Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis

• URL: http://arxiv.org/abs/2605.20998v1
• Date: Wed, 20 May 2026 10:37:57 GMT
• Title: Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis
• Abstract summary: Existing models either re-encode the sentence for each aspect or rely on static use of deep representations.<n>We propose DABS, a single-pass inference framework that encodes each sentence once to construct a reusable, depth-ordered substrate.<n>Experiments on four ATSA benchmarks show that DABS achieves competitive performance while reducing end-to-end computation by up to 60%.
• Score: 11.788282883495725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aspect-Term Sentiment Analysis (ATSA) in multi-aspect sentences faces a fundamental tradeoff between efficiency and expressiveness. Existing models either re-encode the sentence for each aspect or rely on static use of deep representations, leading to redundant computation and limited adaptivity. We argue that Transformer depth is a costly, queryable resource, and propose DABS, a single-pass inference framework that encodes each sentence once to construct a reusable, depth-ordered substrate. Each aspect then queries this shared representation to selectively read relevant tokens and abstraction levels, without re-encoding. This decouples shared sentence encoding from lightweight, aspect-conditioned readout. Experiments on four ATSA benchmarks show that DABS achieves competitive performance while reducing end-to-end computation by up to 60% in multi-aspect settings (M >= 2). Further analyses indicate that adaptive depth querying is most beneficial for linguistically complex cases such as negation and contrast. Code is publicly available at https://github.com/panzhzh/acl-dabs

Related papers

• Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment [5.696801894034388]
  We propose a novel causal adjustment pipeline that iteratively selects a minimal set of SAE features via conditional independence tests.<n> SAE representations achieve better adjustments than alternative representations in standard semi-synthetic evaluations with binary confounders.<n>We also introduce a more realistic semi-synthetic evaluation that uses multi-label data as the unobserved confounders.
  arXiv  Detail & Related papers  (2026-09-01T14:40:23Z)
• SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders [11.728621223411475]
  We propose SoftSAE, a sparse autoencoder with a Dynamic Top-K selection mechanism.<n>Our method uses a differentiable Soft Top-K operator to learn an input-dependent sparsity level k.<n> Experimental results confirm that SoftSAE not only finds meaningful features, but also selects the right number of features for each concept.
  arXiv  Detail & Related papers  (2026-05-07T17:28:40Z)
• Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models [1.5817866616624976]
  Large language models (LLMs) often struggle to accurately read and comprehend long texts.<n>Current methods for improvement typically rely on splitting long contexts into fixed-length chunks.<n>We propose a straightforward approach for dynamically separating and selecting chunks of long context.
  arXiv  Detail & Related papers  (2025-06-01T01:42:40Z)
• Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling [90.86991492288487]
  evaluating constraint on every token can be prohibitively expensive.<n> LCD can distort the global distribution over strings, sampling tokens based only on local information.<n>We show that our approach is superior to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-04-07T18:30:18Z)
• Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective [50.261681681643076]
  We propose a novel metric called SemVarEffect and a benchmark named SemVarBench to evaluate the causality between semantic variations in inputs and outputs in text-to-image synthesis.<n>Our work establishes an effective evaluation framework that advances the T2I synthesis community's exploration of human instruction understanding.
  arXiv  Detail & Related papers  (2024-10-14T08:45:35Z)
• Paired Completion: Flexible Quantification of Issue-framing at Scale with LLMs [0.41436032949434404]
  We introduce paired completion', a novel approach to detect contrasting frames using minimal examples.<n>We demonstrate that paired completion is a cost-efficient, low-bias alternative to both prompt-based and embedding-based methods.
  arXiv  Detail & Related papers  (2024-08-19T07:14:15Z)
• Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations [67.92679668612858]
  We propose the Consensus Network (Css-Net), inspired by the psychological concept that groups outperform individuals. Css-Net comprises two core components: (1) a consensus module with four diverse compositors, each generating distinct image-text embeddings; and (2) a Kullback-Leibler divergence loss that encourages learning of inter-compositor interactions. On benchmark datasets, particularly FashionIQ, Css-Net demonstrates marked improvements. Notably, it achieves significant recall gains, with a 2.77% increase in R@10 and 6.67% boost in R@50, underscoring its
  arXiv  Detail & Related papers  (2023-06-03T11:50:44Z)
• CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval [23.69812399753584]
  Contextual Masked Auto-Encoder has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for passage retrieval. We propose to pre-train Contextual Masked Auto-Encoder with Mixture-of-Textual-Experts (CoT-MoTE)
  arXiv  Detail & Related papers  (2023-04-20T10:12:09Z)
• UATVR: Uncertainty-Adaptive Text-Video Retrieval [90.8952122146241]
  A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities. We propose an Uncertainty-language Text-Video Retrieval approach, termed UATVR, which models each look-up as a distribution matching procedure.
  arXiv  Detail & Related papers  (2023-01-16T08:43:17Z)
• A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysis [91.83895509731144]
  We propose a novel training framework to mitigate the multi-aspect challenge of sentiment analysis. A source sentence is fed a domain-specific generator to obtain some synthetic sentences. The generator generates aspect-specific sentences and a Polarity Augmentation (PAC) to generate polarity-inverted sentences. Our framework can outperform those baselines without any augmentations by about 1% on accuracy and Macro-F1.
  arXiv  Detail & Related papers  (2022-04-16T16:05:58Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• Pareto Probing: Trading Off Accuracy for Complexity [87.09294772742737]
  We argue for a probe metric that reflects the fundamental trade-off between probe complexity and performance. Our experiments with dependency parsing reveal a wide gap in syntactic knowledge between contextual and non-contextual representations.
  arXiv  Detail & Related papers  (2020-10-05T17:27:31Z)

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.