mlsanityData to 7 Oct 2026

Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency

arXiv 2404.09830 ↗First posted 15 Apr 2024cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Previous works of negation understanding mainly focus on negation cue detection and scope resolution, without identifying negation subject which is also significant to the downstream tasks. In this paper, we propose a new negation triplet extraction (NTE) task which aims to extract negation subject along with negation cue and scope. To achieve NTE, we devise a novel Syntax&Semantic-Enhanced Negation Extraction model, namely SSENE, which is built based on a generative pretrained language model (PLM) {of Encoder-Decoder architecture} with a multi-task learning framework. Specifically, the given sentence's syntactic dependency tree is incorporated into the PLM's encoder to discover the correlations between the negation subject, cue and scope. Moreover, the semantic consistency between the sentence and the extracted triplet is ensured by an auxiliary task learning. Furthermore, we have constructed a high-quality Chinese dataset NegComment based on the users' reviews from the real-world platform of Meituan, upon which our evaluations show that SSENE achieves the best NTE performance compared to the baselines. Our ablation and case studies also demonstrate that incorporating the syntactic information helps the PLM's recognize the distant dependency between the subject and cue, and the auxiliary task learning is helpful to extract the negation triplets with more semantic consistency.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 15 Apr 2024.

Builds on

27 of 42 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  5. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  6. 2019Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Flycited by 240
  7. 2022Unified Structure Generation for Universal Information Extractioncited by 220
  8. 2017Joint Extraction of Entities and Relations Based on a Novel Tagging Schemecited by 102
  9. 2021A Unified Generative Framework for Aspect-Based Sentiment Analysiscited by 97
  10. 2020Syntactic Data Augmentation Increases Robustness to Inference Heuristicscited by 85
  11. 2017NegBio: a high-performance tool for negation and uncertainty detection in radiology reportscited by 79
  12. 2019Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extractioncited by 73
15 more
  1. 2021Understanding by Understanding Not: Modeling Negation in Language Modelscited by 73
  2. 2020TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linkingcited by 72
  3. 2021A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysiscited by 61
  4. 2021Learning Span-Level Interactions for Aspect Sentiment Triplet Extractioncited by 60
  5. 2018Joint entity recognition and relation extraction as a multi-head selection problemcited by 59
  6. 2021Syntax-BERT: Improving Pre-trained Transformers with Syntax Treescited by 51
  7. 2021Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinesecited by 45
  8. 2020GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extractioncited by 43
  9. 2020Pre-training Text-to-Text Transformers for Concept-centric Common Sensecited by 42
  10. 2019Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategycited by 41
  11. 2019NegBERT: A Transfer Learning Approach for Negation Detection and Scope Resolutioncited by 36
  12. 2019Self-Attention with Structural Position Representationscited by 21
  13. 2021A Simple but Effective Bidirectional Framework for Relational Triple Extractioncited by 14
  14. 2022Improving negation detection with negation-focused pre-trainingcited by 14
  15. 2020An Analysis of the Utility of Explicit Negative Examples to Improve the Syntactic Abilities of Neural Language Modelscited by 6

Built on by

Not cited yet.