vasospasm 发表于 2025-3-25 04:45:40
Emotion Cause Extraction, A Challenging Task with Corpus Construction,otion category or emotion component of text. We focus on the emotion cause, a.k.a the reason or stimulant of an emotion. Since there is no open dataset available, the lack of annotated resources has limited the research in this area. Thus, we first built an annotated dataset for this task using SINAabysmal 发表于 2025-3-25 09:18:21
http://reply.papertrans.cn/87/8697/869641/869641_22.png阻止 发表于 2025-3-25 15:37:25
Individual Friends Recommendation Based on Random Walk with Restart in Social Networks,orks. In this paper, we design a novel friend recommendation method according to a new individual feature .. Intimacy degree reflects the degree of interaction between two users and further indicates how close two users pay attention to each other. Specifically, we first formally define this problemArroyo 发表于 2025-3-25 18:26:26
http://reply.papertrans.cn/87/8697/869641/869641_24.pngMumble 发表于 2025-3-25 20:41:02
Word Representation on Small Background Texts,arning applications. Word representations in previous works were often trained on large-scale unlabeled texts. However, in some scenarios, large scale background texts are not available. Therefore, in this paper, we propose a novel word representation model based on maximum-margin to train word reprmicronized 发表于 2025-3-26 02:05:32
Extracting Opinion Expression with Neural Attention,ackled by conditional random fields (CRFs). However CRF-based models usually need abundant hand-crafted features and require a lot of engineering effort. Recently deep neural networks are proposed to alleviate this problem. In order to extend neural-network-based models with ability to emphasize relFlirtatious 发表于 2025-3-26 06:34:01
Topic Model Based Adaptation Data Selection for Domain-Specific Machine Translation,vantage of Adaptation data selection (Ada-selection) for enriching the corpora. Encouraged by the empirical finding that topic distribution is conductive to characterizing a distinctive domain, we propose to use topic model to improve Ada-selection. Based on a joint LDA approach, we incorporate topi有危险 发表于 2025-3-26 12:24:22
Early Detection of Promotion Campaigns in Community Question Answering,n information. Previous works mainly focus on identifying low-quality answers or detecting spam information in question-answer (QA) pairs. However, these works suffer from long delay since they all rely on the information of answers or answerers while questions have been displayed on the websites foconspicuous 发表于 2025-3-26 13:28:27
http://reply.papertrans.cn/87/8697/869641/869641_29.png轻而薄 发表于 2025-3-26 20:17:42
,Discovering Region Features Based on User’s Comments,n-line discussion and interact within the network’s platform. By analyzing user comment from the same region, we can understand the implied region features and trending topics in that region. Region features can be categorized as an event or topic therefore it can be labeled based on the user’s comm