Using Language Groundings for Context-Sensitive Text Prediction
نویسندگان
چکیده
In this paper, we present the concept of using language groundings for contextsensitive text prediction using a semantically informed, context-aware language model. We show initial findings from a preliminary study investigating how users react to a communication interface driven by context-based prediction using a simple language model. We suggest that the results support further exploration using a more informed semantic model and more realistic context. Keywords— Grounded language, context sensitive generation, predictive text
منابع مشابه
Learning Unknown Groundings for Natural Language Interaction with Mobile Robots
Our goal is to enable robots to understand or “ground” natural language instructions in the context of its perceived workspace. Contemporary models learn a probabilistic correspondence between input phrases and semantic concepts (or groundings) such as objects, regions or goals for robot motion derived from the robot’s world model. Crucially, these models assume a fixed and a priori known set o...
متن کاملTemporal Grounding Graphs for Language Understanding with Accrued Visual-Linguistic Context
A robot’s ability to understand or ground natural language instructions is fundamentally tied to its knowledge about the surrounding world. We present an approach to grounding natural language utterances in the context of factual information gathered through natural-language interactions and past visual observations. A probabilistic model estimates, from a natural language utterance, the object...
متن کاملTurning Quantitative: An Analytic Scale to Do Critical Discourse Analysis
Critical Discourse Analysis (CDA) could be seen as a theory in qualitative more than in qualitative stud- ies. This might have led to difficulty in doing CDA. Accordingly, this study attempted to develop a quan- titative profile in the form of an analytic rubric. For this purpose, Fairclough’s model of CDA was select- ed as the research framework. The techniques used for structuring analy...
متن کاملPrediction of user's trustworthiness in web-based social networks via text mining
In Social networks, users need a proper estimation of trust in others to be able to initialize reliable relationships. Some trust evaluation mechanisms have been offered, which use direct ratings to calculate or propagate trust values. However, in some web-based social networks where users only have binary relationships, there is no direct rating available. Therefore, a new method is required t...
متن کاملConcept-to-speech generation by integrating syntagmatic features into HMM-based speech synthesis
In conventional concept-to-speech (CTS) methods, a common step is predicting abstract prosodic descriptions, such as the locations of accents and phrase boundaries, from the linguistic information provided by the text generation module. But the prediction results always contain errors, and unacceptable prosodic prediction may ruin the synthesized speech. In addition, linguistic information, whi...
متن کامل