paper-with-me

Papers

BERTGEN: Multi-task Generation through BERT

2021-06-07 · ACL 2021 5 · Faidon Mitzalis, Ozan Caglayan, Pranava Madhyastha, Lucia Specia

We present BERTGEN, a novel generative, decoder-only model which extends BERT by fusing multimodal and multilingual pretrained models VL-BERT and M-BERT, respectively. BERTGEN is auto-regressively trained for language generation tasks, namely image captioning, machine translation and multimodal machine translation, under a multitask setting. With a comprehensive set of evaluations, we show that BERTGEN outperforms many strong baselines across the tasks explored. We also show BERTGEN's ability for zero-shot language generation, where it exhibits competitive performance to supervised counterparts. Finally, we conduct ablation studies which demonstrate that BERTGEN substantially benefits from multi-tasking and effectively transfers relevant inductive biases from the pre-trained models.

📄 PDF Abstract BibTeX arXiv:2106.03484

Code (1)

ImperialNLP/BertGen 공식 구현 pytorch

Tasks

DecoderImage CaptioningMachine TranslationMultimodal Machine TranslationText GenerationTranslation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
VL-BERT VL-BERT is pre-trained on a large-scale image-captions dataset together with text-only corpus. The input to the model are either words from the input sentences or…
Adam 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

What BERT Sees: Cross-Modal Transfer for Visual Question Generation

2020-02-25 · INLG (ACL) 2020 12 · Thomas Scialom, Patrick Bordes, Paul-Alexis Dray, Jacopo Staiano 외

Pre-trained language models have recently contributed to significant advances in NLP tasks. Recently, multi-modal versions of BERT have been developed, using heavy pre-training relying on vast corpora of aligned textual …

Question GenerationQuestion-GenerationText GenerationVisual Question Answering (VQA)

Distilling Knowledge Learned in BERT for Text Generation

2019-11-10 · ACL 2020 6 · Yen-Chun Chen, Zhe Gan, Yu Cheng, Jingzhou Liu 외

Large-scale pre-trained language model such as BERT has achieved great success in language understanding tasks. However, it remains an open question how to utilize BERT for language generation. In this paper, we present …

Language ModelingLanguage ModellingMachine TranslationMasked Language Modeling+4

VD-BERT: A Unified Vision and Dialog Transformer with BERT

2020-04-28 · EMNLP 2020 11 · Yue Wang, Shafiq Joty, Michael R. Lyu, Irwin King 외

Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attentio…

Answer GenerationVisual Dialog

BERTomelo: Your Portuguese Encoder Best Friend

2026-06-27 · Rennê Ruan Alves Oliveira, Gustavo Cordeiro Galvão Van Erven, Luís Paulo Faina Garcia arxiv

Encoders have become the state of the art for multiple NLP tasks, especially those requiring deep contextual understanding. While multilingual models offer broad coverage, dedicated monolingual encoders are essential for…

Automatic Text Evaluation through the Lens of Wasserstein Barycenters

2021-08-27 · EMNLP 2021 11 · Pierre Colombo, Guillaume Staerman, Chloe Clavel, Pablo Piantanida

A new metric \texttt{BaryScore} to evaluate text generation based on deep contextualized embeddings e.g., BERT, Roberta, ELMo) is introduced. This metric is motivated by a new framework relying on optimal transport tools…

Image CaptioningMachine TranslationText GenerationText Summarization+1