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 published on a yearly basis
Papers
More filters
•
15 Jul 2010TL;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
••
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
••
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
••
08 Oct 2016TL;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
••
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