We develop a Ranking framework upon Recursive Neural Networks (R2N2) to rank sentences for multi-document summarization. It formulates the sentence ranking task as a hierarchical regression process, which simultaneously measures the salience of a sentence and its constituents (e.g., phrases) in the parsing tree. This enables us to draw on word-level to sentence-level supervisions derived from r...

This paper proposes an algorithm to improve the calculation of confidence measure for spoken term detection (STD). Given an input query term, the algorithm first calculates a measurement named document ranking weight for each document in the speech database to reflect its relevance with the query term by summing all the confidence measures of the hypothesized term occurrences in this document. ...

Keyphrases are widely used as a brief summary of documents. Since manual assignment is time-consuming, various unsupervised ranking methods based on importance scores are proposed for keyphrase extraction. In practice, the keyphrases of a document should not only be statistically important in the document, but also have a good coverage of the document. Based on this observation, we propose an u...

Although a word-based method is commonly used in document retrieval, it cannot be directly applicable to languages that have no obvious word separator. Given a lexicon, it is possible to identify words in documents, but a large lexicon is troublesome to maintain and makes retrieval systems large and complicated. This paper proposes an effective and efficient ranking that does not use a large le...

Text retrieval systems store a great variety of documents, from abstracts, newspaper articles, and web pages to journal articles, books, court transcripts, and legislation. Collections of diverse types of documents expose shortcomings in current approaches to ranking. Use of short fragments of documents, called passages, instead of whole documents can overcome these shortcomings: passage rankin...

Many machine learning technologies such as support vector machines, boosting, and neural networks have been applied to the ranking problem in information retrieval. However, since originally the methods were not developed for this task, their loss functions do not directly link to the criteria used in the evaluation of ranking. Specifically, the loss functions are defined on the level of docume...

Many machine learning technologies such as Support Vector Machines, Boosting, and Neural Networks have been applied to the ranking problem in information retrieval. However, since originally the methods were not developed for this task, their loss functions do not directly link to the criteria used in the evaluation of ranking. Specifically, the loss functions are defined on the level of docume...

Global ranking, a new information retrieval (IR) technology, uses a ranking model for cases in which there exist relationships between the objects to be ranked. In the ranking task, the ranking model is defined as a function of the properties of the objects as well as the relations between the objects. Existing global ranking approaches address the problem by “learning to rank”. In this paper, ...