scispace - formally typeset
Search or ask a question
Topic

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.


Papers
More filters
Proceedings Article
15 Jul 2010
TL;DR: A novel reordering model for the hierarchical phrase-based approach is introduced which further enhances translation performance, and the effect some recent extended lexicon models have on the performance of the system is analyzed.
Abstract: We present Jane, RWTH's hierarchical phrase-based translation system, which has been open sourced for the scientific community. This system has been in development at RWTH for the last two years and has been successfully applied in different machine translation evaluations. It includes extensions to the hierarchical approach developed by RWTH as well as other research institutions. In this paper we give an overview of its main features. We also introduce a novel reordering model for the hierarchical phrase-based approach which further enhances translation performance, and analyze the effect some recent extended lexicon models have on the performance of the system.

98 citations

Journal ArticleDOI
TL;DR: The data support models of sentence parsing that postulate that the parsing of a sentence is based upon structurally based principles and the influence of semantic or pragmatic information makes itself felt only after the initial parsing decision has been made.

98 citations

Journal ArticleDOI
TL;DR: In two experiments, participants were presented with narrative texts including negation sentences that either introduced or referred to entities, and that either described a situation in which only the nonnegated or only the negated entity was present.
Abstract: Prior experiments have shown that sentences such as (1) Mary bakes bread but no cookies lead to a reduced accessibility of the concept mentioned in the negated phrase, whereas sentences such as (2) Elizabeth burns the letters but not the photographs do not. In the present article, two explanations for this result are investigated. According to situation model theory (Johnson-Laird, 1983; van Dijk & Kintsch, 1983), the reason is that the entity mentioned within the negated phrase in (2) is not absent from the described situation. According to discourse representation theory (Kamp, 1981), in contrast, the negation operator in (2) does not reduce the accessibility of the negated concept, because the corresponding discourse referent is not introduced but merely referred to within the operator's scope. In two experiments, participants were presented with narrative texts including negation sentences that either introduced or referred to entities, and that either described a situation in which only the nonnegated or only the negated entity was present. The accessibility of the relevant concepts was measured by means of a probe recognition task. The results support the situation models explanation.

98 citations

Book ChapterDOI
Mingzhe Wang1, Mahmoud Azab1, Noriyuki Kojima1, Rada Mihalcea1, Jia Deng1 
08 Oct 2016
TL;DR: A structured matching of phrases and regions that encourages the semantic relations between phrases to agree with the visual relations between regions that is formulated as a discrete optimization problem and relaxed to a linear program.
Abstract: In this paper we introduce a new approach to phrase localization: grounding phrases in sentences to image regions. We propose a structured matching of phrases and regions that encourages the semantic relations between phrases to agree with the visual relations between regions. We formulate structured matching as a discrete optimization problem and relax it to a linear program. We use neural networks to embed regions and phrases into vectors, which then define the similarities (matching weights) between regions and phrases. We integrate structured matching with neural networks to enable end-to-end training. Experiments on Flickr30K Entities demonstrate the empirical effectiveness of our approach.

98 citations

Journal ArticleDOI
TL;DR: The data illustrates the crucial involvement of the left BA 45 in syntactic encoding and is in line with more recent imaging and brain lesion data on syntax processing on a sentence level, emphasizing the involvement of a distributed left and right hemispheric network in syntax generation.

97 citations


Network Information
Related Topics (5)
Sentence
41.2K papers, 929.6K citations
92% related
Vocabulary
44.6K papers, 941.5K citations
88% related
Natural language
31.1K papers, 806.8K citations
84% related
Grammar
33.8K papers, 767.6K citations
83% related
Perception
27.6K papers, 937.2K citations
79% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023467
20221,079
2021360
2020470
2019525
2018535