We propose a method for extracting semantic orientations of words: desirable or undesirable. Regarding semantic orientations as spins of electrons, we use the mean field approximation to compute the approximate probability function of the system instead of the intractable actual probability function. We also propose a criterion for parameter selection on the basis of magnetization. Given only a small number of seed words, the proposed method extracts semantic orientations with high accuracy in the experiments on English lexicon. The result is comparable to the best value ever reported.

Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. This capability is crucial for applications such as text summarization, in which we have to generate concise summaries with a desired length. In this paper, we propose methods for controlling the output sequence length for neural encoder-decoder models: two decoding-based methods and two learning-based methods.1 Results show that our learning-based methods have the capability to control length without degrading summary quality in a summarization task.

No abstract

We discuss text summarization in terms of maximum coverage problem and its variant. We explore some decoding algorithms including the ones never used in this summarization formulation, such as a greedy algorithm with performance guarantee, a randomized algorithm, and a branch-andbound method. On the basis of the results of comparative experiments, we also augment the summarization model so that it takes into account the relevance to the document cluster. Through experiments, we showed that the augmented model is superior to the best-performing method of DUC'04 on ROUGE-1 without stopwords.

keywords: text summarization, decoding algorithm, approximate algorithm, integer programming, maximum coverage problem SummaryWe discuss text summarization in terms of maximum coverage problem and its variant. To solve the optimization problem, we applied some decoding algorithms including the ones never used in this summarization formulation, such as a greedy algorithm with performance guarantee, a randomized algorithm, and a branch-and-bound method. We conduct comparative experiments. On the basis of the experimental results, we also augment the summarization model so that it takes into account the relevance to the document cluster. Through experiments, we showed that the augmented model is at least comparable to the best-performing method of DUC'04.