GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation

• URL: http://arxiv.org/abs/2211.10330v1
• Date: Fri, 18 Nov 2022 16:39:45 GMT
• Title: GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation
• Authors: Biyang Guo, Yeyun Gong, Yelong Shen, Songqiao Han, Hailiang Huang, Nan Duan, Weizhu Chen
• Abstract summary: We introduce GENIUS: a conditional text generation model using sketches as input. GENIUS is pre-trained on a large-scale textual corpus with a novel reconstruction from sketch objective. We show that GENIUS can be used as a strong and ready-to-use data augmentation tool for various natural language processing (NLP) tasks.
• Score: 76.7772833556714
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce GENIUS: a conditional text generation model using sketches as input, which can fill in the missing contexts for a given sketch (key information consisting of textual spans, phrases, or words, concatenated by mask tokens). GENIUS is pre-trained on a large-scale textual corpus with a novel reconstruction from sketch objective using an extreme and selective masking strategy, enabling it to generate diverse and high-quality texts given sketches. Comparison with other competitive conditional language models (CLMs) reveals the superiority of GENIUS's text generation quality. We further show that GENIUS can be used as a strong and ready-to-use data augmentation tool for various natural language processing (NLP) tasks. Most existing textual data augmentation methods are either too conservative, by making small changes to the original text, or too aggressive, by creating entirely new samples. With GENIUS, we propose GeniusAug, which first extracts the target-aware sketches from the original training set and then generates new samples based on the sketches. Empirical experiments on 6 text classification datasets show that GeniusAug significantly improves the models' performance in both in-distribution (ID) and out-of-distribution (OOD) settings. We also demonstrate the effectiveness of GeniusAug on named entity recognition (NER) and machine reading comprehension (MRC) tasks. (Code and models are publicly available at https://github.com/microsoft/SCGLab and https://github.com/beyondguo/genius)

Related papers

• Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models [70.86603627188519]
  We focus on a novel, yet challenging task of generating a coherent image sequence based on a given storyline, denoted as open-ended visual storytelling. We propose a learning-based auto-regressive image generation model, termed as StoryGen, with a novel vision-language context module. We show StoryGen can generalize to unseen characters without any optimization, and generate image sequences with coherent content and consistent character.
  arXiv  Detail & Related papers  (2023-06-01T17:58:50Z)
• Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment [81.73717488887938]
  Language-Quantized AutoEncoder (LQAE) learns to align text-image data in an unsupervised manner by leveraging pretrained language models. LQAE learns to represent similar images with similar clusters of text tokens, thereby aligning these two modalities without the use of aligned text-image pairs. This enables few-shot image classification with large language models (e.g., GPT-3) as well as linear classification of images based on BERT text features.
  arXiv  Detail & Related papers  (2023-02-02T06:38:44Z)
• On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization [89.94078728495423]
  We show that recent advances in each modality, CLIP image representations and scaling of language models, do not consistently improve multimodal self-rationalization of tasks with multimodal inputs. Our findings call for a backbone modelling approach that can be built on to advance text generation from images and text beyond image captioning.
  arXiv  Detail & Related papers  (2022-05-24T00:52:40Z)
• DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting [91.56988987393483]
  We present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP. Specifically, we convert the original image-text matching problem in CLIP to a pixel-text matching problem and use the pixel-text score maps to guide the learning of dense prediction models. Our method is model-agnostic, which can be applied to arbitrary dense prediction systems and various pre-trained visual backbones.
  arXiv  Detail & Related papers  (2021-12-02T18:59:32Z)
• Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events [39.577220559911055]
  We propose a new task named "Outline to Story" (O2S) as a test bed for fine-grained controllable generation of long text. We then create datasets for future benchmarks, built by state-of-the-art keyword extraction techniques.
  arXiv  Detail & Related papers  (2021-01-04T08:16:21Z)
• Offline Handwritten Chinese Text Recognition with Convolutional Neural Networks [5.984124397831814]
  In this paper, we build the models using only the convolutional neural networks and use CTC as the loss function. We achieve 6.81% character error rate (CER) on the ICDAR 2013 competition set, which is the best published result without language model correction.
  arXiv  Detail & Related papers  (2020-06-28T14:34:38Z)
• PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation [92.7366819044397]
  Self-supervised pre-training has emerged as a powerful technique for natural language understanding and generation. This work presents PALM with a novel scheme that jointly pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus. An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks.
  arXiv  Detail & Related papers  (2020-04-14T06:25:36Z)
• ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation [0.9542023122304099]
  We present ScrabbleGAN, a semi-supervised approach to synthesize handwritten text images. ScrabbleGAN relies on a novel generative model which can generate images of words with an arbitrary length.
  arXiv  Detail & Related papers  (2020-03-23T21:41:19Z)

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.