paper-with-me

Papers

Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU

2021-09-15 · EMNLP 2021 11 · Patrick Kahardipraja, Brielen Madureira, David Schlangen

Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole, abstracting away the notion of time. Recent work attempts to apply Transformers incrementally via restart-incrementality by repeatedly feeding, to an unchanged model, increasingly longer input prefixes to produce partial outputs. However, this approach is computationally costly and does not scale efficiently for long sequences. In parallel, we witness efforts to make Transformers more efficient, e.g. the Linear Transformer (LT) with a recurrence mechanism. In this work, we examine the feasibility of LT for incremental NLU in English. Our results show that the recurrent LT model has better incremental performance and faster inference speed compared to the standard Transformer and LT with restart-incrementality, at the cost of part of the non-incremental (full sequence) quality. We show that the performance drop can be mitigated by training the model to wait for right context before committing to an output and that training with input prefixes is beneficial for delivering correct partial outputs.

📄 PDF Abstract BibTeX arXiv:2109.07364

Code (1)

pkhdipraja/towards-incremental-transformers 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Incremental Processing in the Age of Non-Incremental Encoders: An Empirical Assessment of Bidirectional Models for Incremental NLU

2020-10-11 · EMNLP 2020 11 · Brielen Madureira, David Schlangen

While humans process language incrementally, the best language encoders currently used in NLP do not. Both bidirectional LSTMs and Transformers assume that the sequence that is to be encoded is available in full, to be p…

Language ModelingLanguage Modelling

TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Model

2023-05-18 · Patrick Kahardipraja, Brielen Madureira, David Schlangen

Language is by its very nature incremental in how it is produced and processed. This property can be exploited by NLP systems to produce fast responses, which has been shown to be beneficial for real-time interactive app…

Natural Language UnderstandingSentence

Best of Both Worlds: Making High Accuracy Non-incremental Transformer-based Disfluency Detection Incremental

2021-08-01 · ACL 2021 5 · Morteza Rohanian, Julian Hough

While Transformer-based text classifiers pre-trained on large volumes of text have yielded significant improvements on a wide range of computational linguistics tasks, their implementations have been unsuitable for live …

Language ModellingSentencespeech-recognitionSpeech Recognition

Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners

2024-04-02 · CVPR 2024 1 · Keon-Hee Park, Kyungwoo Song, Gyeong-Moon Park

Few-Shot Class Incremental Learning (FSCIL) is a task that requires a model to learn new classes incrementally without forgetting when only a few samples for each class are given. FSCIL encounters two significant challen…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning+2

Improving Vision Transformers for Incremental Learning

2021-12-12 · Pei Yu, Yinpeng Chen, Ying Jin, Zicheng Liu

This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning. Although this recipe only combines existing techniques, developing the combination is not trivial. Firstly, naive appl…

class-incremental learningClass Incremental LearningIncremental Learning