彩色
发表于 2025-3-23 09:57:28
Enhancing Document-Based Question Answering via Interaction Between Question Words and POS Tagstion. Experimental results on DBQA Task have shown that our model has achieved better results, compared with several state-of-the-art systems. In addition, it also achieves the best result on NLPCC 2017 Shared Task on DBQA.
Ballerina
发表于 2025-3-23 16:42:33
http://reply.papertrans.cn/67/6619/661815/661815_12.png
出汗
发表于 2025-3-23 19:43:32
Random Projections with Bayesian Priorsto a smaller subspace via random projections, and their relative similarity computed via distance metrics. We propose using marginal information and Bayesian probability to improve the estimates of the inner product between pairs of vectors, and demonstrate our results on actual datasets.
bronchodilator
发表于 2025-3-24 01:24:17
Augmenting Neural Sentence Summarization Through Extractive Summarization to achieve the fusion of the contents in different views, which can be easily adapted to other domains. Experimental results on CNN/Daily Mail dataset demonstrate both our proposed strategies can significantly improve the performance of neural sentence summarization.
表被动
发表于 2025-3-24 05:26:11
http://reply.papertrans.cn/67/6619/661815/661815_15.png
Blasphemy
发表于 2025-3-24 08:49:24
Geography Gaokao-Oriented Knowledge Acquisition for Comparative Sentences Based on Logic Programming programming is employed to filter out non-comparative sentences, and for the latter task, the information of dependency grammar and heuristic position is adopted to represent the relations among comparative elements. The experimental results show that our system achieves outstanding performance for practical use.
网络添麻烦
发表于 2025-3-24 12:00:55
http://reply.papertrans.cn/67/6619/661815/661815_17.png
暴露他抗议
发表于 2025-3-24 16:17:52
Cascaded LSTMs Based Deep Reinforcement Learning for Goal-Driven Dialoguee is no explicit NLU and dialogue states in the network. Experimental results show that our model outperforms both traditional Markov Decision Process (MDP) model and single LSTM with Deep Q-Network on meeting room booking tasks. Visualization of dialogue embeddings illustrates that the model can learn the representation of dialogue states.
CAPE
发表于 2025-3-24 20:21:59
0302-9743Processing, NLPCC 2017, held in Dalian, China, in November 2017.. The 47 full papers and 39 short papers presented were carefully reviewed and selected from 252 submissions. The papers are organized around the following topics: IR/search/bot; knowledge graph/IE/QA; machine learning; machine transl
聪明
发表于 2025-3-24 23:21:37
Conference proceedings 2018ina, in November 2017.. The 47 full papers and 39 short papers presented were carefully reviewed and selected from 252 submissions. The papers are organized around the following topics: IR/search/bot; knowledge graph/IE/QA; machine learning; machine translation; NLP applications; NLP fundamentals;