paper-with-me

Papers

Generating Repetitions with Appropriate Repeated Words

2022-07-03 · NAACL 2022 7 · Toshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura

A repetition is a response that repeats words in the previous speaker's utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repetition generation. To the best of our knowledge, this is the first neural approach to address repetition generation. We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding. We conducted automatic and human evaluations involving applying these methods to the pre-trained language model T5 for generating repetitions. The experimental results indicate that our methods outperformed baselines in both evaluations.

📄 PDF Abstract BibTeX arXiv:2207.00929

Code (1)

titech-nlp/repetition-generation 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

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 &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
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
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation

2022-06-06 · Jin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai 외

While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decod…

SentenceText GenerationText Summarization

Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective

2023-09-21 · NeurIPS 2023 11

There are a number of diverging hypotheses about the neural text degeneration problem, i.e., generating repetitive and dull loops, which makes this problem both interesting and confusing. In this work, we aim to advance …

Taming Repetition in Dialogue Generation

2021-12-16 · Yadong Xi, Jiashu Pu, Xiaoxi Mao

The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repe…

Dialogue GenerationDiversity

Repeated Pattern Detection using CNN activations

2017-03-24 · IEEE Winter Conference on Applications of Computer Vision (WACV) 2017 3 · Louis Lettry, Michal Perdoch, Kenneth Vanhoey, Luc van Gool

We propose a new approach for detecting repeated patterns on a grid in a single image. To do so, we detect repetitions in the space of pre-trained deep CNN filter responses at all layer levels. These encode features at s…

Generic Mechanism for Reducing Repetitions in Encoder-Decoder Models

2021-09-01 · RANLP 2021 9 · Ying Zhang, Hidetaka Kamigaito, Tatsuya Aoki, Hiroya Takamura 외

Encoder-decoder models have been commonly used for many tasks such as machine translation and response generation. As previous research reported, these models suffer from generating redundant repetition. In this research…

DecoderMachine TranslationResponse GenerationSentence+1