NameRec*: Highly Accurate and Fine-grained Person Name Recognition

• URL: http://arxiv.org/abs/2103.11360v2
• Date: Tue, 23 Mar 2021 12:25:59 GMT
• Title: NameRec*: Highly Accurate and Fine-grained Person Name Recognition
• Authors: Rui Zhang, Yimeng Dai, Shijie Liu
• Abstract summary: NameRec* task aims to do highly accurate and fine-grained person name recognition. CogNN fully explores the intra-sentence context and rich training signals of name forms. IsBERT has an overlapped input processor, and an inter-sentence encoder with bidirectional overlapped contextual embedding learning.
• Score: 11.43547342030705
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we introduce the NameRec* task, which aims to do highly accurate and fine-grained person name recognition. Traditional Named Entity Recognition models have good performance in recognising well-formed person names from text with consistent and complete syntax, such as news articles. However, there are rapidly growing scenarios where sentences are of incomplete syntax and names are in various forms such as user-generated contents and academic homepages. To address person name recognition in this context, we propose a fine-grained annotation scheme based on anthroponymy. To take full advantage of the fine-grained annotations, we propose a Co-guided Neural Network (CogNN) for person name recognition. CogNN fully explores the intra-sentence context and rich training signals of name forms. To better utilize the inter-sentence context and implicit relations, which are extremely essential for recognizing person names in long documents, we further propose an Inter-sentence BERT Model (IsBERT). IsBERT has an overlapped input processor, and an inter-sentence encoder with bidirectional overlapped contextual embedding learning and multi-hop inference mechanisms. To derive benefit from different documents with a diverse abundance of context, we propose an advanced Adaptive Inter-sentence BERT Model (Ada-IsBERT) to dynamically adjust the inter-sentence overlapping ratio to different documents. We conduct extensive experiments to demonstrate the superiority of the proposed methods on both academic homepages and news articles.

Related papers

• Contextual Document Embeddings [77.22328616983417]
  We propose two complementary methods for contextualized document embeddings. First, an alternative contrastive learning objective that explicitly incorporates the document neighbors into the intra-batch contextual loss. Second, a new contextual architecture that explicitly encodes neighbor document information into the encoded representation.
  arXiv  Detail & Related papers  (2024-10-03T14:33:34Z)
• On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations [33.56352555780006]
  We investigate the robustness of DocRE models to entity name variations in this work. We propose a principled pipeline to generate entity-renamed documents by replacing the original entity names with names from Wikidata. Experimental results show that both three representative DocRE models and two in-context learned large language models consistently lack sufficient robustness to entity name variations.
  arXiv  Detail & Related papers  (2024-06-11T16:51:14Z)
• Multicultural Name Recognition For Previously Unseen Names [65.268245109828]
  This paper attempts to improve recognition of person names, a diverse category that can grow any time someone is born or changes their name. I look at names from 103 countries to compare how well the model performs on names from different cultures. I find that a model with combined character and word input outperforms word-only models and may improve on accuracy compared to classical NER models.
  arXiv  Detail & Related papers  (2024-01-23T17:58:38Z)
• Language Models As Semantic Indexers [78.83425357657026]
  We introduce LMIndexer, a self-supervised framework to learn semantic IDs with a generative language model. We show the high quality of the learned IDs and demonstrate their effectiveness on three tasks including recommendation, product search, and document retrieval.
  arXiv  Detail & Related papers  (2023-10-11T18:56:15Z)
• Disambiguation of Company names via Deep Recurrent Networks [101.90357454833845]
  We propose a Siamese LSTM Network approach to extract -- via supervised learning -- an embedding of company name strings. We analyse how an Active Learning approach to prioritise the samples to be labelled leads to a more efficient overall learning pipeline.
  arXiv  Detail & Related papers  (2023-03-07T15:07:57Z)
• The Fellowship of the Authors: Disambiguating Names from Social Network Context [2.3605348648054454]
  Authority lists with extensive textual descriptions for each entity are lacking and ambiguous named entities. We combine BERT-based mention representations with a variety of graph induction strategies and experiment with supervised and unsupervised cluster inference methods. We find that in-domain language model pretraining can significantly improve mention representations, especially for larger corpora.
  arXiv  Detail & Related papers  (2022-08-31T21:51:55Z)
• Document Domain Randomization for Deep Learning Document Layout Extraction [37.97092983885967]
  We present document domain randomization (DDR), the first successful transfer of convolutional neural networks (CNNs) trained only on graphically rendered pseudo-paper pages. DDR renders pseudo-document pages by modeling randomized textual and non-textual contents of interest. We show that high-fidelity semantic information is not necessary to label semantic classes but style mismatch between train and test can lower model accuracy.
  arXiv  Detail & Related papers  (2021-05-20T19:16:04Z)
• R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching [58.72111690643359]
  We propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching. We first employ BERT to encode the input sentences from a global perspective. Then a CNN-based encoder is designed to capture keywords and phrase information from a local perspective. To fully leverage labels for better relation information extraction, we introduce a self-supervised relation of relation classification task.
  arXiv  Detail & Related papers  (2020-12-16T13:11:30Z)
• Pairwise Learning for Name Disambiguation in Large-Scale Heterogeneous Academic Networks [81.00481125272098]
  We introduce Multi-view Attention-based Pairwise Recurrent Neural Network (MA-PairRNN) to solve the name disambiguation problem. MA-PairRNN combines heterogeneous graph embedding learning and pairwise similarity learning into a framework. Results on two real-world datasets demonstrate that our framework has a significant and consistent improvement of performance on the name disambiguation task.
  arXiv  Detail & Related papers  (2020-08-30T06:08:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.