Neural Text Generation with Artificial Negative Examples

• URL: http://arxiv.org/abs/2012.14124v1
• Date: Mon, 28 Dec 2020 07:25:10 GMT
• Title: Neural Text Generation with Artificial Negative Examples
• Authors: Keisuke Shirai, Kazuma Hashimoto, Akiko Eriguchi, Takashi Ninomiya, Shinsuke Mori
• Abstract summary: We propose to suppress an arbitrary type of errors by training the text generation model in a reinforcement learning framework. We use a trainable reward function that is capable of discriminating between references and sentences containing the targeted type of errors. The experimental results show that our method can suppress the generation errors and achieve significant improvements on two machine translation and two image captioning tasks.
• Score: 7.187858820534111
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural text generation models conditioning on given input (e.g. machine translation and image captioning) are usually trained by maximum likelihood estimation of target text. However, the trained models suffer from various types of errors at inference time. In this paper, we propose to suppress an arbitrary type of errors by training the text generation model in a reinforcement learning framework, where we use a trainable reward function that is capable of discriminating between references and sentences containing the targeted type of errors. We create such negative examples by artificially injecting the targeted errors to the references. In experiments, we focus on two error types, repeated and dropped tokens in model-generated text. The experimental results show that our method can suppress the generation errors and achieve significant improvements on two machine translation and two image captioning tasks.

Related papers

• Few-Shot Detection of Machine-Generated Text using Style Representations [4.326503887981912]
  Language models that convincingly mimic human writing pose a significant risk of abuse. We propose to leverage representations of writing style estimated from human-authored text. We find that features effective at distinguishing among human authors are also effective at distinguishing human from machine authors.
  arXiv  Detail & Related papers  (2024-01-12T17:26:51Z)
• Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models [39.37532848489779]
  We propose Error Norm Truncation (ENT), a robust enhancement method to the standard training objective that truncates noisy data. We show that ENT improves generation quality over standard training and previous soft and hard truncation methods.
  arXiv  Detail & Related papers  (2023-10-02T01:30:27Z)
• A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages [39.75847219395984]
  We present a methodology for generative spelling correction (SC), which was tested on English and Russian languages. We study the ways those errors can be emulated in correct sentences to effectively enrich generative models' pre-train procedure. As a practical outcome of our work, we introduce SAGE(Spell checking via Augmentation and Generative distribution Emulation)
  arXiv  Detail & Related papers  (2023-08-18T10:07:28Z)
• Towards Fine-Grained Information: Identifying the Type and Location of Translation Errors [80.22825549235556]
  Existing approaches can not synchronously consider error position and type. We build an FG-TED model to predict the textbf addition and textbfomission errors. Experiments show that our model can identify both error type and position concurrently, and gives state-of-the-art results.
  arXiv  Detail & Related papers  (2023-02-17T16:20:33Z)
• Quark: Controllable Text Generation with Reinforced Unlearning [68.07749519374089]
  Large-scale language models often learn behaviors that are misaligned with user expectations. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property. For unlearning toxicity, negative sentiment, and repetition, our experiments show that Quark outperforms both strong baselines and state-of-the-art reinforcement learning methods.
  arXiv  Detail & Related papers  (2022-05-26T21:11:51Z)
• A Contrastive Framework for Neural Text Generation [46.845997620234265]
  We show that an underlying reason for model degeneration is the anisotropic distribution of token representations. We present a contrastive solution: (i) SimCTG, a contrastive training objective to calibrate the model's representation space, and (ii) a decoding method -- contrastive search -- to encourage diversity while maintaining coherence in the generated text.
  arXiv  Detail & Related papers  (2022-02-13T21:46:14Z)
• Scarecrow: A Framework for Scrutinizing Machine Text [69.26985439191151]
  We introduce a new structured, crowdsourced error annotation schema called Scarecrow. Scarecrow collects 13k annotations of 1.3k human and machine generate paragraphs of English language news text. These findings demonstrate the value of Scarecrow annotations in the assessment of current and future text generation systems.
  arXiv  Detail & Related papers  (2021-07-02T22:37:03Z)
• Grammatical Error Generation Based on Translated Fragments [0.0]
  We perform neural machine translation of sentence fragments in order to create large amounts of training data for English grammatical error correction. Our method aims at simulating mistakes made by second language learners, and produces a wider range of non-native style language.
  arXiv  Detail & Related papers  (2021-04-20T12:43:40Z)
• Improving Translation Robustness with Visual Cues and Error Correction [58.97421756225425]
  We introduce the idea of visual context to improve translation robustness against noisy texts. We also propose a novel error correction training regime by treating error correction as an auxiliary task.
  arXiv  Detail & Related papers  (2021-03-12T15:31:34Z)
• On the Transferability of Adversarial Attacksagainst Neural Text Classifier [121.6758865857686]
  We investigate the transferability of adversarial examples for text classification models. We propose a genetic algorithm to find an ensemble of models that can induce adversarial examples to fool almost all existing models. We derive word replacement rules that can be used for model diagnostics from these adversarial examples.
  arXiv  Detail & Related papers  (2020-11-17T10:45:05Z)
• On the Robustness of Language Encoders against Grammatical Errors [66.05648604987479]
  We collect real grammatical errors from non-native speakers and conduct adversarial attacks to simulate these errors on clean text data. Results confirm that the performance of all tested models is affected but the degree of impact varies.
  arXiv  Detail & Related papers  (2020-05-12T11:01:44Z)

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.