Multi-modal person Re-ID introduces more complementary information to assist the traditional task. Existing multi-modal methods ignore importance of modality-specific in feature fusion stage. To this end, we propose a novel method boost representations for Re-ID: Interact, Embed, and EnlargE (IEEE). First, cross-modal interacting module exchange useful between different modalities extraction ph...

Quantification over individuals, times, and worlds can in principle be made explicit in the syntax of the object language, or left to the semantics and spelled out in the metalanguage. The traditional view is that quantification over individuals is syntactically explicit, whereas quantification over times and worlds is not. But a growing body of literature proposes a uniform treatment. This pap...

Protein-protein interaction plays an important role in understanding biological processes. In order to resolve the parsing error resulted from modal verb phrases and the noise interference brought by appositive dependency, an improved tree kernel-based PPI extraction method is proposed in this paper. Both modal verbs and appositive dependency features are considered to define some relevant proc...

In this paper, we describe our participating system, which is based on supervised approaches and dependency parsing, for opinion analysis on traditional Chinese texts at NTCIR-8. For opinionated sentence recognition, the supervised lexicon-based approach, SVM and Maximum Entropy are combined together. For polarity classification, we use only the supervised lexicon-based approach. For opinion ho...

The variable behavior of verbs has always been a fundamental issue for theories of the lexicon/syntax interface. The constructionalist approaches to this problem of the past decade or so have been very successful in accounting for a diverse range of alternations, largely because these approaches have formalized the influence of event structure on argument projection. The theoretical apparatus o...

Athapaskan languages comprise one of the largest, most geographically distributed, and most culturally diverse families in North America. Nevertheless, each daughter language features a set of classificatory verb stems which, semantically, focus less on signaling a relational predication than on some physical attribute of a prominent relational participant. Consequently, most consumption expres...

In this article we are going to trace the transition of modal verbs into epistemic adverbs. This development found in nearly all European languages will be analysed on the basis of Russian možet (byt’) which goes back to the third person singular present tense of the modal verb moč’ plus infinitive. In our study we shall focus on the constructional aspects of this language change with the aim t...

In this study, we provide evidence for a cross-modal interaction between the meaning of pantomimes and words when the visuo-spatial and perceptual information of these last is enhanced. We recorded behavioral and electrophysiological responses with a cross-modal repetition priming. Pantomimes of objects and actions were used to prime visually presented nouns and verbs with an image formation ta...

This paper examines the question of differences between a traditional interlingua approach and a transferbased approach that uses cross-linguistic semantic features to generalize its transfer lexicon entries, and concludes that the two approaches share a common interest in lexical classifications that can be distinguished by cross-linguistic semantic features. The paper goes on to discuss curre...