Controllable Text Generation with Neurally-Decomposed Oracle

• URL: http://arxiv.org/abs/2205.14219v1
• Date: Fri, 27 May 2022 20:17:53 GMT
• Title: Controllable Text Generation with Neurally-Decomposed Oracle
• Authors: Tao Meng, Sidi Lu, Nanyun Peng and Kai-Wei Chang
• Abstract summary: We propose a framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO) We present a closed-form optimal solution to incorporate the token-level guidance into the base model for controllable generation.
• Score: 91.18959622763055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a general and efficient framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO). Given a pre-trained base language model and a sequence-level boolean oracle function, we propose to decompose the oracle function into token-level guidance to steer the base model in text generation. Specifically, the token-level guidance is approximated by a neural model trained with examples sampled from the base model, demanding no additional auxiliary labeled data. We present the closed-form optimal solution to incorporate the token-level guidance into the base model for controllable generation. We further provide a theoretical analysis of how the approximation quality of NADO affects the controllable generation results. Experiments conducted on two applications: (1) text generation with lexical constraints and (2) machine translation with formality control demonstrate that our framework efficiently guides the base model towards the given oracle while maintaining high generation quality.

Related papers

• Controlled Text Generation via Language Model Arithmetic [7.687678490751105]
  We introduce model arithmetic, a novel inference framework for composing and biasing Large Language Models. We show that model arithmetic allows fine-grained control of generated text while outperforming state-of-the-art on the task of toxicity reduction.
  arXiv  Detail & Related papers  (2023-11-24T13:41:12Z)
• DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models [55.06442277395388]
  NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. Vanilla NADO suffers from vanishing gradient for low-probability control signals. We propose a improved version of the NADO algorithm, namely DiNADO, which improves the performance of the NADO algorithm.
  arXiv  Detail & Related papers  (2023-06-20T18:36:52Z)
• 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)
• Plan-then-Generate: Controlled Data-to-Text Generation via Planning [11.127156275580305]
  We propose a novel Plan-then-Generate (PlanGen) framework to improve the controllability of neural data-to-text models. Our model is able to control both the intra-sentence and inter-sentence structure of the generated output.
  arXiv  Detail & Related papers  (2021-08-31T10:53:32Z)
• Few-Shot Table-to-Text Generation with Prototype Memory [14.69889589370148]
  We propose a new framework: Prototype-to-Generate (P2G), for table-to-text generation under the few-shot scenario. The proposed framework utilizes the retrieved prototypes, which are jointly selected by an IR system and a novel prototype selector. Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance.
  arXiv  Detail & Related papers  (2021-08-27T22:16:30Z)
• AutoBERT-Zero: Evolving BERT Backbone from Scratch [94.89102524181986]
  We propose an Operation-Priority Neural Architecture Search (OP-NAS) algorithm to automatically search for promising hybrid backbone architectures. We optimize both the search algorithm and evaluation of candidate models to boost the efficiency of our proposed OP-NAS. Experiments show that the searched architecture (named AutoBERT-Zero) significantly outperforms BERT and its variants of different model capacities in various downstream tasks.
  arXiv  Detail & Related papers  (2021-07-15T16:46:01Z)
• Control as Hybrid Inference [62.997667081978825]
  We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. We verify the scalability of our algorithm on a continuous control benchmark, demonstrating that it outperforms strong model-free and model-based baselines.
  arXiv  Detail & Related papers  (2020-07-11T19:44:09Z)
• Posterior Control of Blackbox Generation [126.33511630879713]
  We consider augmenting neural generation models with discrete control states learned through a structured latent-variable approach. We find that this method improves over standard benchmarks, while also providing fine-grained control.
  arXiv  Detail & Related papers  (2020-05-10T03:22:45Z)
• Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling [4.525267347429154]
  We train a Transformer-based neural model on the BERT language model. In addition, we propose a new method of BERT-windowing, which allows chunk-wise processing of texts longer than the BERT window size. The results of our models are compared to a baseline and the state-of-the-art models on the CNN/Daily Mail dataset.
  arXiv  Detail & Related papers  (2020-03-29T14:00:17Z)

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.