paper-with-me

홈 › Papers

Neural Knowledge Bank for Pretrained Transformers

2022-07-31 · Damai Dai, Wenbin Jiang, Qingxiu Dong, Yajuan Lyu, Qiaoqiao She, Zhifang Sui

The ability of pretrained Transformers to remember factual knowledge is essential but still limited for existing models. Inspired by existing work that regards Feed-Forward Networks (FFNs) in Transformers as key-value memories, we design a Neural Knowledge Bank (NKB) and a knowledge injection strategy to introduce extra factual knowledge for pretrained Transformers. The NKB is in the form of additional knowledgeable memory slots to the FFN and the memory-like architecture makes it highly interpretable and flexible. When injecting extra knowledge with the Salient Span Masking (SSM) pretraining objective, we fix the original pretrained model and train only the NKB. This training strategy makes sure the general language modeling ability of the original pretrained model is not influenced. By mounting the NKB onto the T5 model, we verify its strong ability to store extra factual knowledge based on three closed-book question answering datasets. Also, we prove that mounting the NKB will not degrade the general language modeling ability of T5 through two representative tasks, summarization and machine translation. Further, we thoroughly analyze the interpretability of the NKB and reveal the meaning of its keys and values in a human-readable way. Finally, we show the flexibility of the NKB by directly modifying its value vectors to update the factual knowledge stored in it.

📄 PDF Abstract BibTeX arXiv:2208.00399

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMachine TranslationQuestion AnsweringText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…

Similar Papers 제목 키워드 기반

COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers

2023-09-03 · Julien Denize, Mykola Liashuha, Jaonary Rabarisoa, Astrid Orcesi 외

We present COMEDIAN, a novel pipeline to initialize spatiotemporal transformers for action spotting, which involves self-supervised learning and knowledge distillation. Action spotting is a timestamp-level temporal actio…

Action DetectionAction SpottingKnowledge DistillationSelf-Supervised Learning

Knowledge Neurons in Pretrained Transformers

2021-09-17 · ACL ARR September 2021 9 · Anonymous

Large-scale pretrained language models are surprisingly good at recalling factual knowledge presented in the training corpus. In this paper, we present preliminary studies on how factual knowledge is stored in pretrained…

Knowledge Neurons in Pretrained Transformers

2021-04-18 · ACL 2022 5 · Damai Dai, Li Dong, Yaru Hao, Zhifang Sui 외

Large-scale pretrained language models are surprisingly good at recalling factual knowledge presented in the training corpus. In this paper, we present preliminary studies on how factual knowledge is stored in pretrained…

Thai Universal Dependency Treebank

2024-05-13 · Panyur Sriwirote, Wei Qi Leong, Charin Polpanumas, Santhawat Thanyawong 외

Automatic dependency parsing of Thai sentences has been underexplored, as evidenced by the lack of large Thai dependency treebanks with complete dependency structures and the lack of a published systematic evaluation of …

Dependency Parsing

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

2022-12-16 · Runpei Dong, Zekun Qi, Linfeng Zhang, Junbo Zhang 외

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential…

3D Point Cloud ClassificationFew-Shot 3D Point Cloud ClassificationKnowledge DistillationRepresentation Learning