Challenge: asynchronous domains lack large labeled datasets to train an effective speech act recognition model.
Approach: They propose methods to leverage abundant unlabeled conversational data and available labeled data from synchronous domains to train an effective SAR model.
Outcome: The proposed method outperforms existing methods when trained on in-domain data only.

Similar Papers

Augmenting Small Data to Classify Contextualized Dialogue Acts for Exploratory Visualization (2020.lrec-1)

Copied to clipboard

Challenge: a new corpus of conversations is being developed to support data visualization exploration . we use data augmentation to improve our methods for dialogue act classification .
Approach: They propose to use a corpus of conversations to annotate contextualized dialogue acts . they highlight how thinking aloud affects interpretation of dialogue acts in the context .
Outcome: The proposed AI can support visualization exploration with a small corpus of conversations . the proposed AI outperforms existing models in terms of performance and performance .
Session-level Language Modeling for Conversational Speech (D18-1)

Copied to clipboard

Challenge: Xiong et al., 2017) generalizes language models for conversational speech recognition . recurrent neural networks (RNNs) read a list of words sequentially and predict the next word at each position.
Approach: They propose to generalize language models for conversational speech recognition to capture conversation-level phenomena such as adjacency pairs, lexical entrainment, and topical coherence.
Outcome: The proposed model reduces perplexity and improves word error rate over standard models in the conversational telephone speech domain.
Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach (P18-1)

Copied to clipboard

Challenge: Existing coherence models are not able to distinguish coherent discourses from incoherent ones.
Approach: They propose a novel coherence model for written asynchronous conversations . they propose to lexicalize the model's entity transitions and extend it to asynchron conversations based on conversational structure .
Outcome: The proposed model outperforms existing models on coherence assessment and thread reconstruction tasks.
Unsupervised Learning of Hierarchical Conversation Structure (2022.findings-emnlp)

Copied to clipboard

Challenge: Goal-oriented conversations often have sub-dialogue structure, but it can be domain-dependent . Increasingly, language understanding applications involve conversational speech and text .
Approach: They propose an unsupervised approach to learning hierarchical conversation structure . they use turn and sub-dialogue segment labels to decode the structure based on dialogue acts and subtasks .
Outcome: The proposed approach improves neural models for three conversation-level understanding tasks.
Dialogue Act Classification with Context-Aware Self-Attention (N19-1)

Copied to clipboard

Challenge: Recent work in Dialogue Act classification has treated the task as a sequence labeling problem using hierarchical deep neural networks.
Approach: They propose a hierarchical deep neural network to model different levels of utterance and dialogue act semantics and use contextual dependencies to improve performance.
Outcome: The proposed model improves on the Switchboard Dialogue Act Corpus while maintaining high accuracy.
A Dynamic Speaker Model for Conversational Interactions (N19-1)

Copied to clipboard

Challenge: a neural model for characterizing individual differences in speakers is shown to be useful in human-computer interaction and dialog act prediction.
Approach: They propose a neural model for learning a dynamically updated speaker embedding in a conversational context.
Outcome: The proposed model is used for content ranking and dialog act prediction in human-human conversations.
Spoken Conversational Agents with Large Language Models (2025.emnlp-tutorials)

Copied to clipboard

Challenge: This tutorial focuses on the evolution of voice-native LLMs . it reviews the adaptation of text LLM to audio, cross-modal alignment, and joint speech–text training .
Approach: This tutorial examines the evolution of voice-native LLMs in conversational agents . it compares cascaded and voice-based LLM systems to end-to-end retrieval-and vision-grounded systems .
Outcome: This tutorial examines the evolution of voice-native LLMs . it compares the performance of voice assistants to current open-domain agents .
A Multi-Dimensional, Cross-Domain and Hierarchy-Aware Neural Architecture for ISO-Standard Dialogue Act Tagging (2022.coling-1)

Copied to clipboard

Challenge: Dialogue Act tagging with ISO 24617-2 standard is a difficult task that requires multiple labels covering semantic, syntactic and pragmatic aspects of dialogue.
Approach: They propose a neural architecture to increase Dialogue Act tagging accuracy by using low-frequency fine-grained tags.
Outcome: The proposed model achieves state-of-the-art tagging results on DialogBank data set . it uses syntactic information in the form of Part-Of-Speech and dependency tags .
Dialogue-act-driven Conversation Model : An Experimental Study (C18-1)

Copied to clipboard

Challenge: In the last decade, natural language processing and machine learning have come a long way towards building an automated dialogue system.
Approach: They propose a way to encode dialogue act information and use it to build a model that can use it in a natural way.
Outcome: The proposed model outperforms baseline models on a new daily dialogue dataset and achieves an MRR of about 84.8%.
Pretrained Language Models for Sequential Sentence Classification (D19-1)

Copied to clipboard

Challenge: Recent successful models for document-level understanding have used hierarchical encoding and CRFs to capture dependencies between subsequent labels.
Approach: They propose a pretrained language model that captures contextual dependencies without hierarchical encoding nor a CRF.
Outcome: The proposed model captures contextual dependencies without hierarchical encoding nor a CRF on four datasets, including a new dataset of structured scientific abstracts.

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