Standards, literature, and open problems
Standards and literature
AWAI's analysis of the functions, connections, and context of thoughts is based on the international standards and peer-reviewed papers below. Each topic page explains how we interpreted and applied them.
International standards
- ISO 24617-2:2020. Language resource management — Semantic annotation framework (SemAF) — Part 2: Dialogue acts. www.iso.org/standard/76443.htmlChecked against the ISO/DIS 24617-2 text published by its authors (2019; the version approved in the international ballot of February 2020): dit.uvt.nlCited on: Functions / Connections
- ISO 24617-8:2016. Language resource management — Semantic annotation framework (SemAF) — Part 8: Semantic relations in discourse, core annotation schema (DR-core). www.iso.org/standard/60780.htmlCited on: Connections
Dialogue acts and discourse relations
- Bunt, H. (2006). Dimensions in Dialogue Act Annotation. Proceedings of LREC 2006, Genoa, pp. 919–924.Cited on: Functions
- Bunt, H. (2009). The DIT++ taxonomy for functional dialogue markup. Proceedings of the AAMAS 2009 Workshop EDAML, Budapest, pp. 13–24.Cited on: Functions
- Petukhova, V. and Bunt, H. (2009). The independence of dimensions in multidimensional dialogue act annotation. Proceedings of NAACL-HLT 2009, Short Papers, pp. 197–200. aclanthology.org/N09-2050Cited on: Functions
- Bunt, H., Petukhova, V., Gilmartin, E., Pelachaud, C., Fang, A., Keizer, S. and Prévot, L. (2020). The ISO Standard for Dialogue Act Annotation, Second Edition. Proceedings of LREC 2020, pp. 549–558. aclanthology.org/2020.lrec-1.69Cited on: Functions / Connections
- Prasad, R. and Bunt, H. (2015). Semantic Relations in Discourse: The Current State of ISO 24617-8. Proceedings of the 11th Joint ACL-ISO Workshop on Interoperable Semantic Annotation (ISA-11), London. aclanthology.org/W15-0210Cited on: Connections
Common ground in conversation
- Clark, H. H. and Brennan, S. E. (1991). Grounding in communication. In L. B. Resnick, J. M. Levine and S. D. Teasley (eds.), Perspectives on Socially Shared Cognition, pp. 127–149. American Psychological Association. doi.org/10.1037/10096-006Cited on: Context
- Stalnaker, R. (2002). Common ground. Linguistics and Philosophy, 25(5–6), 701–721. doi.org/10.1023/A:1020867916902Cited on: Context
Memory and cognition
- Cowan, N. (2001). The magical number 4 in short-term memory: A reconsideration of mental storage capacity. Behavioral and Brain Sciences, 24(1), 87–114. doi.org/10.1017/S0140525X01003922Cited on: Context
- Baddeley, A. (2000). The episodic buffer: a new component of working memory? Trends in Cognitive Sciences, 4(11), 417–423. doi.org/10.1016/S1364-6613(00)01538-2Cited on: Context
- Gilboa, A. and Marlatte, H. (2017). Neurobiology of Schemas and Schema-Mediated Memory. Trends in Cognitive Sciences, 21(8), 618–631. doi.org/10.1016/j.tics.2017.04.013Cited on: Context
- Bein, O. and Niv, Y. (2025). Schemas, reinforcement learning and the medial prefrontal cortex. Nature Reviews Neuroscience, 26, 141–157. doi.org/10.1038/s41583-024-00893-zCited on: Context
- Moscovitch, D. A., Moscovitch, M. and Sheldon, S. (2023). Neurocognitive Model of Schema-Congruent and -Incongruent Learning in Clinical Disorders: Application to Social Anxiety and Beyond. Perspectives on Psychological Science, 18(6), 1412–1435.Cited on: Context
- Anderson, J. R., Bothell, D., Byrne, M. D., Douglass, S., Lebiere, C. and Qin, Y. (2004). An Integrated Theory of the Mind. Psychological Review, 111(4), 1036–1060. doi.org/10.1037/0033-295X.111.4.1036Cited on: Context
- Anderson, J. R. and Schooler, L. J. (1991). Reflections of the Environment in Memory. Psychological Science, 2(6), 396–408. doi.org/10.1111/j.1467-9280.1991.tb00174.xCited on: Context
Density-based methods
- Ester, M., Kriegel, H.-P., Sander, J. and Xu, X. (1996). A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Proceedings of KDD-96, pp. 226–231.Cited on: Context
- Campello, R. J. G. B., Moulavi, D. and Sander, J. (2013). Density-Based Clustering Based on Hierarchical Density Estimates. PAKDD 2013, LNCS 7819, pp. 160–172. doi.org/10.1007/978-3-642-37456-2_14Cited on: Context
Open problems
AWAI's analysis rests on two premises.
The first is that an LLM makes the judgments. The standards' definitions are provided to an LLM, which selects functions and connections based on them. When the standards were established, they assumed manual annotation and the machine-learning methods of the time for automatic annotation. While LLMs now make it possible to apply the definitions as written, their judgments still include misreadings.
The second is that the input is limited to the words of the conversation. Tone of voice, facial expressions, experiences outside the conversation, and assumptions shared by participants are not included in the analysis.
Misreadings occur even between participants in the same conversation. We believe most of AWAI's open problems stem from the difficulty of reading in the moment, from words alone.
What comes next
As LLMs improve and can handle more information, we believe these challenges can be addressed. We intend to maintain the foundation built on standards and literature while improving the accuracy of the analysis.