no code implementations • 12 Jan 2016 • Yuqing Hou, Zhouchen Lin, Jin-Ge Yao
Annotating images with tags is useful for indexing and retrieving images.
no code implementations • WS 2017 • Jin-Ge Yao, Jianmin Zhang, Xiaojun Wan, Jianguo Xiao
We study the task of constructing sports news report automatically from live commentary and focus on content selection.
no code implementations • IJCNLP 2017 • Liunian Li, Xiaojun Wan, Jin-Ge Yao, Siming Yan
In this work we study the challenging task of automatically constructing essays for Chinese college entrance examination where the topic is specified in advance.
no code implementations • ACL 2018 • Danqing Huang, Jin-Ge Yao, Chin-Yew Lin, Qingyu Zhou, Jian Yin
To solve math word problems, previous statistical approaches attempt at learning a direct mapping from a problem description to its corresponding equation system.
no code implementations • 15 Aug 2018 • Feng Nie, Hailin Chen, Jinpeng Wang, Jin-Ge Yao, Chin-Yew Lin, Rong pan
Recent neural models for data-to-document generation have achieved remarkable progress in producing fluent and informative texts.
1 code implementation • 8 Sep 2018 • Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong pan, Chin-Yew Lin
Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data.
no code implementations • EMNLP 2018 • Fangfang Zhang, Jin-Ge Yao, Rui Yan
Many modern neural document summarization systems based on encoder-decoder networks are designed to produce abstractive summaries.
no code implementations • EMNLP 2018 • Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong pan, Chin-Yew Lin
Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data.
1 code implementation • EMNLP 2018 • Guanghui Qin, Jin-Ge Yao, Xuening Wang, Jinpeng Wang, Chin-Yew Lin
Previous work on grounded language learning did not fully capture the semantics underlying the correspondences between structured world state representations and texts, especially those between numerical values and lexical terms.
no code implementations • EMNLP 2018 • Longxu Dou, Guanghui Qin, Jinpeng Wang, Jin-Ge Yao, Chin-Yew Lin
Data2Text Studio is a platform for automated text generation from structured data.
no code implementations • 8 Mar 2019 • Tianwen Jiang, Sendong Zhao, Jing Liu, Jin-Ge Yao, Ming Liu, Bing Qin, Ting Liu, Chin-Yew Lin
Time-DS is composed of a time series instance-popularity and two strategies.
1 code implementation • ACL 2019 • Tianyu Liu, Jin-Ge Yao, Chin-Yew Lin
Most of the recently proposed neural models for named entity recognition have been purely data-driven, with a strong emphasis on getting rid of the efforts for collecting external resources or designing hand-crafted features.
Ranked #14 on Named Entity Recognition (NER) on Ontonotes v5 (English) (using extra training data)
no code implementations • ACL 2019 • Feng Nie, Jin-Ge Yao, Jinpeng Wang, Rong pan, Chin-Yew Lin
Recent neural language generation systems often \textit{hallucinate} contents (i. e., producing irrelevant or contradicted facts), especially when trained on loosely corresponding pairs of the input structure and text.
no code implementations • WS 2019 • Guanyi Chen, Jin-Ge Yao
Automatic natural language generation systems need to use the contextually-appropriate verbs when describing different kinds of facts or events, which has triggered research interest on verb selection for data-to-text generation.
1 code implementation • ACL 2021 • Tingting Ma, Jin-Ge Yao, Chin-Yew Lin, Tiejun Zhao
The general format of natural language inference (NLI) makes it tempting to be used for zero-shot text classification by casting any target label into a sentence of hypothesis and verifying whether or not it could be entailed by the input, aiming at generic classification applicable on any specified label space.