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 .

Similar Papers

ISO-Standard Domain-Independent Dialogue Act Tagging for Conversational Agents (C18-1)

Copied to clipboard

Challenge: Existing methods for DA annotation are incompatible with each other and do not cover all aspects necessary for open-domain human-machine interaction.
Approach: They propose to map publicly available corpora to a subset of the ISO standard and create a task-independent training corpus for DA classification.
Outcome: The proposed method can train a domain-independent DA tagger on out-of-domain conversational data and achieve robustness across different DA categories.
The ISO Standard for Dialogue Act Annotation, Second Edition (2020.lrec-1)

Copied to clipboard

Challenge: ISO standard 24617-2 for dialogue act annotation has been used in corpus annotation and in the design of components for spoken and multimodal interactive systems.
Approach: ISO standard 24617-2 for dialogue act annotation is proposed for a second edition . this second edition allows a more accurate annotation of dependence relations and rhetorical relations in dialogue.
Outcome: The proposed second edition of ISO 24617-2 for dialogue act annotation addresses some inaccuracies and undesirable limitations.
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.
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.
Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation (N19-1)

Copied to clipboard

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.
Dialog-Post: Multi-Level Self-Supervised Objectives and Hierarchical Model for Dialogue Post-Training (2023.acl-long)

Copied to clipboard

Challenge: a new method for dialogue representation and understanding is proposed . pre-trained language models (PLMs) are inappropriate for dialogue understanding tasks .
Approach: They propose a method that trains pre-trained language models to fit dialogues . they use a hierarchical segment-wise self-attention network to model dialogues more comprehensively .
Outcome: The proposed method outperforms existing models and achieves a 3.3% improvement on average.
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging (D18-1)

Copied to clipboard

Challenge: Low-resource languages lack manual annotated data to learn basic models such as part-of-speech (POS) taggers.
Approach: They propose a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision in a uniform framework.
Outcome: The proposed model scales to hundreds of low-resource languages without access to gold annotated data.
A Deeper (Autoregressive) Approach to Non-Convergent Discourse Parsing (2023.emnlp-main)

Copied to clipboard

Challenge: Existing frameworks for dialogic discourse parsing are not suitable for contentious discussions . authors propose a model for non-convergent discourse paring that does not require label collocation .
Approach: They propose a multi-label scheme for contentious dialog parsing that uses multiple labels . they propose combining embeddings of the utterance, context and the labels through GRN layers .
Outcome: The proposed model achieves comparable results with SOTA without label collocation and without training a unique architecture/model for each label.
In Search of the Lost Arch in Dialogue: A Dependency Dialogue Acts Corpus for Multi-Party Dialogues (2025.findings-acl)

Copied to clipboard

Challenge: Understanding speaker intentions remains a challenge in NLP . a number of corpora annotated using theoretical frameworks of dialogue focus on utterance-level labeling of speaker intent, missing wider context, or the rhetorical structure of a dialogue.
Approach: They propose to annotate a corpus of 33 dialogues and over 9,000 utterance units using the Dependency Dialogue Acts framework.
Outcome: The proposed corpus spans four genres of multi-party conversations from different modalities.
Coarse-to-Fine Decoding for Neural Semantic Parsing (P18-1)

Copied to clipboard

Challenge: Experimental results show that semantic parsing is more efficient than using simple decoders.
Approach: They propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages.
Outcome: The proposed architecture consistently improves performance on four datasets characteristic of different domains and meaning representations.

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