Weak Supervision for Learning Discourse Structure (D19-1)

Copied to clipboard

Challenge: a weak supervision approach is a promising tool for learning discourse structure for multi-party dialogue.
Approach: They propose a data programming paradigm that allows a user to label training data using expert-composed heuristics and transform them into probability distributions of the class labels.
Outcome: The proposed approach outperforms both deep learning and traditional ML approaches on the task of learning discourse structure for multi-party dialogue.

Similar Papers

Data Programming for Learning Discourse Structure (P19-1)

Copied to clipboard

Challenge: Discourse structures are a relational semantic structure that convey causal, topical, argumentative relations or more generally coherence relations.
Approach: They propose to use Snorkel to label training data using expert-composed heuristics and transform them into probability distributions of the class labels given to training candidates.
Outcome: The proposed paradigm can be used for difficult tasks such as that of discourse attachment.
Weakly supervised discourse segmentation for multiparty oral conversations (2021.emnlp-main)

Copied to clipboard

Challenge: Discourse segmentation is the first step of discourse analysis.
Approach: They propose a weak supervision approach to adapt a latent model to French conversation transcripts with a linguistic and acoustic input.
Outcome: The proposed model improves in situations where speaker turns are lacking or noisy, gaining up to 13% in F-score.
META: Metadata-Empowered Weak Supervision for Text Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for weakly supervised text classification use text data alone to generate pseudo-labels . strong label indicators exist in metadata and it has been long overlooked due to challenges .
Approach: They propose a framework that leverages metadata as an additional source of weak supervision by combining text data and metadata into a text-rich network.
Outcome: The proposed framework exploits metadata as an additional source of weak supervision.
Semi-Supervised Tri-Training for Explicit Discourse Argument Expansion (2020.lrec-1)

Copied to clipboard

Challenge: a novel application of semi-supervision for shallow discourse parsing is described . we focus on explicit discourse arguments, but we leave the sense selection aside .
Approach: They propose a semi-supervised approach for shallow discourse parsing using sequence tagging.
Outcome: The proposed approach improves performance by 2-10% in the first setting and by comparing the results with training relations.
Self-Training with Weak Supervision (2021.naacl-main)

Copied to clipboard

Challenge: State-of-the-art deep neural networks require large amounts of labeled training data that is expensive to obtain or not available for many tasks.
Approach: They propose a weak supervision framework that leverages all available data for a given task . they leverage task-specific unlabeled data through self-training with a model that predicts pseudo-labels for instances that may not be covered by weak rules .
Outcome: The proposed framework improves on state-of-the-art datasets on six benchmark tasks.
Multitask Semi-Supervised Learning for Class-Imbalanced Discourse Classification (2021.emnlp-main)

Copied to clipboard

Challenge: Discourse learning is a complex task, and schemas evolve across annotation efforts preventing compilation of smaller datasets into larger ones.
Approach: They propose a multitask learning approach that can combine discourse datasets from similar and diverse domains to improve discourse classification.
Outcome: The proposed approach improves on the NewsDiscourse dataset by 4.9% over current state-of-the-art benchmarks on one of the largest discourse datasets.
X-Class: Text Classification with Extremely Weak Supervision (2021.naacl-main)

Copied to clipboard

Challenge: Weak supervision is a problem in text classification, but it requires corpusspecific knowledge.
Approach: They propose a framework for extremely weak supervision that can be used to train a text classifier.
Outcome: The proposed framework outperforms seed-driven weakly supervised methods on 7 benchmark datasets.
Integrating Tree Structures and Graph Structures with Neural Networks to Classify Discussion Discourse Acts (C18-1)

Copied to clipboard

Challenge: Existing models that analyze textual contents and discussion structures require understanding of textual content and discussion structure.
Approach: They propose a model that integrates discussion structures with neural networks to classify discourse acts.
Outcome: The proposed model improves accuracy and FB1 score by 1.5% compared to the previous best model.
The Strength of the Weakest Supervision: Topic Classification Using Class Labels (N19-3)

Copied to clipboard

Challenge: a topic classifier can understand only class labels when training for tasks that require a large amount of labeled documents.
Approach: They propose an algorithm that can initialize a topic classifier using only class labels . they propose a method that combines word embedding and naive Bayes classification .
Outcome: The proposed approach saves significant initial labeling effort by providing a "warm start" the proposed approach can be fine-tuned with more labeled documents to reach a certain performance level.
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.

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