Decoding Text Spans for Efficient and Accurate Named-Entity Recognition

• URL: http://arxiv.org/abs/2604.20447v1
• Date: Wed, 22 Apr 2026 11:09:45 GMT
• Title: Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
• Abstract summary: 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.
• Score: 19.920965306385074
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. State-of-the-art NER accuracy is often achieved by span-based frameworks, which construct span representations from token encodings and classify candidate spans. However, many span-based methods enumerate large numbers of candidates and process each candidate with marker-augmented inputs, substantially increasing inference cost and limiting scalability in large-scale deployments. In this work, we propose SpanDec, an efficient span-based NER framework that targets this bottleneck. Our main insight is that span representation interactions can be computed effectively at the final transformer stage, avoiding redundant computation in earlier layers via a lightweight decoder dedicated to span representations. We further introduce a span filtering mechanism during enumeration to prune unlikely candidates before expensive processing. Across multiple benchmarks, SpanDec matches competitive span-based baselines while improving throughput and reducing computational cost, yielding a better accuracy-efficiency trade-off suitable for high-volume serving and on-device applications.

Related papers

• Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation [49.97373153077311]
  We investigate the decoding overhead associated with a centroid encoding for Instance, in which each pixel regresses a positional embedding of its instance centroid.<n>Our solution significantly reduces decoding overhead and improves Endto-End latency, outperforming both CPU-based approaches and naive GPU implementations.
  arXiv  Detail & Related papers  (2026-09-15T09:05:17Z)
• Accelerate Speculative Decoding with Sparse Computation in Verification [49.74839681322316]
  Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel.<n>Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding.<n>We propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost.
  arXiv  Detail & Related papers  (2025-12-26T07:53:41Z)
• Prompt-based Dynamic Token Pruning for Efficient Segmentation of Medical Images [1.4146420810689422]
  This research proposes a Prompt-driven Adaptive Token pruning method to selectively reduce the processing of irrelevant tokens in the segmentation pipeline.<n>The experimental results show a reduction of $sim$ 35-55% tokens; thus reducing the computational costs relative to baselines.
  arXiv  Detail & Related papers  (2025-06-19T14:45:46Z)
• SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving [7.69991252191073]
  acronym is a framework that allows lightweight edge devices to draft multiple candidate tokens locally using diverse draft models.<n>A single, shared edge server verifies the tokens utilizing a more precise target model.<n>Our initial experiments with Jetson Orin Nano, Raspberry Pi 4B/5, and an edge server equipped with 4 Nvidia A100 GPUs indicate substantial benefits.
  arXiv  Detail & Related papers  (2025-06-11T04:55:54Z)
• End-to-End Dialog Neural Coreference Resolution: Balancing Efficiency and Accuracy in Large-Scale Systems [0.9752323911408618]
  Large-scale coreference resolution presents a significant challenge in natural language processing.<n>We introduce an End-to-End Neural Coreference Resolution system tailored for large-scale applications.<n>Our system efficiently identifies and resolves coreference links in text, ensuring minimal computational overhead.
  arXiv  Detail & Related papers  (2025-04-08T09:06:52Z)
• TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding [76.23719557942917]
  TETRIS actively selects the most promising draft tokens (for every request in a batch) to be accepted when verified in parallel.<n>We show theoretically and empirically that TETRIS outperforms baseline speculative decoding and existing methods that dynamically select draft tokens.
  arXiv  Detail & Related papers  (2025-02-21T04:19:24Z)
• Small Language Model Makes an Effective Long Text Extractor [10.886875977716608]
  Named Entity Recognition (NER) is a fundamental problem in natural language processing (NLP)<n>This paper introduces a lightweight span-based NER method called SeNER.<n>It incorporates a bidirectional arrow attention mechanism coupled with LogN-Scaling on the [] token to embed long texts effectively.<n>It achieves state-of-the-art extraction accuracy on three long NER datasets and is capable of extracting entities from long texts in a GPU-memory-friendly manner.
  arXiv  Detail & Related papers  (2025-02-11T06:06:25Z)
• Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy [46.81745860690336]
  Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems. This paper presents a generic framework for accelerating the inference process, resulting in a substantial increase in speed and cost reduction. We conduct extensive experiments to demonstrate the significant improvements achieved by applying our inference acceleration framework.
  arXiv  Detail & Related papers  (2023-12-20T02:55:15Z)
• Deep Span Representations for Named Entity Recognition [1.990310782671166]
  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.
  arXiv  Detail & Related papers  (2022-10-09T06:29:04Z)
• Should All Proposals be Treated Equally in Object Detection? [110.27485090952385]
  The complexity-precision trade-off of an object detector is a critical problem for resource constrained vision tasks. It is hypothesized that improved detection efficiency requires a paradigm shift, towards the unequal processing of proposals. This results in better utilization of available computational budget, enabling higher accuracy for the same FLOPS.
  arXiv  Detail & Related papers  (2022-07-07T18:26:32Z)
• Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion [62.269219152425556]
  segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field. We propose a Differentiable Binarization (DB) module that integrates the binarization process into a segmentation network. An efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively.
  arXiv  Detail & Related papers  (2022-02-21T15:30:14Z)
• Dependency Aware Filter Pruning [74.69495455411987]
  Pruning a proportion of unimportant filters is an efficient way to mitigate the inference cost. Previous work prunes filters according to their weight norms or the corresponding batch-norm scaling factors. We propose a novel mechanism to dynamically control the sparsity-inducing regularization so as to achieve the desired sparsity.
  arXiv  Detail & Related papers  (2020-05-06T07:41:22Z)

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.