Challenge: Existing studies focus on extracting NMs from small-scale well-structured corpora such as movie scripts wherein NM is enclosed in parentheses by scriptwriters, which greatly decreases the difficulty of extraction.
Approach: They propose to extract nonverbal messages (NMs) from written text and NMs from spoken text by using a semi-supervised learning algorithm.
Outcome: The extracted NMs can generate more relevant, valid, and factually consistent NM than the purely supervised generator.

Similar Papers

Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System (2022.lrec-1)

Copied to clipboard

Challenge: Contextually aware intelligent agents are often required to understand the users and their surroundings in real-time.
Approach: They propose to build a multimodal dialogue system for children learning basic math concepts using limited datasets.
Outcome: The proposed system improves the Natural Language Understanding (NLU) module of a task-oriented SDS pipeline with limited dataset resources.
Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues (2025.acl-long)

Copied to clipboard

Challenge: Existing large language models fail to incorporate nonverbal elements into conversational experiences.
Approach: They propose a multimodal language model that generates nonverbal cues alongside text . their dataset is annotated with time-aligned text, facial expressions, and body language .
Outcome: The proposed model generates nonverbal languages and text, corresponding to conversational input.
Machines Getting with the Program: Understanding Intent Arguments of Non-Canonical Directives (2020.findings-emnlp)

Copied to clipboard

Challenge: Modern dialog managers face the challenge of having to fulfill human-level conversational skills as part of common user expectations.
Approach: They propose to extract the intent argument of non-canonical directives in a natural language format and build a parallel corpus for this purpose.
Outcome: The proposed method extracts the intent argument of non-canonical directives in a natural language format, which may yield more accurate parsing.
Data Augmentation for Multiclass Utterance Classification – A Systematic Study (2020.coling-main)

Copied to clipboard

Challenge: a lack of sufficient training data for some categories can cause imbalanced data distributions . a weak classifier may miscategorize a request, resulting in customer dissatisfaction .
Approach: They propose to use random resampling, word-level transformations and neural text generation to augment existing data to cope with imbalanced data.
Outcome: The proposed methods improve utterance classification results by drawing on utterant variation.
PAED: Zero-Shot Persona Attribute Extraction in Dialogues (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for persona attribute extraction from conversations are inconsistent and unreliable.
Approach: They propose a model with a hard negative sampling strategy for generalized zero-shot persona attribute extraction.
Outcome: The proposed model outperforms existing models in persona attribute extraction tasks.
Pretrained Language Models for Dialogue Generation with Multiple Input Sources (2020.findings-emnlp)

Copied to clipboard

Challenge: Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks.
Approach: They propose to fuse attention information from multiple input sources to achieve better relevance with dialogue history than simple fusion baselines.
Outcome: The proposed models deliver higher relevance with dialogue history than baselines.
Automatic Dialogue Generation with Expressed Emotions (N18-2)

Copied to clipboard

Challenge: a growing interest in neural dialogue generation systems is focusing on generating human-like responses based on past utterances . despite efforts, few consider putting restrictions on the response itself . authors present three models that concatenate the desired emotion with the source input .
Approach: They propose three models that concatenate the desired emotion with the source input or push the emotion in the decoder.
Outcome: The proposed model is more efficient than the previous models, but it lacks the emotion vector.
Extractive Summarization with Text Generator (2024.naacl-long)

Copied to clipboard

Challenge: Existing extractive systems lack gold training signals, thereby hindering learning of extractive models.
Approach: They propose to use text generators to train extractive summarizers by approximating outputs of abstractive summaries.
Outcome: The proposed method can be used to train extractive summarizers without training . it is shown that the approximated summaries correlate positively with the auxiliary summary outputs.
Diversifying Dialogue Generation with Non-Conversational Text (2020.acl-main)

Copied to clipboard

Challenge: Neural network-based sequence-to-sequence models suffer from low diversity in open-domain dialogue generation.
Approach: They propose a way to diversify dialogue generation by leveraging non-conversational text . they collect large-scale corpus from forum comments, idioms and book snippets .
Outcome: The proposed model produces significantly more diverse responses without sacrificing relevance with context.
Affectron: Emotional Speech Synthesis with Affective and Contextually Aligned Nonverbal Vocalizations (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on speech synthesis incorporating NVs have limited ability to generate expressive speech.
Approach: They propose a framework for affective and contextually aligned NV generation using a small-scale open corpus.
Outcome: The proposed framework expands the distribution of NV types and insertion locations . it produces more expressive and diverse NVs than baseline systems while preserving naturalness of verbal speech stream.

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