mlsanityData to 7 Oct 2026

Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems

arXiv 1508.01745 ↗First posted 7 Aug 2015cs.CLcited by 134

Not on the map. Why?

Abstract (arXiv)

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised responses without the natural variation of human language. They are also not easily scaled to systems covering multiple domains and languages. This paper presents a statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure. The LSTM generator can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates. With fewer heuristics, an objective evaluation in two differing test domains showed the proposed method improved performance compared to previous methods. Human judges scored the LSTM system higher on informativeness and naturalness and overall preferred it to the other systems.

Key facts. Cited by 134 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Aug 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 3; 2019: 2; 2020: 0; 2021: 36; 2022: 35; 2023: 27; 2024: 21; 2025: 5; 2026: 5.

134 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  3. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  4. 2023GPTScore: Evaluate as You Desirecited by 357
  5. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  6. 2021GODIVA: Generating Open-DomaIn Videos from nAtural Descriptionscited by 254
  7. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  8. 2023X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languagescited by 127
  9. 2023Textually Pretrained Speech Language Modelscited by 99
  10. 2025A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applicationscited by 91
  11. 2023MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Taskscited by 57
  12. 2023Calibrating LLM-Based Evaluatorcited by 53
38 more
  1. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  2. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  3. 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
  4. 2022Neural Approaches to Conversational Information Retrievalcited by 41
  5. 2021Automatic Text Evaluation through the Lens of Wasserstein Barycenterscited by 38
  6. 2024Leveraging Large Language Models for NLG Evaluation: Advances and Challengescited by 37
  7. 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
  8. 2024HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decompositioncited by 33
  9. 2022Continual Sequence Generation with Adaptive Compositional Modulescited by 31
  10. 2021CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systemscited by 30
  11. 2022Visualize Before You Write: Imagination-Guided Open-Ended Text Generationcited by 30
  12. 2023X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspectscited by 28
  13. 2021Focused Attention Improves Document-Grounded Generationcited by 24
  14. 2021Semantic Representation for Dialogue Modelingcited by 24
  15. 2024Reliable LLM-based User Simulator for Task-Oriented Dialogue Systemscited by 24
  16. 2021Better Feature Integration for Named Entity Recognitioncited by 22
  17. 2022GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformerscited by 22
  18. 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
  19. 2018Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learningcited by 21
  20. 2021Improving Compositional Generalization with Self-Training for Data-to-Text Generationcited by 19
  21. 2023Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systemscited by 19
  22. 2023In-Context Learning User Simulators for Task-Oriented Dialog Systemscited by 19
  23. 2024Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretabilitycited by 19
  24. 2021Refocusing on Relevance: Personalization in NLGcited by 18
  25. 2022Toward Human-Like Evaluation for Natural Language Generation with Error Analysiscited by 18
  26. 2021A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regionscited by 17
  27. 2021AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentationcited by 17
  28. 2021Learning to Select External Knowledge with Multi-Scale Negative Samplingcited by 16
  29. 2022ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Modelscited by 14
  30. 2023Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learningcited by 14
  31. 2018Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learningcited by 12
  32. 2023X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agentscited by 12
  33. 2021DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generationcited by 11
  34. 2021Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLGcited by 11
  35. 2022Parameter-Efficient Abstractive Question Answering over Tables or Textcited by 11
  36. 2022KETOD: Knowledge-Enriched Task-Oriented Dialoguecited by 11
  37. 2022Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialogcited by 11
  38. 2021Style Control for Schema-Guided Natural Language Generationcited by 10

50 most cited of 134 All 134 (JSON)