paper-with-me

홈 › Papers

Improving Compositional Generalization with Self-Training for Data-to-Text Generation

2021-10-16 · ACL 2022 5 · Sanket Vaibhav Mehta, Jinfeng Rao, Yi Tay, Mihir Kale, Ankur P. Parikh, Emma Strubell

Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs). Such representations are compositional and it is costly to collect responses for all possible combinations of atomic meaning schemata, thereby necessitating few-shot generalization to novel MRs. In this work, we systematically study the compositional generalization of the state-of-the-art T5 models in few-shot data-to-text tasks. We show that T5 models fail to generalize to unseen MRs, and we propose a template-based input representation that considerably improves the model's generalization capability. To further improve the model's performance, we propose an approach based on self-training using fine-tuned BLEURT for pseudo response selection. On the commonly-used SGD and Weather benchmarks, the proposed self-training approach improves tree accuracy by 46%+ and reduces the slot error rates by 73%+ over the strong T5 baselines in few-shot settings.

📄 PDF Abstract BibTeX arXiv:2110.08467

Code (1)

google-research/google-research 공식 구현 tf

Tasks

Data-to-Text GenerationText Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Adafactor Adafactor is a stochastic optimization method based on Adam that reduces memory usage while retaining the empirical benefits of…

Similar Papers 제목 키워드 기반

Improving Compositional Generalization with Self-Training for Data-to-Text Generation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs). Such representations are compositional and it is costly to collect responses for all possible…

Data-to-Text GenerationText Generation

Compositional Generalization from First Principles

2023-09-21 · NeurIPS 2023 11

Leveraging the compositional nature of our world to expedite learning and facilitate generalization is a hallmark of human perception. In machine learning, on the other hand, achieving compositional generalization has pr…

SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval

2025-01-12 · WACV 2025 3 · Bhavin Jawade, Joao V. B. Soares, Kapil Thadani, Deen Dayal Mohan 외

Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds applications in a variety of domains inc…

Image RetrievalRetrievalTripletZero-Shot Composed Image Retrieval (ZS-CIR)

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation

2024-04-05 · Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song 외

Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect con…

AttributeBenchmarkingMeta-LearningText Generation

How Do In-Context Examples Affect Compositional Generalization?

2023-05-08 · Shengnan An, Zeqi Lin, Qiang Fu, Bei Chen 외

Compositional generalization--understanding unseen combinations of seen primitives--is an essential reasoning capability in human intelligence. The AI community mainly studies this capability by fine-tuning neural networ…

In-Context Learning