paper-with-me

Papers

Empirical Analysis of Training Strategies of Transformer-based Japanese Chit-chat Systems

2021-09-11 · Hiroaki Sugiyama, Masahiro Mizukami, Tsunehiro Arimoto, Hiromi Narimatsu, Yuya Chiba, Hideharu Nakajima, Toyomi Meguro

In recent years, several high-performance conversational systems have been proposed based on the Transformer encoder-decoder model. Although previous studies analyzed the effects of the model parameters and the decoding method on subjective dialogue evaluations with overall metrics, they did not analyze how the differences of fine-tuning datasets affect on user's detailed impression. In addition, the Transformer-based approach has only been verified for English, not for such languages with large inter-language distances as Japanese. In this study, we develop large-scale Transformer-based Japanese dialogue models and Japanese chit-chat datasets to examine the effectiveness of the Transformer-based approach for building chit-chat dialogue systems. We evaluated and analyzed the impressions of human dialogues in different fine-tuning datasets, model parameters, and the use of additional information.

📄 PDF Abstract BibTeX arXiv:2109.05217

Code (1)

nttcslab/japanese-dialog-transformers 공식 구현 pytorch

Tasks

Decoder

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
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…
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…
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…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Empirical Analysis of Training Strategies of Transformer-based Japanese Chit-chat Systems

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

In recent years, several high-performance conversational systems have been proposed based on the Transformer encoder-decoder model. Although previous studies analyzed the effects of the model parameters and the decoding …

Decoder

Is Japanese CCGBank empirically correct? A case study of passive and causative constructions

2023-02-28 · Daisuke Bekki, Hitomi Yanaka

The Japanese CCGBank serves as training and evaluation data for developing Japanese CCG parsers. However, since it is automatically generated from the Kyoto Corpus, a dependency treebank, its linguistic validity still ne…

Semantic Parsing

Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task

2020-07-01 · WS 2020 7 · Yuhui Sun, Mengxue Guo, Xiang Li, Jianwei Cui 외

This paper describes the Xiaomi{'}s submissions to the IWSLT20 shared open domain translation task for Chinese{\textless}-{\textgreater}Japanese language pair. We explore different model ensembling strategies based on re…

Domain AdaptationKnowledge DistillationRe-RankingTranslation

JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its Applications

2023-01-19 · Zihao Chen, Hisashi Handa, Kimiaki Shirahama

Contrastive learning is widely used for sentence representation learning. Despite this prevalence, most studies have focused exclusively on English and few concern domain adaptation for domain-specific downstream tasks, …

Contrastive LearningDomain AdaptationInformation RetrievalLanguage Modelling+7

Linguistically-driven Multi-task Pre-training for Low-resource Neural Machine Translation

2022-01-20 · Zhuoyuan Mao, Chenhui Chu, Sadao Kurohashi

In the present study, we propose novel sequence-to-sequence pre-training objectives for low-resource machine translation (NMT): Japanese-specific sequence to sequence (JASS) for language pairs involving Japanese as the s…

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationNMT+1