paper-with-me

홈 › Papers

Towards Equipping Transformer with the Ability of Systematic Compositionality

2023-12-12 · Chen Huang, Peixin Qin, Wenqiang Lei, Jiancheng Lv

One of the key factors in language productivity and human cognition is the ability of systematic compositionality, which refers to understanding composed unseen examples of seen primitives. However, recent evidence reveals that the Transformers have difficulty generalizing the composed context based on the seen primitives. To this end, we take the first step to propose a compositionality-aware Transformer called CAT and two novel pre-training tasks to facilitate systematic compositionality. We tentatively provide a successful implementation of a multi-layer CAT on the basis of the especially popular BERT. The experimental results demonstrate that CAT outperforms baselines on compositionality-aware tasks with minimal impact on the effectiveness on standardized language understanding tasks.

📄 PDF Abstract BibTeX arXiv:2312.07280

Code (1)

huangzichun/CompBERT 공식 구현 pytorch

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
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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.

Similar Papers 제목 키워드 기반

Inducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks

2021-11-01 · EMNLP 2021 11 · Yichen Jiang, Mohit Bansal

Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability i…

Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks

2021-09-30 · Yichen Jiang, Mohit Bansal

Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability i…

Enabling Systematic Generalization in Abstract Spatial Reasoning through Meta-Learning for Compositionality

2025-04-02 · Philipp Mondorf, Shijia Zhou, Monica Riedler, Barbara Plank

Systematic generalization refers to the capacity to understand and generate novel combinations from known components. Despite recent progress by large language models (LLMs) across various domains, these models often fai…

Meta-LearningSpatial ReasoningSystematic GeneralizationTranslation

Interpreting token compositionality in LLMs: A robustness analysis

2024-10-16 · Nura Aljaafari, Danilo S. Carvalho, André Freitas

Understanding the internal mechanisms of large language models (LLMs) is integral to enhancing their reliability, interpretability, and inference processes. We present Constituent-Aware Pooling (CAP), a methodology desig…

Definition Modelling

Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods

2022-12-13 · CVPR 2024 1 · Mingqi Jiang, Saeed Khorram, Li Fuxin

In order to gain insights about the decision-making of different visual recognition backbones, we propose two methodologies, sub-explanation counting and cross-testing, that systematically applies deep explanation algori…

Decision Making