Zuchang Ma ◽  
Lisheng Gao ◽  
Yang Xu
Keyword(s):  
Language Processing ◽  
Text Classification ◽  
Knowledge Integration ◽  
Named Entity Recognition ◽  
Training Model ◽  
Joint Model ◽  
Entity Recognition ◽  
Named Entity ◽  
Sentence Level ◽  
Joint Training

Named Entity Recognition (NER) is the fundamental task for Natural Language Processing (NLP) and the initial step in building a Knowledge Graph (KG). Recently, BERT (Bidirectional Encoder Representations from Transformers), which is a pre-training model, has achieved state-of-the-art (SOTA) results in various NLP tasks, including the NER. However, Chinese NER is still a more challenging task for BERT because there are no physical separations between Chinese words, and BERT can only obtain the representations of Chinese characters. Nevertheless, the Chinese NER cannot be well handled with character-level representations, because the meaning of a Chinese word is quite different from that of the characters, which make up the word. ERNIE (Enhanced Representation through kNowledge IntEgration), which is an improved pre-training model of BERT, is more suitable for Chinese NER because it is designed to learn language representations enhanced by the knowledge masking strategy. However, the potential of ERNIE has not been fully explored. ERNIE only utilizes the token-level features and ignores the sentence-level feature when performing the NER task. In this paper, we propose the ERNIE-Joint, which is a joint model based on ERNIE. The ERNIE-Joint can utilize both the sentence-level and token-level features by joint training the NER and text classification tasks. In order to use the raw NER datasets for joint training and avoid additional annotations, we perform the text classification task according to the number of entities in the sentences. The experiments are conducted on two datasets: MSRA-NER and Weibo. These datasets contain Chinese news data and Chinese social media data, respectively. The results demonstrate that the ERNIE-Joint not only outperforms BERT and ERNIE but also achieves the SOTA results on both datasets.

scholarly journals Hierarchical Contextualized Representation for Named Entity Recognition

2020 ◽  
Vol 34 (05) ◽  
pp. 8441-8448
Author(s):  
Ying Luo ◽  
Fengshun Xiao ◽  
Hai Zhao
Keyword(s):  
Named Entity Recognition ◽  
Entity Recognition ◽  
Named Entity ◽  
Sentence Level ◽  
Unique Word ◽  
Entire Sentence ◽  
Single Input ◽  
Memory Network ◽  
Full Utilization ◽  
Document Level

Named entity recognition (NER) models are typically based on the architecture of Bi-directional LSTM (BiLSTM). The constraints of sequential nature and the modeling of single input prevent the full utilization of global information from larger scope, not only in the entire sentence, but also in the entire document (dataset). In this paper, we address these two deficiencies and propose a model augmented with hierarchical contextualized representation: sentence-level representation and document-level representation. In sentence-level, we take different contributions of words in a single sentence into consideration to enhance the sentence representation learned from an independent BiLSTM via label embedding attention mechanism. In document-level, the key-value memory network is adopted to record the document-aware information for each unique word which is sensitive to similarity of context information. Our two-level hierarchical contextualized representations are fused with each input token embedding and corresponding hidden state of BiLSTM, respectively. The experimental results on three benchmark NER datasets (CoNLL-2003 and Ontonotes 5.0 English datasets, CoNLL-2002 Spanish dataset) show that we establish new state-of-the-art results.

scholarly journals InferNER: an attentive model leveraging the sentence-level information for Named Entity Recognition in Microblogs

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Moemmur Shahzad ◽  
Ayesha Amin ◽  
Diego Esteves ◽  
Axel-Cyrille Ngonga Ngomo
Keyword(s):  
Social Media ◽  
Visual Information ◽  
State Of The Art ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Named Entity ◽  
Current State ◽  
Sentence Level ◽  
Level Information ◽  
External Sources

