Abstractive text summarization is a blossoming area of natural language processing research in which short textual summaries are generated from longer input documents. Existing state-of-the-art methods take long time to train, and are limited to functioning on relatively short input sequences. We evaluate neural network architectures with simplified encoder stages, which naturally support arbit...

Document clustering for short texts has received considerable interest. Traditional document clustering approaches are designed for long documents and perform poorly for short texts due to the their sparseness representation. To better understand short texts, we observe that words that appear in long documents can enrich short text context and improve the clustering performance for short texts....

0

We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text. These encoders are connected to a single decoder, trained end-to-end usi...

The new AT&T Text-To-Speech (TTS) system for general U.S. English text is based on best-choice components of the AT&T Flextalk TTS, the Festival System from the University of Edinburgh, and ATR’s CHATR system. From Flextalk, it employs text normalization, letter-to-sound, and prosody generation. Festival provides a flexible and modular architecture for easy experimentation and competitive evalu...

The growing number of web services puts forward higher requirements for searching desired web services, and clustering web services can greatly enhance the discovery of web service. Most existing clustering approaches are designed to handle long text documents. However, the descriptions of most services are in the form of short text, which impairs the quality of clustering owing to the lack of ...

In this paper, we consider the approximate string matching problem. We give a method to eliminate candidate locations in text T as there can be no substring S starting from those locations such that the edit distance between S and pattern P is smaller than or equal to a specified error bound k . Our method is simple to implement. Experimental results show that our method is effective, especiall...