Joint Generator-Ranker Learning for Natural Language Generation

• URL: http://arxiv.org/abs/2206.13974v3
• Date: Sun, 28 May 2023 13:51:09 GMT
• Title: Joint Generator-Ranker Learning for Natural Language Generation
• Authors: Weizhou Shen, Yeyun Gong, Yelong Shen, Song Wang, Xiaojun Quan, Nan Duan, Weizhu Chen
• Abstract summary: JGR is a novel joint training algorithm that integrates the generator and the ranker in a single framework. By iteratively updating the generator and the ranker, JGR can effectively harmonize their learning and enhance their quality jointly.
• Score: 99.16268050116717
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generate-then-rank is a widely used mechanism for text generation, where a generator produces multiple text candidates and a ranker chooses the best one among the text candidates. However, existing methods usually train the generator and the ranker individually, neglecting the mutual feedback that could further enhance the generation quality. To tackle this limitation, we propose JGR, a novel joint training algorithm that integrates the generator and the ranker in a single framework. JGR optimizes the generator with a hybrid objective that combines data likelihood and ranker reward, and trains the ranker with a contrastive loss that compares the generator outputs. By iteratively updating the generator and the ranker, JGR can effectively harmonize their learning and enhance their quality jointly. We evaluate JGR on various text generation tasks and demonstrate that it surpasses existing methods on four public datasets across three common generation scenarios. Our code and models are publicly available at https://github.com/microsoft/ProphetNet/tree/master/JGR.

Related papers

• Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation [10.736876118242384]
  We propose RRG (Retrieve, Refactor, Generate), a novel framework for effective and efficient code generation. This framework introduces a code-auger module between the retriever and the generator to bridge them. RRG achieved significant performance improvements, with increases of up to 28% on EM, 13% on BLEU, and 6.8% on CodeBLEU.
  arXiv  Detail & Related papers  (2024-09-24T09:15:37Z)
• CodeRAG-Bench: Can Retrieval Augment Code Generation? [78.37076502395699]
  We conduct a systematic, large-scale analysis of code generation using retrieval-augmented generation. We first curate a comprehensive evaluation benchmark, CodeRAG-Bench, encompassing three categories of code generation tasks. We examine top-performing models on CodeRAG-Bench by providing contexts retrieved from one or multiple sources.
  arXiv  Detail & Related papers  (2024-06-20T16:59:52Z)
• Distillation Enhanced Generative Retrieval [96.69326099136289]
  Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. In this work, we identify a viable direction to further enhance generative retrieval via distillation and propose a feasible framework, named DGR. We conduct experiments on four public datasets, and the results indicate that DGR achieves state-of-the-art performance among the generative retrieval methods.
  arXiv  Detail & Related papers  (2024-02-16T15:48:24Z)
• Generative Representational Instruction Tuning [89.76840377003178]
  GritLM 7B sets a new state of the art on the Massive Text Embedding Benchmark (MTEB) GritLM 8x7B outperforms all open generative language models that we tried while still being among the best embedding models.
  arXiv  Detail & Related papers  (2024-02-15T12:12:19Z)
• MGR: Multi-generator Based Rationalization [14.745836934156427]
  Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model. In this paper, we propose a simple yet effective method named MGR to simultaneously solve the two problems. We show that MGR improves the F1 score by up to 20.9% as compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-08T06:36:46Z)
• DORE: Document Ordered Relation Extraction based on Generative Framework [56.537386636819626]
  This paper investigates the root cause of the underwhelming performance of the existing generative DocRE models. We propose to generate a symbolic and ordered sequence from the relation matrix which is deterministic and easier for model to learn. Experimental results on four datasets show that our proposed method can improve the performance of the generative DocRE models.
  arXiv  Detail & Related papers  (2022-10-28T11:18:10Z)
• Gaussian-Bernoulli RBMs Without Tears [113.62579223055958]
  We propose a novel Gibbs-Langevin sampling algorithm that outperforms existing methods like Gibbs sampling. We propose a modified contrastive divergence (CD) algorithm so that one can generate images with GRBMs starting from noise.
  arXiv  Detail & Related papers  (2022-10-19T06:22:55Z)
• KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation [36.78998964614422]
  We propose a Knowledge-enhanced Commonsense Generation framework, termed KGR4, consisting of four stages: Retrieval, Retrospect, Refine, Rethink. KGR4 obtains 33.56 SPICE points in the official leaderboard, outperforming the previously-reported best result by 2.49 SPICE points.
  arXiv  Detail & Related papers  (2021-12-15T17:00:11Z)
• Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation [24.46198850268219]
  generative adversarial models have been applied extensively on text generation tasks. adversarial generators alleviate the exposure bias experienced by conventional maximum likelihood approaches. In this paper, we propose a novel approach which aims to improve the performance of adversarial text generation via efficiently decelerating mode collapse.
  arXiv  Detail & Related papers  (2020-03-12T04:47:52Z)

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.