【摘 要】
：
In this paper,we conduct a review headline generation task that produces a short headline from a review post by a user.We ar-gue that this task is more challenging than document summarization,because
【机 构】
：
National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beiji
【出 处】
：
第十七届全国计算语言学学术会议暨第六届基于自然标注大数据的自然语言处理国际学术研讨会(CCL 2018)
论文部分内容阅读
In this paper,we conduct a review headline generation task that produces a short headline from a review post by a user.We ar-gue that this task is more challenging than document summarization,because the headlines generated by users vary from person to person.It not only needs to effectively capture the preferences of the users who post the reviews,but also requires to mine the emphasis of the users regard-ing the review when they write the headlines.To this end,we propose to incorporate the user information as the prior knowledge into the en-coder and decoder for general sequence-to-sequence model.Specifically,we introduce user embedding for each user,and then we use these em-beddings to initialize the encoder and decoder,or as biases for decoder initialization.We construct a review headline generation dataset,and the experiments on this dataset demonstrate that our models significantly outperform baseline models which do not consider user information.
其他文献
In recent years,mining opinions from customer reviews has been widely explored.Aspect-level sentiment analysis is a fine-grained subtask,which aims to detect the sentiment polarity towards a partic-ul
Network Representation Learning(NRL)can learn a latent space rep-resentation of each vertex in a topology network structure to reflect linked in-formation.Recently,NRL algorithms have been applied to
Network representation learning(NRL)aims at building a low-dimensional vector for each vertex in a network,which is also increasingly recognized as an important aspect for network analysis.Some curren
This paper studies the methods to improve end-to-end neural coreference resolution.First,we introduce a coreference cluster modification algorithm,which can help modify the coreference cluster to rule
Type information is very important in knowledge bases,but some large knowledge bases are lack of type information due to the incompleteness of knowledge bases.In this paper,we propose to use a well-de
It is common to fine-tune pre-trained word embeddings in text categorization.However,we find that fine-tuning does not guarantee improvement across text categorization datasets,while could introduce c
Named entity recognition(NER)in Chinese electronic medical records(EMRs)has become an important task of clinical natural language processing(NLP).However,limited studies have been performed on the cli
Keyphrase extraction can provide effective ways of organiz-ing scientific documents.For this task,neural-based methods usually suffer from performance unstability due to data scarcity.In this paper,we
Recent studies have shown effectiveness in using neural networks for Chinese Word Segmentation(CWS).However,these models,constrained by the domain and size of the training corpus,do not work well in d
Automated essay scoring aims to score an essay automatically without any human assistance.Traditional methods heavily rely on manual feature engi-neering,making it expensive to extract the features.So