Events described in textual narratives do not always occur in neat, chronological order but occur, for example, during or overlapping each other or as simultaneous events. Summarizations of narratives, however, benefit from a simpler, linear ordering of events. This paper describes an approach for modeling events in text as event intervals and for generating linear orders of event intervals, us...

This paper describes a method for linear text segmentation which is twice as accurate and over seven times as fast as the state-of-the-art (Reynar, 1998). Inter-sentence similarity is replaced by rank in the local context. Boundary locations are discovered by divisive clustering.

Low dimensional representations of words allow accurate NLP models to be trained on limited annotated data. While most representations ignore words’ local context, a natural way to induce context-dependent representations is to perform inference in a probabilistic latent-variable sequence model. Given the recent success of continuous vector space word representations, we provide such an inferen...

Previous work on paraphrase extraction and application has relied on either parallel datasets, or on distributional similarity metrics over large text corpora. Our approach combines these two orthogonal sources of information and directly integrates them into our paraphrasing system’s log-linear model. We compare different distributional similarity feature-sets and show significant improvements...

This paper describes a joint model of word segmentation and phonological alternations, which takes unsegmented utterances as input and infers word segmentations and underlying phonological representations. The model is a Maximum Entropy or log-linear model, which can express a probabilistic version of Optimality Theory (OT; Prince and Smolensky (2004)), a standard phonological framework. The fe...

We present an approach for automatically learning to solve algebra word problems. Our algorithm reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers in these equations to the problem text. The learning algorithm uses varied supervision, including either full equations or just the final a...

In this paper, we study the complete convergence and complete moment convergence for weighted sums of extended negatively dependent (END) random variables under sub-linear expectations space with the condition of [Formula: see text], further [Formula: see text], [Formula: see text] ([Formula: see text] is a slow varying and monotone nondecreasing function). As an application, the Baum-Katz type...

A text is a word together with an (additional) linear ordering. Each text has a generic tree representation, called its shape. We consider texts in a logical and an algebraic framework, and we prove that the classes of monadic second order deenable and of recognizable text languages coincide. In particular we demonstrate that the construction of the shape of a text can be formalized in terms of...