SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration

• URL: http://arxiv.org/abs/2008.01474v3
• Date: Mon, 21 Dec 2020 03:10:17 GMT
• Title: SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration
• Authors: Mengzuo Huang, Feng Li, Wuhe Zou and Weidong Zhang
• Abstract summary: In this paper, we investigate the incomplete utterance restoration which has brought general improvement over multi-turn dialogue systems. We propose a novel semi autoregressive generator (SARG) with the high efficiency and flexibility.
• Score: 9.394277095571942
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and information omission. In this paper, we investigate the incomplete utterance restoration which has brought general improvement over multi-turn dialogue systems in recent studies. Meanwhile, jointly inspired by the autoregression for text generation and the sequence labeling for text editing, we propose a novel semi autoregressive generator (SARG) with the high efficiency and flexibility. Moreover, experiments on two benchmarks show that our proposed model significantly outperforms the state-of-the-art models in terms of quality and inference speed.

Related papers

• RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery [69.41989381702858]
  Existing methods, such as direct generation and multi-agent discussion, often struggle with issues like hallucinations, topic incoherence, and significant latency. We propose RAPID, an efficient retrieval-augmented long text generation framework. Our work provides a robust and efficient solution to the challenges of automated long-text generation.
  arXiv  Detail & Related papers  (2025-03-02T06:11:29Z)
• Few-Shot, No Problem: Descriptive Continual Relation Extraction [27.296604792388646]
  Few-shot Continual Relation Extraction is a crucial challenge for enabling AI systems to identify and adapt to evolving relationships in real-world domains. Traditional memory-based approaches often overfit to limited samples, failing to reinforce old knowledge. We propose a novel retrieval-based solution, starting with a large language model to generate descriptions for each relation.
  arXiv  Detail & Related papers  (2025-02-27T23:44:30Z)
• Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring [4.819085609772069]
  We propose a novel approach for enhancing contextual recognition within ASR systems via semantic lattice processing. Our solution consists of using Hidden Markov Models and Gaussian Mixture Models (HMM-GMM) along with Deep Neural Networks (DNN) models for better accuracy. We demonstrate the effectiveness of our proposed framework on the LibriSpeech dataset with empirical analyses.
  arXiv  Detail & Related papers  (2023-10-14T23:16:05Z)
• Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback [57.816210168909286]
  We leverage recent progress on textual entailment models to address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual entailment rewards to optimize for factual consistency. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience, and conciseness of the generated summaries.
  arXiv  Detail & Related papers  (2023-05-31T21:04:04Z)
• $\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation [65.29170569821093]
  parallel text generation has received widespread attention due to its success in generation efficiency. In this paper, we propose $textitlatent$-GLAT, which employs the discrete latent variables to capture word categorical information. Experiment results show that our method outperforms strong baselines without the help of an autoregressive model.
  arXiv  Detail & Related papers  (2022-04-05T07:34:12Z)
• Reinforced Generative Adversarial Network for Abstractive Text Summarization [7.507096634112164]
  Sequence-to-sequence models provide a viable new approach to generative summarization. These models have three drawbacks: their grasp of the details of the original text is often inaccurate, and the text generated by such models often has repetitions. We propose a new architecture that combines reinforcement learning and adversarial generative networks to enhance the sequence-to-sequence attention model.
  arXiv  Detail & Related papers  (2021-05-31T17:34:47Z)
• Non-Autoregressive Text Generation with Pre-trained Language Models [40.50508206201288]
  We show that BERT can be employed as the backbone of a NAG model to greatly improve performance. We devise mechanisms to alleviate the two common problems of vanilla NAG models. We propose a new decoding strategy, ratio-first, for applications where the output lengths can be approximately estimated beforehand.
  arXiv  Detail & Related papers  (2021-02-16T15:30:33Z)
• Robust Dialogue Utterance Rewriting as Sequence Tagging [62.12912805378693]
  The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances drop dramatically when testing on a different domain. We propose a novel sequence-tagging-based fluency model so that the search space is significantly reduced.
  arXiv  Detail & Related papers  (2020-12-29T00:05:35Z)
• Controllable Text Simplification with Explicit Paraphrasing [88.02804405275785]
  Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained end-to-end to perform all these operations simultaneously. We propose a novel hybrid approach that leverages linguistically-motivated rules for splitting and deletion, and couples them with a neural paraphrasing model to produce varied rewriting styles.
  arXiv  Detail & Related papers  (2020-10-21T13:44:40Z)
• Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
  Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-10-06T02:51:02Z)
• Improving Adversarial Text Generation by Modeling the Distant Future [155.83051741029732]
  We consider a text planning scheme and present a model-based imitation-learning approach to alleviate the aforementioned issues. We propose a novel guider network to focus on the generative process over a longer horizon, which can assist next-word prediction and provide intermediate rewards for generator optimization.
  arXiv  Detail & Related papers  (2020-05-04T05:45:13Z)
• Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks [22.585901751927995]
  We study multi-turn response generation for open-domain dialogues. In this work, we pursue a model that has a simple structure yet can effectively leverage conversation contexts for response generation.
  arXiv  Detail & Related papers  (2020-04-04T16:37:00Z)

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.