Challenge: Using sequences of sentences, we show that learning long-range latent discourse structure from large corpora can be useful for machine learning.
Approach: They propose a probabilistic model of documents as sequences of sentences with a 2- or 3-D spatial grid and embed sentences into a grid.
Outcome: The proposed model outperforms or is competitive with state-of-the-art generative approaches on tasks such as predicting the outcome of a story, and sentence ordering.

Similar Papers

Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues (2023.findings-eacl)

Copied to clipboard

Challenge: Discourse processing suffers from data sparsity, especially for dialogues . a variety of discourse frameworks have been proposed to extract discourse information from dialogues.
Approach: They propose unsupervised and semi-supervised methods to infer latent discourse structures for dialogues based on attention matrices from Pre-trained Language Models.
Outcome: The proposed methods achieve encouraging results on the STAC corpus, with F1 scores of 57.2 and 59.3 for the unsupervised and semi-supervised methods, respectively.
Screenplay Summarization Using Latent Narrative Structure (2020.acl-main)

Copied to clipboard

Challenge: Experimental results show that latent turning points improve summarization performance over general extractive summarizing models.
Approach: They propose to explicitly incorporate the underlying structure of narratives into extractive summarization models by treating it as latent.
Outcome: The proposed model improves on the CSI corpus of screenplays on a CSI episode . it shows that latent turning points correlate with important aspects of the document .
Discourse Representation Parsing for Sentences and Documents (P19-1)

Copied to clipboard

Challenge: Experimental results show that our model outperforms competitive baselines by a wide margin.
Approach: They propose a neural model which parses discourse structures of arbitrary length and granularity.
Outcome: The proposed model outperforms baseline models on sentence- and document-level benchmarks.
Latent Structure Models for Natural Language Processing (P19-4)

Copied to clipboard

Challenge: Latent structure models are a powerful tool for compositional data modeling and pipelines.
Approach: This tutorial will cover recent advances in discrete latent structure models . it will discuss their motivation, potential, and limitations .
Outcome: This tutorial will cover recent advances in discrete latent structure models . it will discuss their motivation, potential, and limitations .
A Structured Clustering Approach for Inducing Media Narratives (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to modeling media narratives miss subtle narrative patterns through coarse-grained analysis or require domain-specific taxonomies that limit scalability.
Approach: They propose a framework for inducing rich narrative schemas by jointly modeling events and characters via structured clustering.
Outcome: The proposed framework produces explainable narrative schemas that align with established framing theory while scaling to large corpora without exhaustive manual annotation.
Pre-training Multi-party Dialogue Models with Latent Discourse Inference (2023.acl-long)

Copied to clipboard

Challenge: Existing studies have failed to scale up the pre-training process by putting aside unlabeled data . et al., 2019: multi-party dialogues are more difficult for models to understand since they involve multiple interlocutors resulting in interweaving reply-to relations and information flows.
Approach: They propose to treat discourse structures as latent variables and jointly infer them to pre-train a model that understands the discourse structure of multi-party dialogues.
Outcome: The proposed model outperforms baselines and achieves state-of-the-art results on multiple downstream tasks.
Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies on text summarization focus on single-speaker docs, scientific publications and encyclopedia articles.
Approach: They propose a multi-view sequence-to-sequence model that extracts conversational structures from unstructured daily chats and incorporates different views to generate dialogue summaries.
Outcome: The proposed model outperforms state-of-the-art models via automatic evaluation and human judgment on a large-scale dialogue summarization corpus.
Exploiting Discourse-Level Segmentation for Extractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing approaches to extract summarize text are based on sentences as the elementary unit, but semantic segments containing supplementary information or descriptive details are often nonessential in the generated summaries.
Approach: They propose to exploit discourse-level segmentation as a finer-grained means to more precisely pinpoint the core content in a document.
Outcome: The proposed method improves extractive summarization performance on CNN/Daily Mail dataset.
Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs (2024.acl-long)

Copied to clipboard

Challenge: Empirical findings show that although both LLMs and humans generate distinct discourse patterns influenced by specific domains, human-written texts exhibit more structural variability, reflecting the nuanced nature of human writing in different domains.
Approach: They propose a method to leverage hierarchical parse trees and recursive hypergraphs to uncover distinctive discourse patterns in texts written by humans and LLMs.
Outcome: The proposed method combines hierarchical parse trees and recursive hypergraphs to uncover distinctive discourse patterns in texts produced by both LLMs and humans.
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for document-level relation extraction capture non-local interactions but are not able to capture rich non-linguistic interactions.
Approach: They propose a document-level relation extraction model that empowers relational reasoning across sentences by automatically inducing the latent document- level graph.
Outcome: The proposed model achieves an F1 score of 59.05 on a large-scale document-level dataset (DocRED), significantly improving over the previous results.

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