paper-with-me

Papers

Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings

2020-10-10 · Findings of the Association for Computational Linguistics 2020 · Prafull Prakash, Saurabh Kumar Shashidhar, Wenlong Zhao, Subendhu Rongali, Haidar Khan, Michael Kayser

The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants such as Amazon Alexa and Google Assistant on edge devices with limited memory budgets. We propose to learn compositional code embeddings to greatly reduce the sizes of BERT-base and RoBERTa-base. We also apply the technique to DistilBERT, ALBERT-base, and ALBERT-large, three already compressed BERT variants which attain similar state-of-the-art performances on semantic parsing with much smaller model sizes. We observe 95.15% ~ 98.46% embedding compression rates and 20.47% ~ 34.22% encoder compression rates, while preserving greater than 97.5% semantic parsing performances. We provide the recipe for training and analyze the trade-off between code embedding sizes and downstream performances.

📄 PDF Abstract BibTeX arXiv:2010.05002

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Parsing

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
WordPiece 설명 없음
Adam 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 $x$…
Multi-Head Attention 설명 없음
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…
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…

Similar Papers 제목 키워드 기반

Making Transformers Solve Compositional Tasks

2021-11-16 · ACL ARR September 2021 9 · Anonymous

Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this paper we explore the design space of Trans…

Semantic Parsing

Making Transformers Solve Compositional Tasks

2021-08-09 · ACL 2022 5 · Santiago Ontañón, Joshua Ainslie, Vaclav Cvicek, Zachary Fisher

Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this paper we explore the design space of Trans…

Semantic Parsing

Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention

2021-06-01 · NAACL 2021 4 · Pengcheng Yin, Hao Fang, Graham Neubig, Adam Pauls 외

We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers. Our approach builds on existing losses that encourage attention maps in neural sequence-to-sequence model…

Machine TranslationSemantic ParsingTranslationWord Alignment

Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

2023-07-25 · Hexuan Deng, Xin Zhang, Meishan Zhang, Xuebo Liu 외

In this paper, we conduct a holistic exploration of the Universal Decompositional Semantic (UDS) Parsing. We first introduce a cascade model for UDS parsing that decomposes the complex parsing task into semantically appr…

AttributeData AugmentationSemantic Parsing

Improving Compositional Generalization in Semantic Parsing

2020-10-12 · Findings of the Association for Computational Linguistics 2020 · Inbar Oren, Jonathan Herzig, Nitish Gupta, Matt Gardner 외

Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components o…

DecoderSemantic Parsing