Challenge: Verbal communication is companied by rich non-verbal signals, but few studies have explored the non- verbal channels with finer theoretical lens.
Approach: They extract gesture representations from monologue video data and train neural sequential models to examine their results.
Outcome: The proposed method shows that speakers use simple gestures to convey information that enhances verbal communication.

Similar Papers

Spontaneous gestures encoded by hand positions improve language models: An Information-Theoretic motivated study (2023.findings-acl)

Copied to clipboard

Challenge: a key missing step is to explore whether the nonverbal information can be quantified.
Approach: They explore whether incorporating gesture representations can improve the language model’s performance . they also examine whether spontaneous gestures demonstrate entropy rate constancy (ERC) .
Outcome: The proposed model improves the performance of the mixed-modal language models against monologue video data.
Does Listener Gaze in Face-to-Face Interaction Follow the Entropy Rate Constancy Principle: An Empirical Study (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have shown that nonverbal behaviours are rich in communicative functions, such as gaze, head movements, and speech-accompanying manual gestures.
Approach: They train a transformer-based neural sequence model to process gaze data extracted from video-recorded conversations and compute its information density.
Outcome: The proposed model computes listeners’ gaze behaviour and the information density of speech using a pre-trained language model.
How Much Does Nonverbal Communication Conform to Entropy Rate Constancy?: A Case Study on Listener Gaze in Interaction (2024.findings-acl)

Copied to clipboard

Challenge: Whether the Entropy Rate Constancy principle applies to nonverbal communication signals is still under investigation.
Approach: They perform empirical analyses of video-recorded dialogue data and investigate whether listener gaze adheres to the Entropy Rate Constancy principle.
Outcome: The results show that the ERC principle holds for listener gaze, and that linguistic factors syntactic complexity and turn transition potential are weakly correlated with local entropy of listener gaze.
What Do Prosody and Text Convey? Characterizing How Meaningful Information is Distributed Across Multiple Channels (2026.acl-long)

Copied to clipboard

Challenge: Prosody—the melody of speech—conveys critical information often not captured by the words or text of a message.
Approach: They propose an information-theoretic approach to quantify how much is conveyed by prosody that is not recoverable from text alone.
Outcome: The proposed framework can quantify how much is conveyed by prosody that is not recoverable from text alone and crucially, what prosody conveys.
Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Effective interlocutors account for the uncertain goals, beliefs, and emotions of others.
Approach: They propose to calibrate language models to better represent outcome uncertainty . they propose to use two methods to calibrated small open-source models .
Outcome: The proposed fine-tuning strategies can calibrate smaller open-source models to beat pre-trained models 10x their size.
Revisiting Entropy Rate Constancy in Text (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing evidence supports the uniform information density hypothesis . however, we re-evaluate the hypothesis with neural language models .
Approach: They propose to use n-gram language models to argue that English documents exhibit entropy rate constancy . they re-evaluate the claims of Genzel and Charniak with neural language models .
Outcome: The proposed hypothesis fails to support the proposed hypothesis with language models.
The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learning (2021.emnlp-main)

Copied to clipboard

Challenge: Existing studies have focused on agent-based simulations of language emergence.
Approach: They propose to model the trade-off between word order and inflection in natural languages by using neural network agents.
Outcome: The results show that neural agents strive to maintain the utterance type distribution observed during learning, rather than developing a more efficient or systematic language.
Towards Understanding the Relation between Gestures and Language (2022.coling-1)

Copied to clipboard

Challenge: a new study explores the relationship between gestures and language . we use contrastive learning to learn gesture embeddings .
Approach: They adapt a semi-supervised multimodal model to learn gesture embeddings using Ted talks . they show gestures are predictive of the native language of the speaker .
Outcome: The proposed model learns gesture embeddings from a multimodal dataset . it shows that gesture embeds are predictive of the native language of the speaker .
LLM Knows Body Language, Too: Translating Speech Voices into Human Gestures (2024.acl-long)

Copied to clipboard

Challenge: despite advances in the generation of realistic human gestures, the process often includes unintended, meaningless, or non-realistic gestures.
Approach: They propose a framework that leverages large language models to generate human gestures . the primary stage employs a transformer-based auto-encoder network to encode human gesture into discrete symbols .
Outcome: The proposed framework has demonstrated state-of-the-art performance on public TED and TED-Expressive datasets.
Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses (2026.acl-long)

Copied to clipboard

Challenge: Existing studies have focused mainly on LLMs' comprehension of verbal behavior, with non-verbal behavior considered only in conjunction with verbal responses.
Approach: They present the first systematic evaluation of LLMs’ ability to infer pragmatic meaning in dialogue consisting solely of non-verbal responses.
Outcome: The proposed model fails to capture non-verbal intent and has accuracy dropping by 60% compared to verbal ones.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations