mlsanityData to 14 Oct 2026

Learning Structured Text Representations

arXiv 1705.09207 ↗First posted 25 May 2017cs.CL cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural bias, we propose a model that can encode a document while automatically inducing rich structural dependencies. Specifically, we embed a differentiable non-projective parsing algorithm into a neural model and use attention mechanisms to incorporate the structural biases. Experimental evaluation across different tasks and datasets shows that the proposed model achieves state-of-the-art results on document modeling tasks while inducing intermediate structures which are both interpretable and meaningful.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 8; 2023: 6; 2024: 1.

24 papers.

Sort:

By area:

  1. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 178
  2. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  3. 2022Estimating the Personality of White-Box Language Modelscited by 48
  4. 2021Attribute Alignment: Controlling Text Generation from Pre-trained Language Modelscited by 27
  5. 2021Modeling Hierarchical Structures with Continuous Recursive Neural Networkscited by 15
  6. 2021Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Argumentscited by 14
  7. 2021Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarizationcited by 11
  8. 2021Predicting Discourse Trees from Transformer-based Neural Summarizerscited by 10
  9. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  10. 2022More Interpretable Graph Similarity Computation via Maximum Common Subgraph Inferencecited by 8
  11. 2023Advancements in Scientific Controllable Text Generation Methodscited by 7
  12. 2021To be Closer: Learning to Link up Aspects with Opinionscited by 5
12 more
  1. 2022Improving Topic Segmentation by Injecting Discourse Dependenciescited by 5
  2. 2023Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialoguescited by 4
  3. 2023Structured Dialogue Discourse Parsingcited by 4
  4. 2023Efficient Beam Tree Recursioncited by 4
  5. 2022Learning with Latent Structures in Natural Language Processing: A Surveycited by 2
  6. 2022Discourse-Aware Graph Networks for Textual Logical Reasoningcited by 2
  7. 2023Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classificationcited by 2
  8. 2024To be Continuous, or to be Discrete, Those are Bits of Questionscited by 2
  9. 2021Speaker-Oriented Latent Structures for Dialogue-Based Relation Extractioncited by 1
  10. 2022An Overview on Controllable Text Generation via Variational Auto-Encoderscited by 1
  11. 2023Learning Unbiased News Article Representations: A Knowledge-Infused Approachcited by 1
  12. 2022Testing the Robustness of a BiLSTM-based Structural Story Classifiercited by 0