Re-Representation in Sentential Relation Extraction with Sequence Routing Algorithm

• URL: http://arxiv.org/abs/2508.21049v2
• Date: Sat, 30 Aug 2025 08:52:21 GMT
• Title: Re-Representation in Sentential Relation Extraction with Sequence Routing Algorithm
• Abstract summary: We first show that the proposed approach outperform state of the art on common sentential relation extraction datasets Tacred, Tacredrev, Retacred, and Conll04.<n>We then investigate potential reasons for its good performance on the mentioned datasets, and yet low performance on another similar, yet larger sentential RE dataset, Wikidata.
• Score: 3.5364886788398753
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sentential relation extraction (RE) is an important task in natural language processing (NLP). In this paper we propose to do sentential RE with dynamic routing in capsules. We first show that the proposed approach outperform state of the art on common sentential relation extraction datasets Tacred, Tacredrev, Retacred, and Conll04. We then investigate potential reasons for its good performance on the mentioned datasets, and yet low performance on another similar, yet larger sentential RE dataset, Wikidata. As such, we identify noise in Wikidata labels as one of the reasons that can hinder performance. Additionally, we show associativity of better performance with better re-representation, a term from neuroscience referred to change of representation in human brain to improve the match at comparison time. As example, in the given analogous terms King:Queen::Man:Woman, at comparison time, and as a result of re-representation, the similarity between related head terms (King,Man), and tail terms (Queen,Woman) increases. As such, our observation show that our proposed model can do re-representation better than the vanilla model compared with. To that end, beside noise in the labels of the distantly supervised RE datasets, we propose re-representation as a challenge in sentential RE.

Related papers

• SiReRAG: Indexing Similar and Related Information for Multihop Reasoning [96.60045548116584]
  SiReRAG is a novel RAG indexing approach that explicitly considers both similar and related information.<n>SiReRAG consistently outperforms state-of-the-art indexing methods on three multihop datasets.
  arXiv  Detail & Related papers  (2024-12-09T04:56:43Z)
• REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training [49.581884130880944]
  Deep neural network (DNN) has been proven effective in various domains. However, they often struggle to perform well on certain minority groups during inference.
  arXiv  Detail & Related papers  (2023-12-05T16:27:54Z)
• Sequence Generation with Label Augmentation for Relation Extraction [17.38986046630852]
  We propose Relation Extraction with Label Augmentation (RELA), a Seq2Seq model with automatic label augmentation for relation extraction. Experimental results show RELA achieves competitive results compared with previous methods on four RE datasets.
  arXiv  Detail & Related papers  (2022-12-29T11:28:05Z)
• Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction [36.85068584859058]
  We introduce a simple enhancement of Relation extraction using $k$ nearest neighbors ($k$NN-RE) $k$NN-RE allows the model to consult training relations at test time through a nearest-neighbor search. Experimental results show that the proposed $k$NN-RE achieves state-of-the-art performances on a variety of supervised RE datasets.
  arXiv  Detail & Related papers  (2022-10-21T08:25:10Z)
• Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis [60.83756368501083]
  We propose the CORE (Counterfactual Analysis based Relation Extraction) debiasing method for sentence-level relation extraction. Our CORE method is model-agnostic to debias existing RE systems during inference without changing their training processes.
  arXiv  Detail & Related papers  (2022-05-08T05:13:54Z)
• Automatically Generating Counterfactuals for Relation Exaction [18.740447044960796]
  relation extraction (RE) is a fundamental task in natural language processing. Current deep neural models have achieved high accuracy but are easily affected by spurious correlations. We develop a novel approach to derive contextual counterfactuals for entities.
  arXiv  Detail & Related papers  (2022-02-22T04:46:10Z)
• Learning from Context or Names? An Empirical Study on Neural Relation Extraction [112.06614505580501]
  We study the effect of two main information sources in text: textual context and entity mentions (names) We propose an entity-masked contrastive pre-training framework for relation extraction (RE) Our framework can improve the effectiveness and robustness of neural models in different RE scenarios.
  arXiv  Detail & Related papers  (2020-10-05T11:21:59Z)
• Relation of the Relations: A New Paradigm of the Relation Extraction Problem [52.21210549224131]
  We propose a new paradigm of Relation Extraction (RE) that considers as a whole the predictions of all relations in the same context. We develop a data-driven approach that does not require hand-crafted rules but learns by itself the relation of relations (RoR) using Graph Neural Networks and a relation matrix transformer. Experiments show that our model outperforms the state-of-the-art approaches by +1.12% on the ACE05 dataset and +2.55% on SemEval 2018 Task 7.2.
  arXiv  Detail & Related papers  (2020-06-05T22:25:27Z)
• Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction [80.38130122127882]
  We introduce 14 probing tasks targeting linguistic properties relevant to neural relation extraction (RE) We use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets. We find that the bias induced by the architecture and the inclusion of linguistic features are clearly expressed in the probing task performance.
  arXiv  Detail & Related papers  (2020-04-17T09:17:40Z)
• Feature selection in machine learning: R\'enyi min-entropy vs Shannon entropy [6.434361163743876]
  We propose an algorithm based on a notion of conditional R'enyi min-entropy that has been recently adopted in the field of security and privacy. In practice, however, it seems that the R'enyi-based algorithm tends to outperform the other one.
  arXiv  Detail & Related papers  (2020-01-27T09:50:54Z)

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.