We investigate the problem of named entity recognition in the user-generated text such as social media posts. This task is rendered particularly difficult by the restricted length and limited grammatical coherence of this data type. Current state-of-the-art approaches rely on external sources such as gazetteers to alleviate some of these restrictions. We present a neural model able to outperform state of the art on this task without recurring to gazetteers or similar external sources of information. Our approach relies on word-, character-, and sentence-level information for NER in short-text. Social media posts like tweets often have associated images that may provide auxiliary context relevant to understand these texts. Hence, we also incorporate visual information and introduce an attention component which computes attention weight probabilities over textual and text-relevant visual contexts separately. Our model outperforms the current state of the art on various NER datasets. On WNUT 2016 and 2017, our model achieved 53.48\% and 50.52\% F1 score, respectively. With Multimodal model, our system also outperforms the current SOTA with an F1 score of 74\% on the multimodal dataset. Our evaluation further suggests that our model also goes beyond the current state-of-the-art on newswire data, hence corroborating its suitability for various NER tasks.

scholarly journals Leveraging Multi-Token Entities in Document-Level Named Entity Recognition

2020 ◽  
Vol 34 (05) ◽  
pp. 7961-7968
Author(s):  
Anwen Hu ◽  
Zhicheng Dou ◽  
Jian-Yun Nie ◽  
Ji-Rong Wen
Keyword(s):  
Neural Networks ◽  
State Of The Art ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Context Information ◽  
Named Entity ◽  
Sentence Level ◽  
Semantic Relevance ◽  
Recognition Systems ◽  
Document Level

Most state-of-the-art named entity recognition systems are designed to process each sentence within a document independently. These systems are easy to confuse entity types when the context information in a sentence is not sufficient enough. To utilize the context information within the whole document, most document-level work let neural networks on their own to learn the relation across sentences, which is not intuitive enough for us humans. In this paper, we divide entities to multi-token entities that contain multiple tokens and single-token entities that are composed of a single token. We propose that the context information of multi-token entities should be more reliable in document-level NER for news articles. We design a fusion attention mechanism which not only learns the semantic relevance between occurrences of the same token, but also focuses more on occurrences belonging to multi-tokens entities. To identify multi-token entities, we design an auxiliary task namely ‘Multi-token Entity Classification’ and perform this task simultaneously with document-level NER. This auxiliary task is simplified from NER and doesn't require extra annotation. Experimental results on the CoNLL-2003 dataset and OntoNotesnbm dataset show that our model outperforms state-of-the-art sentence-level and document-level NER methods.

scholarly journals A Joint Model for Entity Analysis: Coreference, Typing, and Linking

2014 ◽  
Vol 2 ◽  
pp. 477-490 ◽  
Author(s):  
Greg Durrett ◽  
Dan Klein
Keyword(s):  
State Of The Art ◽  
Conditional Random Field ◽  
Named Entity Recognition ◽  
Joint Modeling ◽  
Joint Model ◽  
Entity Recognition ◽  
Coreference Resolution ◽  
Entity Linking ◽  
Semantic Type ◽  
Named Entity

We present a joint model of three core tasks in the entity analysis stack: coreference resolution (within-document clustering), named entity recognition (coarse semantic typing), and entity linking (matching to Wikipedia entities). Our model is formally a structured conditional random field. Unary factors encode local features from strong baselines for each task. We then add binary and ternary factors to capture cross-task interactions, such as the constraint that coreferent mentions have the same semantic type. On the ACE 2005 and OntoNotes datasets, we achieve state-of-the-art results for all three tasks. Moreover, joint modeling improves performance on each task over strong independent baselines.

scholarly journals RELATION EXTRACTION DATASET FOR THE RUSSIAN

2020 ◽  
Author(s):  
D. I. Gordeev ◽  
◽  
A. A. Davletov ◽  
A. I. Rey ◽  
G. R. Akzhigitova ◽  
...  
Keyword(s):  
Named Entity Recognition ◽  
Relation Extraction ◽  
Russian Language ◽  
Entity Recognition ◽  
Named Entities ◽  
Named Entity ◽  
Sentence Level ◽  
The Russian Language

There are few existing relation extraction datasets for the Russian language and they contain a rather small number of examples. Thus, we decided to create a new Ontonotes-based named entities and relation extraction sentence-level dataset called RURED. The dataset contains more than 500 annotated texts and more than 5,000 labelled relations. We also publish baseline models for relation extraction and named entity recognition trained on the dataset. Our models achieve 0.85 for named entity recognition and 0.78 for relation extraction in F1-score.

Sign in / Sign up

Export Citation Format

Share Document