发怨言
发表于 2025-3-25 06:30:14
Cue-Phrase-Based Text Segmentation and Optimal Segment Concatenation for the NTCIR-14 QA Lab-PoliInf We divided the segmentation subtask into two steps, segmentation and search. Cue phrases were effectively used to detect segment boundaries. We compared five methods for detecting segment boundaries: a rule-based method, three supervised learning methods, and a novel semi-supervised learning method
textile
发表于 2025-3-25 08:55:30
http://reply.papertrans.cn/67/6602/660144/660144_22.png
institute
发表于 2025-3-25 12:18:08
Team’s Summarization System at the NTCIR-14 QA Lab-PoliInfoeches using random forest classifiers. Since we encountered an imbalance in the data, we were unable to achieve good results in this subtask when training on all data. To solve this problem, we developed a new summarization system that applies multiple random forest classifiers training on different
相反放置
发表于 2025-3-25 17:41:44
http://reply.papertrans.cn/67/6602/660144/660144_24.png
capsaicin
发表于 2025-3-25 21:29:09
http://reply.papertrans.cn/67/6602/660144/660144_25.png
Liability
发表于 2025-3-26 02:28:33
http://reply.papertrans.cn/67/6602/660144/660144_26.png
转折点
发表于 2025-3-26 06:30:47
THUIR at the NTCIR-14 WWW-2 Taskesults in the WWW-2 task. In the Chinese subtask, we designed and trained two neural ranking models on the Sogou-QCL dataset. In the English subtask, we adopted learning to rank models by training them on MQ2007 and MQ2008 datasets. Our methods achieved the best performances in both Chinese and Engl
屈尊
发表于 2025-3-26 11:15:50
http://reply.papertrans.cn/67/6602/660144/660144_28.png
Aspiration
发表于 2025-3-26 16:07:11
http://reply.papertrans.cn/67/6602/660144/660144_29.png
向外才掩饰
发表于 2025-3-26 16:57:05
http://reply.papertrans.cn/67/6602/660144/660144_30.png