Controlling the Focus of Pretrained Language Generation Models

• URL: http://arxiv.org/abs/2203.01146v1
• Date: Wed, 2 Mar 2022 14:46:14 GMT
• Title: Controlling the Focus of Pretrained Language Generation Models
• Authors: Jiabao Ji, Yoon Kim, James Glass, Tianxing He
• Abstract summary: We develop a control mechanism by which a user can select spans of context as "highlights" for the model to focus on, and generate relevant output. To achieve this goal, we augment a pretrained model with trainable "focus vectors" that are directly applied to the model's embeddings. Our experiments show that the trained focus vectors are effective in steering the model to generate outputs that are relevant to user-selected highlights.
• Score: 22.251710018744497
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The finetuning of pretrained transformer-based language generation models are typically conducted in an end-to-end manner, where the model learns to attend to relevant parts of the input by itself. However, there does not exist a mechanism to directly control the model's focus. This work aims to develop a control mechanism by which a user can select spans of context as "highlights" for the model to focus on, and generate relevant output. To achieve this goal, we augment a pretrained model with trainable "focus vectors" that are directly applied to the model's embeddings, while the model itself is kept fixed. These vectors, trained on automatic annotations derived from attribution methods, act as indicators for context importance. We test our approach on two core generation tasks: dialogue response generation and abstractive summarization. We also collect evaluation data where the highlight-generation pairs are annotated by humans. Our experiments show that the trained focus vectors are effective in steering the model to generate outputs that are relevant to user-selected highlights.

Related papers

• Stanceformer: Target-Aware Transformer for Stance Detection [59.69858080492586]
  Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively. We introduce Stanceformer, a target-aware transformer model that incorporates enhanced attention towards the targets during both training and inference.
  arXiv  Detail & Related papers  (2024-10-09T17:24:28Z)
• Adjusting Pretrained Backbones for Performativity [34.390793811659556]
  We propose a novel technique to adjust pretrained backbones for performativity in a modular way. We show how it leads to smaller loss along the retraining trajectory and enables us to effectively select among candidate models to anticipate performance degradations.
  arXiv  Detail & Related papers  (2024-10-06T14:41:13Z)
• A Two-Phase Recall-and-Select Framework for Fast Model Selection [13.385915962994806]
  We propose a two-phase (coarse-recall and fine-selection) model selection framework. It aims to enhance the efficiency of selecting a robust model by leveraging the models' training performances on benchmark datasets. It has been demonstrated that the proposed methodology facilitates the selection of a high-performing model at a rate about 3x times faster than conventional baseline methods.
  arXiv  Detail & Related papers  (2024-03-28T14:44:44Z)
• Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
  We propose self-distillation as a regularization for a further pre-training stage. We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
  arXiv  Detail & Related papers  (2022-09-30T02:25:12Z)
• Exploring Target Representations for Masked Autoencoders [78.57196600585462]
  We show that a careful choice of the target representation is unnecessary for learning good representations. We propose a multi-stage masked distillation pipeline and use a randomly model as the teacher. A proposed method to perform masked knowledge distillation with bootstrapped teachers (dBOT) outperforms previous self-supervised methods by nontrivial margins.
  arXiv  Detail & Related papers  (2022-09-08T16:55:19Z)
• Extracting Latent Steering Vectors from Pretrained Language Models [14.77762401765532]
  We show that latent vectors can be extracted directly from language model decoders without fine-tuning. Experiments show that there exist steering vectors, which, when added to the hidden states of the language model, generate a target sentence nearly perfectly. We find that distances between steering vectors reflect sentence similarity when evaluated on a textual similarity benchmark.
  arXiv  Detail & Related papers  (2022-05-10T19:04:37Z)
• A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis [90.24921443175514]
  We focus on aspect-based sentiment analysis, which involves extracting aspect term, category, and predicting their corresponding polarities. We propose to reformulate the extraction and prediction tasks into the sequence generation task, using a generative language model with unidirectional attention. Our approach outperforms the previous state-of-the-art (based on BERT) on average performance by a large margins in few-shot and full-shot settings.
  arXiv  Detail & Related papers  (2022-04-11T18:31:53Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)
• Guiding Attention for Self-Supervised Learning with Transformers [24.785500242464646]
  We propose a technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained models contain a majority of non-linguistic regularities.
  arXiv  Detail & Related papers  (2020-10-06T00:04:08Z)
• Interpretable Entity Representations through Large-Scale Typing [61.4277527871572]
  We present an approach to creating entity representations that are human readable and achieve high performance out of the box. Our representations are vectors whose values correspond to posterior probabilities over fine-grained entity types. We show that it is possible to reduce the size of our type set in a learning-based way for particular domains.
  arXiv  Detail & Related papers  (2020-04-30T23:58:03Z)

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.