AutoEmbedder: A semi-supervised DNN embedding system for clustering
نویسندگان
چکیده
منابع مشابه
Semi-Supervised DNN Training with Word Selection for ASR
Not all the questions related to the semi-supervised training of hybrid ASR system with DNN acoustic model were already deeply investigated. In this paper, we focus on the question of the granularity of confidences (per-sentence, per-word, perframe), the question of how the data should be used (dataselection by masks, or in mini-batch SGD with confidences as weights). Then, we propose to re-tun...
متن کاملSemi supervised clustering for Text Clustering
ABSTRACT: Based on clustering algorithm Affinity Propagation (AP) I present this paper a semisupervised text clustering algorithm, called Seeds Affinity Propagation (SAP). There are two main contributions in my approach: 1) a similarity metric that captures the structural information of texts, and 2) seed construction method to improve the semisupervised clustering process. To study the perform...
متن کاملCompound Embedding Features for Semi-supervised Learning
There has been a recent trend in discriminative methods of NLP to use representations of lexical items learned from unlabeled data as features, in order to overcome the problem of data sparsity. In this paper, we investigated the usage of word representations learned by neural language models, i.e. word embeddings. We built compound features of continuous word embeddings based on clustering to ...
متن کاملSemi-supervised Clustering
Clustering is an unsupervised learning problem whose objective is to find a partition of the given data. However, a major challenge in clustering is to define an appropriate objective function in order to to find an optimal partition that is useful to the user. To facilitate data clustering, it has been suggested that the user provide some supplementary information about the data (eg. pairwise ...
متن کاملSemi-Supervised Projected Clustering
Recent studies suggest that projected clusters with extremely low dimensionality exist in many real datasets. A number of projected clustering algorithms have been proposed in the past several years, but few can identify clusters with dimensionality lower than 10% of the total number of dimensions, which are commonly found in some real datasets such as gene expression profiles. In this paper we...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Knowledge-Based Systems
سال: 2020
ISSN: 0950-7051
DOI: 10.1016/j.knosys.2020.106190