Phrase

About: Phrase is a research topic. Over the lifetime, 12580 publications have been published within this topic receiving 317823 citations. The topic is also known as: syntagma & phrases.

Detecting potential significant errors in speech recognition results

Abstract: In some embodiments, the recognition results produced by a speech processing system (which may include two or more recognition results, including a top recognition result and one or more alternative recognition results) based on an analysis of a speech input, are evaluated for indications of potential significant errors. In some embodiments, the recognition results may be evaluated to determine whether a meaning of any of the alternative recognition results differs from a meaning of the top recognition result in a manner that is significant for a domain, such as the medical domain. In some embodiments, words and/or phrases that may be confused by an ASR system may be determined and associated in sets of words and/or phrases. Words and/or phrases that may be determined include those that change a meaning of a phrase or sentence when included in the phrase/sentence.

Compact encoding of multi-lingual translation dictionaries

Abstract: A computerized multilingual translation dictionary includes a set of word and phrases for each of the languages it contains, plus a mapping that indicates for each word or phrase in one language what the corresponding translations in the other languages are. The set of words and phrases for each language are divided up among corresponding concept groups based on an abstract pivot language. The words and phrases are encoded as token numbers assigned by a word-number mapper laid out in sequence that can be searched fairly rapidly with a simple linear scan. The complex associations of words and phrases to particular pivot language senses are represented by including a list of pivot-language sense numbers with each word or phrase. The preferred coding of these sense numbers is by means of a bit vector for each word, where each bit corresponds to a particular pivot element in the abstract language, and the bit is ON if the given word is a translation of that pivot element. Then, to determine whether a word in language 1 translates to a word in language 2 only requires a bit-wise intersection of their associated bit-vectors. Each word or phrase is prefixed by its bit-vector token number, so the bit-vector tokens do double duty: they also act as separators between the tokens of one phrase and those of another. A pseudo-Huffman compression scheme is used to reduce the size of the token stream. Because of the frequency skew for the bit-vector tokens, this produces a very compact encoding.

A Joint Sequence Translation Model with Integrated Reordering

Abstract: We present a novel machine translation model which models translation by a linear sequence of operations. In contrast to the "N-gram" model, this sequence includes not only translation but also reordering operations. Key ideas of our model are (i) a new reordering approach which better restricts the position to which a word or phrase can be moved, and is able to handle short and long distance re-orderings in a unified way, and (ii) a joint sequence model for the translation and reordering probabilities which is more flexible than standard phrase-based MT. We observe statistically significant improvements in BLEU over Moses for German-to-English and Spanish-to-English tasks, and comparable results for a French-to-English task.

Automatic Generation of Story Highlights

Abstract: In this paper we present a joint content selection and compression model for single-document summarization. The model operates over a phrase-based representation of the source document which we obtain by merging information from PCFG parse trees and dependency graphs. Using an integer linear programming formulation, the model learns to select and combine phrases subject to length, coverage and grammar constraints. We evaluate the approach on the task of generating "story highlights"---a small number of brief, self-contained sentences that allow readers to quickly gather information on news stories. Experimental results show that the model's output is comparable to human-written highlights in terms of both grammaticality and content.

On the flexibility of grammatical advance planning during sentence production: Effects of cognitive load on multiple lexical access

Abstract: Three picture-word interference experiments addressed the question of whether the scope of grammatical advance planning in sentence production corresponds to some fixed unit or rather is flexible. Subjects produced sentences of different formats under varying amounts of cognitive load. When speakers described 2-object displays with simple sentences of the form "the frog is next to the mug," the 2 nouns were found to be lexically-semantically activated to similar degrees at speech onset, as indexed by similarly sized interference effects from semantic distractors related to either the first or the second noun. When speakers used more complex sentences (including prenominal color adjectives; e.g., "the blue frog is next to the blue mug") much larger interference effects were observed for the first than the second noun, suggesting that the second noun was lexically-semantically activated before speech onset on only a subset of trials. With increased cognitive load, introduced by an additional conceptual decision task and variable utterance formats, the interference effect for the first noun was increased and the interference effect for second noun disappeared, suggesting that the scope of advance planning had been narrowed. By contrast, if cognitive load was induced by a secondary working memory task to be performed during speech planning, the interference effect for both nouns was increased, suggesting that the scope of advance planning had not been affected. In all, the data suggest that the scope of advance planning during grammatical encoding in sentence production is flexible, rather than structurally fixed.