paper-with-me

홈 › Papers

Adaptable Multi-Domain Language Model for Transformer ASR

2020-08-14 · Taewoo Lee, Min-Joong Lee, Tae Gyoon Kang, Seokyeoung Jung, Minseok Kwon, Yeona Hong, Jungin Lee, Kyoung-Gu Woo, Ho-Gyeong Kim, Jiseung Jeong, Ji-Hyun Lee, Hosik Lee, Young Sang Choi

We propose an adapter based multi-domain Transformer based language model (LM) for Transformer ASR. The model consists of a big size common LM and small size adapters. The model can perform multi-domain adaptation with only the small size adapters and its related layers. The proposed model can reuse the full fine-tuned LM which is fine-tuned using all layers of an original model. The proposed LM can be expanded to new domains by adding about 2% of parameters for a first domain and 13% parameters for after second domain. The proposed model is also effective in reducing the model maintenance cost because it is possible to omit the costly and time-consuming common LM pre-training process. Using proposed adapter based approach, we observed that a general LM with adapter can outperform a dedicated music domain LM in terms of word error rate (WER).

📄 PDF Abstract BibTeX arXiv:2008.06208

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationLanguage ModelingLanguage Modellingmodel

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…

Similar Papers 제목 키워드 기반

Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models

2025-01-17 · Pit Neitemeier, Björn Deiseroth, Constantin Eichenberg, Lukas Balles

Tokenization is a fundamental step in natural language processing, breaking text into units that computational models can process. While learned subword tokenizers have become the de-facto standard, they present challeng…

Language ModellingWord Embeddings

ModRWKV: Transformer Multimodality in Linear Time

2025-05-20 · Jiale Kang, Ziyin Yue, Qingyu Yin, Jiang Rui 외

Currently, most multimodal studies are based on large language models (LLMs) with quadratic-complexity Transformer architectures. While linear models like RNNs enjoy low inference costs, their application has been largel…

Computational Efficiency

Adaptable and Reliable Text Classification using Large Language Models

2024-05-17 · Zhiqiang Wang, Yiran Pang, Yanbin Lin, Xingquan Zhu

Text classification is fundamental in Natural Language Processing (NLP), and the advent of Large Language Models (LLMs) has revolutionized the field. This paper introduces an adaptable and reliable text classification pa…

ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONSentiment Analysis+2

PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis

2023-04-24 · Shu Wei, Nuo Xu

Document layout analysis has a wide range of requirements across various domains, languages, and business scenarios. However, most current state-of-the-art algorithms are language-dependent, with architectures that rely …

Document Layout AnalysisGraph Neural NetworkImage SegmentationSemantic Segmentation

Guiding Symbolic Natural Language Grammar Induction via Transformer-Based Sequence Probabilities

2020-05-26 · Ben Goertzel, Andres Suarez Madrigal, Gino Yu

A novel approach to automated learning of syntactic rules governing natural languages is proposed, based on using probabilities assigned to sentences (and potentially longer word sequences) by transformer neural network …

Clustering