Document-level Sentiment Analysis is a complex task that implies the analysis of large textual content can incorporate multiple contradictory polarities at phrase and word levels. Most current approaches either represent data using pre-trained embeddings without considering local context be extracted from dataset, or they detect overall topic polarity both global context. In this paper, we prop...

This paper describes CMUIR’s participation in the NTCIR13 We Want Web (WWW) task. In the context of the Chinese subtask, we experimented with a neural network approach using the kernel based neural ranking model (KNRM). The model learns a word embedding that encodes IRcustomized soft match patterns from a Chinese search log. The learned model is then directly applied to re-rank the baseline run...

Paragraph Vectors has been recently proposed as an unsupervised method for learning distributed representations for pieces of texts. In their work, the authors showed that the method can learn an embedding of movie review texts which can be leveraged for sentiment analysis. That proof of concept, while encouraging, was rather narrow. Here we consider tasks other than sentiment analysis, provide...

Sentiment lexicon is an important tool for identifying the sentiment polarity of words and texts. How to automatically construct sentiment lexicons has become a research topic in the field of sentiment analysis and opinion mining. Recently there were some attempts to employ representation learning algorithms to construct a sentiment lexicon with sentiment-aware word embedding. However, these me...

The selection of an embedding scheme is an important step in the modeling and prediction of chaotic dynamical systems. Theoretical work in embedding selection abounds in the literature. However in neural network research, mostly compute intensive methods for embedding selection exist. In this paper, we propose a novel embedding selection scheme based on cluster analysis. A neural network implem...

Abstract Ranking models are the main components of information retrieval systems. Several approaches to ranking based on traditional machine learning algorithms using a set hand-crafted features. Recently, researchers have leveraged deep in retrieval. These trained end-to-end extract features from raw data for tasks, so that they overcome limitations A variety been proposed, and each model pres...

This paper tackles the problem of the semantic gap between a document and a query within an ad-hoc information retrieval task. In this context, knowledge bases (KBs) have already been acknowledged as valuable means since they allow the representation of explicit relations between entities. However, they do not necessarily represent implicit relations that could be hidden in a corpora. This latt...