Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics Proceedings of the Doctoral Consortium
نویسندگان
چکیده
Structural information in language is important for obtaining a better understanding of a human communication (e.g., sentence segmentation, speaker turns, and topic segmentation). Human communication involves a variety of multimodal behaviors that signal both propositional content and structure, e.g., gesture, gaze, and body posture. These non-verbal signals have tight temporal and semantic links to spoken content. In my thesis, I am working on incorporating non-verbal cues into a multimodal model to better predict the structural events to further improve the understanding of human communication. Some research results are summarized in this document and my future research plan is described.
منابع مشابه
NAACL HLT 2009 Human Language Technologies : The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
متن کامل
Linguistic Characteristics of Nouns Representing the Concept of “Power” in American Political Discourse
The article analyzes the linguistic nature of some nuclear lexemes (power, control, authority, influence) verbalizing the basic concept of the English-language political discourse – the concept of “Power”. The paper reveals the structure of the concept, its conceptual features, as well as the main characteristics of the concept representatives at the language and functional levels.
متن کاملCreating Local Coherence: An Empirical Assessment
Two of the mechanisms for creating natural transitions between adjacent sentences in a text, resulting in local coherence, involve discourse relations and switches of focus of attention between discourse entities. These two aspects of local coherence have been traditionally discussed and studied separately. But some empirical studies have given strong evidence for the necessity of understanding...
متن کاملHuman Language Technology Conference of the North American Chapter of the Association of Computational Linguistics Short Papers
We present a new type of neural probabilistic language model that learns a mapping from both words and explicit word features into a continuous space that is then used for word prediction. Additionally, we investigate several ways of deriving continuous word representations for unknown words from those of known words. The resulting model significantly reduces perplexity on sparse-data tasks whe...
متن کاملThe Visual Transitivity System in Two ELT Books Series
The present study aims to investigate the system of the visual transitivity by analyzing the images of American English file (2014) and Cutting edge (2005) series based on Halliday’s (1976) systemic functional linguistics and Kress and van leuween’s (1997-2006) social semiotics. The system of visual transitivity refers to a type of process which determines how represented participants are label...
متن کامل