Titlebook: Natural Language Processing and Chinese Computing; 7th CCF Internationa Min Zhang,Vincent Ng,Hongying Zan Conference proceedings 2018 Sprin

conjunctiva

outset

Response Selection of Multi-turn Conversation with Deep Neural Networksce, and ensemble of two models makes good improvement. The official results show that our solution takes 2nd place. We open the source of our code on GitHub, so that other researchers can reproduce easily.

Robust

刀鋒

激怒某人

Conference proceedings 2018inese Computing, NLPCC 2018, held in Hohhot, China, in August 2018.. ..The 55 full papers and 31 short papers presented were carefully reviewed and selected from 308 submissions. The papers of the first volume are organized in the following topics: conversational Bot/QA/IR; knowledge graph/IE; machi

尊嚴

0302-9743 ing and Chinese Computing, NLPCC 2018, held in Hohhot, China, in August 2018.. ..The 55 full papers and 31 short papers presented were carefully reviewed and selected from 308 submissions. The papers of the first volume are organized in the following topics: conversational Bot/QA/IR; knowledge graph

紳士

Learning to Converse Emotionally Like Humans: A Conditional Variational Approach emotion category for the response. We propose a new neural conversation model which is able to produce reasonable emotion interaction and generate emotional expressions. Experiments show that our proposed approaches can generate appropriate emotion and yield significant improvements over the baseline methods in emotional conversation.

Absenteeism

Parallel

Effective Character-Augmented Word Embedding for Machine Reading Comprehensionrepresentation to augment word embedding with a short list to improve word representations, especially for rare words. Experimental results show that the proposed approach helps the baseline model significantly outperform state-of-the-art baselines on various public benchmarks.

HUSH

A Neural Question Generation System Based on Knowledge Basee design a new format of input sequence for the system, which promotes the performance of the model. On the evaluation of KBQG of NLPCC 2018 Shared Task 7, our system achieved 73.73 BLEU, and took the first place in the evaluation.