More Than Spoken Words: Nonverbal Message Extraction and Generation (2023.emnlp-main)
Copied to clipboard
| 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
Youngmin Kim, Jiwan Chung, Jisoo Kim, Sunghyun Lee, Sangkyu Lee, Junhyeok Kim, Cheoljong Yang, Youngjae Yu
| 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. |