Discourse over Discourse: The Need for an Expanded Pragmatic Focus in Conversational AI
Not on the map. Why?
Abstract (arXiv)
The summarization of conversation, that is, discourse over discourse, elevates pragmatic considerations as a pervasive limitation of both summarization and other applications of contemporary conversational AI. Building on impressive progress in both semantics and syntax, pragmatics concerns meaning in the practical sense. In this paper, we discuss several challenges in both summarization of conversations and other conversational AI applications, drawing on relevant theoretical work. We illustrate the importance of pragmatics with so-called star sentences, syntactically acceptable propositions that are pragmatically inappropriate in conversation or its summary. Because the baseline for quality of AI is indistinguishability from human behavior, we draw heavily on the psycho-linguistics literature, and label our complaints as "Turing Test Triggers" (TTTs). We discuss implications for the design and evaluation of conversation summarization methods and conversational AI applications like voice assistants and chatbots
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 88 references that are in the map. First posted on arXiv 27 Apr 2023.
Builds on
22 of 88 references.
References · 22
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
- 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
- 2019What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language modelscited by 317
- 2020Re-evaluating Evaluation in Text Summarizationcited by 144
- 2020MIME: MIMicking Emotions for Empathetic Response Generationcited by 114
- 2020Heterogeneous Graph Neural Networks for Extractive Document Summarizationcited by 90
- 2019Proactive Human-Machine Conversation with Explicit Conversation Goalscited by 87
- 2018Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Actscited by 44
10 more
- 2021Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causescited by 43
- 2021Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledgecited by 40
- 2021Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphscited by 36
- 2022Improving the Adversarial Robustness of NLP Models by Information Bottleneckcited by 17
- 2021Pragmatic competence of pre-trained language models through the lens of discourse connectivescited by 16
- 2020Pragmatic Issue-Sensitive Image Captioningcited by 15
- 2022Learning to Mediate Disparities Towards Pragmatic Communicationcited by 14
- 2021A recipe for annotating grounded clarificationscited by 13
- 2021Calibrate your listeners! Robust communication-based training for pragmatic speakerscited by 9
- 2021Deciding Whether to Ask Clarifying Questions in Large-Scale Spoken Language Understandingcited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.