We present a new family of models for unsupervised parsing, Dependency and Boundary models, that use cues at constituent boundaries to inform head-outward dependency tree generation. We build on three intuitions that are explicit in phrase-structure grammars but only implicit in standard dependency formulations: (i) Distributions of words that occur at sentence boundaries — such as English dete...

The aim of this paper is to provide an overview of the results of a study concerning the prosodic interpretation of punctuation. The focus is placed on the two most common punctuation marks, that is to say, full stops and commas. The findings are based on a comparison between The Stranger by Albert Camus the way it is published as a book and the way it is read out by its author in two French ra...

We explore character-level neural network models for inferring punctuation from text-only input. Punctuation inference is treated as a sequence tagging problem where the input is a sequence of un-punctuated characters, and the output is a corresponding sequence of punctuation tags. We experiment with six architectures, all of which use a long short-term memory (LSTM) network for sequence modeli...

This paper describes the systems of, and the experiments by, Microsoft Research Asia (MSRA), with the support of Microsoft Research (MSR), in the IWSLT 2010 evaluation campaign. We participated in all tracks of the DIALOG task (Chinese/English). While we follow the general training and decoding routine of statistical machine translation (SMT) and that of MT output combination, it is our first t...

Punctuation in a Lexicalized Grammar

This paper presents a proof-theoretical approach to the question "What is a logical constant?" This approach starts with the assumption that logic is the science of formal deductions, and that basic formal deductions are structural deductions, i.e. deductions independent of any constant of the language to which the premises and conclusions belong. Logical constants, on which the remaining forma...

Higher-level graphical and lexical punctuation (paragraphing, indentation, font changes, ...) must be taken into consideration in comprehension processes and text generation. In this paper, we analyse a class of text punctuation marks which includes lexical units (chapter, introduction). We give a method for the analysis of the semantics of these units, in terms of metalanguage. In addition, th...

In this paper we present a methodoly for the scoring of punctuation annotated texts, as well as a preliminary system to perform the task. We modify SCLITE’s scoring methodology to support scoring of punctuation. Using this methodology, we show that the error rate of an initial automatic system is comparable to annotator inconsistency. However, the use of multiple references allows us to differe...