Figate
发表于 2025-3-28 15:10:38
Category-Based Strategy-Driven Question Generator for Visual Dialogueerated. Then the question is generated with the helps of category-based dialogue strategy as well as encoding of both the image and dialogue history. The evaluation on large-scale visual dialogue dataset GuessWhat?! shows that our method can help guesser achieve 51.71% success rate which is the state-of-the-art on the supervised training methods.
nonchalance
发表于 2025-3-28 20:25:42
0302-9743 n August 2021..The 31 full presented in this volume were carefully reviewed and selected from 90 submissions...The conference papers covers the following topics such as Machine Translation and Multilingual Information Processing, Minority Language Information Processing, Social Computing and Sentime
壕沟
发表于 2025-3-29 02:34:23
http://reply.papertrans.cn/23/2258/225764/225764_43.png
BIDE
发表于 2025-3-29 06:37:51
Conference proceedings 2021021..The 31 full presented in this volume were carefully reviewed and selected from 90 submissions...The conference papers covers the following topics such as Machine Translation and Multilingual Information Processing, Minority Language Information Processing, Social Computing and Sentiment Analysi
Generosity
发表于 2025-3-29 10:24:37
http://reply.papertrans.cn/23/2258/225764/225764_45.png
Benzodiazepines
发表于 2025-3-29 13:48:17
Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph s on the SAMSum dataset show that our model can outperform various methods. We also conduct zero-shot setting experiments on the Argumentative Dialogue Summary Corpus, the results show that our model can better generalized to the new domain.
镶嵌细工
发表于 2025-3-29 17:52:44
http://reply.papertrans.cn/23/2258/225764/225764_47.png
AVERT
发表于 2025-3-29 20:38:45
http://reply.papertrans.cn/23/2258/225764/225764_48.png
Limerick
发表于 2025-3-30 02:17:31
Gwendal Priser,Elena Vanneaux,Goran Frehsedel. In addition, we alleviated the lack of Korean corpus resources by adding training data. In our experiment, we introduce a monolingual corpus of a certain scale to construct pseudo-parallel data. At the same time, we also preprocessed the Korean corpus with different granularities to overcome th