In informal terms, a vocative identifies to whom the sentence’s content is addressed, a topic informs the addressee what it’s about, and a force marker says how the speaker wishes to use it to update the conversational context. I include all of these functions under the broad label “instructions for interpretation”, and in this paper I will pursue the idea that they should be studied within a s...

comparing literary views of the poets and writers, as the creators of literary texts and those of the critics has rarely been noticed in the area of literary criticism. this article, studies attar’s point of views on various issues of poetry including rhyme, rhythm, poetic inspiration, addressee, utterance, meaning and didactic poem. the author of the article studies four masnavis of attar –ela...

Based on the Theory of Communicative Action developed by Jürgen Habermas we propose to analyse the actions of participants in a dialogue in terms of dialogue act offers that raise validity claims to be evaluated by the addressee of a move. We argue that this approach allows us to model disputes and misunderstandings in conversations in a way that minimises revisions of discourse structure and r...

This paper presents experiments into the resolution of “you” in multi-party dialog, dividing this process into two tasks: distinguishing between generic and referential uses; and then, for referential uses, identifying the referred-to addressee(s). On the first task we achieve an accuracy of 75% on multi-party data. We achieve an accuracy of 47% on determining the actual identity of the referen...

Prior approaches to politeness modulation in natural language generation (NLG) often focus on manipulating factors such as the directness of requests that pertain to preserving the autonomy of the addressee (negative face threats), but do not have a systematic way of understanding potential impoliteness from inadvertently critical or blame-oriented communications (positive face threats). In thi...

We present persona-based models for handling the issue of speaker consistency in neural response generation. A speaker model encodes personas in distributed embeddings that capture individual characteristics such as background information and speaking style. A dyadic speaker-addressee model captures properties of interactions between two interlocutors. Our models yield qualitative performance i...