From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots
标题:从单词到句子:用视觉枢轴进行零资源机器翻译的渐进式学习方法
作者: Shizhe Chen, Jianlong Fu
备注:Accepted by IJCAI 2019
链接:https://arxiv.org/abs/1906.00872
使用图像作为中间枢纽,实现翻译
Gender-preserving Debiasing for Pre-trained Word Embeddings
标题:保留性别的Debyasing用于预先训练的单词嵌入
作者: Masahiro Kaneko, Danushka Bollegala
备注:Accepted as a long paper to the 57th Annual Conference of the Association for Computational Linguistics (ACL-2019)
链接:https://arxiv.org/abs/1906.00742
更好训练词向量,减少下游任务偏差
Latent Retrieval for Weakly Supervised Open Domain Question Answering
标题:弱监督开放域问答的潜在检索
作者: Kenton Lee, Kristina Toutanova
备注:Accepted to ACL 2019
链接:https://arxiv.org/abs/1906.00300
使用反响完型任务进行训练
Emotional Embeddings: Refining Word Embeddings to Capture Emotional Content of Words
标题:情感嵌入:精炼词嵌入捕捉词的情感内容
作者: Armin Seyeditabari, Wlodek Zadrozny
链接:https://arxiv.org/abs/1906.00112
融合心理模型???没看懂