Journal Article•
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
TL;DR: This article introduced a unified framework that converts all text-based language problems into a text-to-text format and compared pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks.
Abstract: Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new ``Colossal Clean Crawled Corpus'', we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.
Citations
More filters
Posted Content•
TL;DR: In this paper, the authors proposed a novel gender bias detection method by utilizing attention map for transformer-based models by comparing the different relation degree between the genders and the occupation according to the attention scores, and drew consistent gender bias conclusion by scanning the entire Wikipedia, a BERT pretraining dataset.
Abstract: In this paper, we propose a novel gender bias detection method by utilizing attention map for transformer-based models. We 1) give an intuitive gender bias judgement method by comparing the different relation degree between the genders and the occupation according to the attention scores, 2) design a gender bias detector by modifying the attention module, 3) insert the gender bias detector into different positions of the model to present the internal gender bias flow, and 4) draw the consistent gender bias conclusion by scanning the entire Wikipedia, a BERT pretraining dataset. We observe that 1) the attention matrices, Wq and Wk introduce much more gender bias than other modules (including the embedding layer) and 2) the bias degree changes periodically inside of the model (attention matrix Q, K, V, and the remaining part of the attention layer (including the fully-connected layer, the residual connection, and the layer normalization module) enhance the gender bias while the averaged attentions reduces the bias).
1 citations
TL;DR: This article used paraphrase detection and paraphrase generation tasks to improve the robustness of question answering models to paraphrase paraphrasing in the context of natural language understanding tasks, and found that paraphrase knowledge does not transfer to other decaNLP tasks.
Abstract: Multitask learning has led to significant advances in Natural Language Processing, including the decaNLP benchmark where question answering is used to frame 10 natural language understanding tasks in a single model. In this work we show how models trained to solve decaNLP fail with simple paraphrasing of the question. We contribute a crowd-sourced corpus of paraphrased questions (PQ-decaNLP), annotated with paraphrase phenomena. This enables analysis of how transformations such as swapping the class labels and changing the sentence modality lead to a large performance degradation. Training both MQAN and the newer T5 model using PQ-decaNLP improves their robustness and for some tasks improves the performance on the original questions, demonstrating the benefits of a model which is more robust to paraphrasing. Additionally, we explore how paraphrasing knowledge is transferred between tasks, with the aim of exploiting the multitask property to improve the robustness of the models. We explore the addition of paraphrase detection and paraphrase generation tasks, and find that while both models are able to learn these new tasks, knowledge about paraphrasing does not transfer to other decaNLP tasks.
1 citations
Posted Content•
TL;DR: TreeBERT as discussed by the authors is a tree-based pre-trained model for improving programming language-oriented generation tasks, which represents the AST corresponding to the code as a set of composition paths and introduces node position embedding.
Abstract: Source code can be parsed into the abstract syntax tree (AST) based on defined syntax rules. However, in pre-training, little work has considered the incorporation of tree structure into the learning process. In this paper, we present TreeBERT, a tree-based pre-trained model for improving programming language-oriented generation tasks. To utilize tree structure, TreeBERT represents the AST corresponding to the code as a set of composition paths and introduces node position embedding. The model is trained by tree masked language modeling (TMLM) and node order prediction (NOP) with a hybrid objective. TMLM uses a novel masking strategy designed according to the tree's characteristics to help the model understand the AST and infer the missing semantics of the AST. With NOP, TreeBERT extracts the syntactical structure by learning the order constraints of nodes in AST. We pre-trained TreeBERT on datasets covering multiple programming languages. On code summarization and code documentation tasks, TreeBERT outperforms other pre-trained models and state-of-the-art models designed for these tasks. Furthermore, TreeBERT performs well when transferred to the pre-trained unseen programming language.
1 citations
01 Aug 2021
TL;DR: This article propose a two-stage finetuning method to alleviate the pretrain-finetune discrepancy and introduce a novel multi-source sequence generation model with a fine encoder to learn better representations in MSG tasks.
Abstract: Multi-source sequence generation (MSG) is an important kind of sequence generation tasks that takes multiple sources, including automatic post-editing, multi-source translation, multi-document summarization, etc. As MSG tasks suffer from the data scarcity problem and recent pretrained models have been proven to be effective for low-resource downstream tasks, transferring pretrained sequence-to-sequence models to MSG tasks is essential. Although directly finetuning pretrained models on MSG tasks and concatenating multiple sources into a single long sequence is regarded as a simple method to transfer pretrained models to MSG tasks, we conjecture that the direct finetuning method leads to catastrophic forgetting and solely relying on pretrained self-attention layers to capture cross-source information is not sufficient. Therefore, we propose a two-stage finetuning method to alleviate the pretrain-finetune discrepancy and introduce a novel MSG model with a fine encoder to learn better representations in MSG tasks. Experiments show that our approach achieves new state-of-the-art results on the WMT17 APE task and multi-source translation task using the WMT14 test set. When adapted to document-level translation, our framework outperforms strong baselines significantly.
1 citations
Posted Content•
TL;DR: This paper extended a sequence-to-sequence model with a retrieval component, used to fetch existing similar examples and provide them as an additional input to the model, which outperforms the baseline method by 1.5% absolute macro-F1, especially at the low resource setting.
Abstract: While large pre-trained language models accumulate a lot of knowledge in their parameters, it has been demonstrated that augmenting it with non-parametric retrieval-based memory has a number of benefits from accuracy improvements to data efficiency for knowledge-focused tasks, such as question answering. In this paper, we are applying retrieval-based modeling ideas to the problem of multi-domain task-oriented semantic parsing for conversational assistants. Our approach, RetroNLU, extends a sequence-to-sequence model architecture with a retrieval component, used to fetch existing similar examples and provide them as an additional input to the model. In particular, we analyze two settings, where we augment an input with (a) retrieved nearest neighbor utterances (utterance-nn), and (b) ground-truth semantic parses of nearest neighbor utterances (semparse-nn). Our technique outperforms the baseline method by 1.5% absolute macro-F1, especially at the low resource setting, matching the baseline model accuracy with only 40% of the data. Furthermore, we analyze the nearest neighbor retrieval component's quality, model sensitivity and break down the performance for semantic parses of different utterance complexity.
1 citations