Deep Span Representations for Named Entity Recognition

• URL: http://arxiv.org/abs/2210.04182v2
• Date: Tue, 9 May 2023 08:09:50 GMT
• Title: Deep Span Representations for Named Entity Recognition
• Abstract summary: Existing span-based NER systems shallowly aggregate the token representations to span representations. We propose DSpERT, which comprises a standard Transformer and a span Transformer. The latter uses low-layered span representations as queries, and aggregates the token representations as keys and values, layer by layer from bottom to top.
• Score: 1.990310782671166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Span-based models are one of the most straightforward methods for named entity recognition (NER). Existing span-based NER systems shallowly aggregate the token representations to span representations. However, this typically results in significant ineffectiveness for long-span entities, a coupling between the representations of overlapping spans, and ultimately a performance degradation. In this study, we propose DSpERT (Deep Span Encoder Representations from Transformers), which comprises a standard Transformer and a span Transformer. The latter uses low-layered span representations as queries, and aggregates the token representations as keys and values, layer by layer from bottom to top. Thus, DSpERT produces span representations of deep semantics. With weight initialization from pretrained language models, DSpERT achieves performance higher than or competitive with recent state-of-the-art systems on eight NER benchmarks. Experimental results verify the importance of the depth for span representations, and show that DSpERT performs particularly well on long-span entities and nested structures. Further, the deep span representations are well structured and easily separable in the feature space.

Related papers

• Decoding Text Spans for Efficient and Accurate Named-Entity Recognition [19.920965306385074]
  SpanDec is an efficient span-based NER framework that targets this bottleneck.<n>Our main insight is that span representation interactions can be computed effectively at the final transformer stage.<n>Across multiple benchmarks, SpanDec matches competitive span-based baselines while improving throughput and reducing computational cost.
  arXiv  Detail & Related papers  (2026-04-22T11:09:45Z)
• PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Search [56.81939214465558]
  We propose PromptNER: a novel prompting method for few-shot NER via k nearest neighbor search. We use prompts that contains entity category information to construct label prototypes, which enables our model to fine-tune with only the support set. Our approach achieves excellent transfer learning ability, and extensive experiments on the Few-NERD and CrossNER datasets demonstrate that our model achieves superior performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-20T15:47:59Z)
• Span-based Named Entity Recognition by Generating and Compressing Information [23.444967843156086]
  We propose to combine the two types of IB models into one system to enhance Named Entity Recognition. Experiments on five different corpora indicate that jointly training both generative and information compression models can enhance the performance of the baseline span-based NER system.
  arXiv  Detail & Related papers  (2023-02-10T17:40:51Z)
• SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition [45.012327072558975]
  Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. We propose a seminal span-based prototypical network (SpanProto) that tackles few-shot NER via a two-stage approach. In the span extraction stage, we transform the sequential tags into a global boundary matrix, enabling the model to focus on the explicit boundary information. For mention classification, we leverage prototypical learning to capture the semantic representations for each labeled span and make the model better adapt to novel-class entities.
  arXiv  Detail & Related papers  (2022-10-17T12:59:33Z)
• Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning [80.36076044023581]
  We present an efficient bi-encoder framework for named entity recognition (NER) We frame NER as a metric learning problem that maximizes the similarity between the vector representations of an entity mention and its type. A major challenge to this bi-encoder formulation for NER lies in separating non-entity spans from entity mentions.
  arXiv  Detail & Related papers  (2022-08-30T23:19:04Z)
• UnifieR: A Unified Retriever for Large-Scale Retrieval [84.61239936314597]
  Large-scale retrieval is to recall relevant documents from a huge collection given a query. Recent retrieval methods based on pre-trained language models (PLM) can be coarsely categorized into either dense-vector or lexicon-based paradigms. We propose a new learning framework, UnifieR which unifies dense-vector and lexicon-based retrieval in one model with a dual-representing capability.
  arXiv  Detail & Related papers  (2022-05-23T11:01:59Z)
• Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction [88.6585431949086]
  We propose a novel Hierarchical Visual Prefix fusion NeTwork (HVPNeT) for visual-enhanced entity and relation extraction. We regard visual representation as pluggable visual prefix to guide the textual representation for error insensitive forecasting decision. Experiments on three benchmark datasets demonstrate the effectiveness of our method, and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-05-07T02:10:55Z)
• Hierarchical Transformer Model for Scientific Named Entity Recognition [0.20646127669654832]
  We present a simple and effective approach for Named Entity Recognition. The main idea of our approach is to encode the input subword sequence with a pre-trained transformer such as BERT. We evaluate our approach on three benchmark datasets for scientific NER.
  arXiv  Detail & Related papers  (2022-03-28T12:59:06Z)
• Hierarchical Neural Network Approaches for Long Document Classification [3.6700088931938835]
  We employ pre-trained Universal Sentence (USE) and Bidirectional Representations from Transformers (BERT) in a hierarchical setup to capture better representations efficiently. Our proposed models are conceptually simple where we divide the input data into chunks and then pass this through base models of BERT and USE. We show that USE + CNN/LSTM performs better than its stand-alone baseline. Whereas the BERT + CNN/LSTM performs on par with its stand-alone counterpart.
  arXiv  Detail & Related papers  (2022-01-18T07:17:40Z)
• Boosting Span-based Joint Entity and Relation Extraction via Squence Tagging Mechanism [10.894755638322]
  Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in text span form. Recent studies have shown that token labels can convey crucial task-specific information and enrich token semantics. We pro-pose Sequence Tagging enhanced Span-based Network (STSN), a span-based joint extrac-tion network that is enhanced by token BIO label information.
  arXiv  Detail & Related papers  (2021-05-21T01:10:03Z)
• Dependency Parsing based Semantic Representation Learning with Graph Neural Network for Enhancing Expressiveness of Text-to-Speech [49.05471750563229]
  We propose a semantic representation learning method based on graph neural network, considering dependency relations of a sentence. We show that our proposed method outperforms the baseline using vanilla BERT features both in LJSpeech and Bilzzard Challenge 2013 datasets.
  arXiv  Detail & Related papers  (2021-04-14T13:09:51Z)

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.