Automatic Measures to Characterise Verbal Alignment in Human-Agent Interaction

Abstract

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 differences in the strength and orientation of verbal alignment showing the ability of our approach to characterise important aspects of verbal alignment.

Does Ability Affect Alignment in Second Language Tutorial Dialogue?

“…It is also important to separate the effects of priming per se from other factors that can influence lexical convergence, such as differences in vocabulary and topic specificity. As a first step toward that goal, we plan to compare lexical convergence in the original corpus with convergence in matched baselines of randomly ordered utterances (Duplessis et al, 2017), which will account for vocabulary effects and corpus-specific factors. To explore more measures of word complexity in addition to simple WOF, we will further investigate measures specific to L2 dialogue, such as the English Vocabulary Profile (EVP) (Capel, 2012), with word lists per CEFR 10 level, or measures such as counts of word sense per word, or whether a word is concrete or abstract 11 , exploiting existing readability features (Vajjala and Meurers, 2014).…”

“…By also making comparisons across L2 ability levels, we can now analyse priming effects in terms of L2 acquisition. Similar work in this area outside the scope of this paper includes work analysing alignment of expressions in a task-based dialogue setting (Duplessis et al, 2017) and the analysis of alignment-capable dialogue generation (Buschmeier et al, 2009). In addition to informing dialogue tutoring agent design, this work has potential to augment existing measures of linguistic sophistication predic-1 Also know as Dialogue-based Computer Assisted Language Learning (CALL) 2 bots.duolingo.com tion (Vajjala and Meurers, 2016) to better deal with individual speakers within a dialogue, using alignment as a predictor of learner ability as has been suggested by Ward and Litman (2007a).…”

Towards alignment strategies in human-agent interactions based on measures of lexical repetitions

“…The automatic extraction of shared expressions and self-repetitions from a dialogue is an instance of sequential pattern mining [44] applied to textual dialogues. In this work, we follow a similar approach to [22,23] by employing a generalised suffix tree in order to solve the multiple common subsequences problem [33] to extract frequent surface text patterns between utterances. Notably, this problem is solved in linear time with respect to the number of tokens in a dialogue [33].…”

“…Verbal alignment is here considered through its lexical materialization, both at the intra and inter speaker levels. In a previous work [23], we provided a first set of measures for interspeaker alignment. The present paper is an extension of the proposed model, providing: i) improved measures of other-repetitions that better integrate complexity of the built shared lexicons; ii) the quantification of a new communicative behaviour-self-repetitions; iii) the extension of the study of lexical alignment process to a new H-A corpus-HAI Alice Corpus [62].…”

A Methodology for Evaluating Interaction Strategies of Task-Oriented Conversational Agents

“…The agent will start using the user's frequent expressions in order to align its lexicon. For example, it should align its linguistic register or reuse the same words used by the user in the generation of the following turn (Branigan et al, 2010;Duplessis et al, 2017).…”