Individuality and Alignment in Generated Dialogues
نویسندگان
چکیده
It would be useful to enable dialogue agents to project, through linguistic means, their individuality or personality. Equally, each member of a pair of agents ought to adjust its language (to a greater or lesser extent) to match that of its interlocutor. We describe CRAG, which generates dialogues between pairs of agents, who are linguistically distinguishable, but able to align. CRAG-2 makes use of OPENCCG and an over-generation and ranking approach, guided by a set of language models covering both personality and alignment. We illustrate with examples of output, and briefly note results from user studies with the earlier CRAG-1, indicating how CRAG-2 will be further evaluated. Related work is discussed, along with current limitations and future directions.
منابع مشابه
Perceptions of Alignment and Personality in Generated Dialogue
Variation in language style can lead to different perceptions of the interaction, and different behaviour outcomes. Using the CRAG 2 language generation system we examine how accurately judges can perceive character personality from short, automatically generated dialogues, and how alignment (similarity between speakers) alters judge perceptions of the characters’ relationship. Whilst personali...
متن کاملAutomatic Measures to Characterise Verbal Alignment in Human-Agent Interaction
This work aims at characterising verbal alignment processes for improving virtual agent communicative capabilities. We propose computationally inexpensive measures of verbal alignment based on expression repetition in dyadic textual dialogues. Using these measures, we present a contrastive study between Human-Human and Human-Agent dialogues on a negotiation task. We exhibit quantitative differe...
متن کاملConcern-Alignment for Negotiation and Joint Inquiry in Dialogues
‘Concern Alignment in Conversations’ project aims, through empirical examinations of real-life conversations, to establish a theoretical and descriptive framework to capture discourse structures and underlying rational and affective processes in human-human joint planning interactions at dialogue act exchange level. Concern alignment model has been developed to address convergent negotiation fo...
متن کاملPoliteness and alignment in dialogues with a virtual guide
Language alignment is something that happens automatically in dialogues between human speakers. The ability to align is expected to increase the believability of virtual dialogue agents. In this paper we extend the notion of alignment to affective language use, describing a model for dynamically adapting the linguistic style of a virtual agent to the level of politeness and formality detected i...
متن کاملIndividuality in Higher Education: The Use of the Multiple-Mnemonic Method to Enhance ESP Students' Vocabulary Development (Depth and Size) and Retention
Vocabulary learning is considered to be the most comprehensive and the most difficult part of language learning for all the students especially for ESP students. These students complain that vocabulary items are too many and are easily forgotten after they are learned. Mnemonic devices, a group of mental strategies, are developed to facilitate vocabulary learning and retention for such students...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006