Continuous Relational Diffusion Driven Topic Model with Multi-grained Text for Microblog (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing topic models assume that there are only 0/1-state relationships between the two parties in social networks, but the relationship status in real life is more complicated. |
| Approach: | They propose a topic model that leverages unsupervised learning to mine hidden topics in document collections using multi-grained text. |
| Outcome: | The proposed model can be applied to microblog with multi-grained text to realize the representation of the relationship state and make up for the context and structural information lost by previous representation methods. |
Similar Papers
Interaction-Aware Topic Model for Microblog Conversations through Network Embedding and User Attention (C18-1)
Copied to clipboard
| Challenge: | Existing topic models ignore that one discusses diverse topics when dynamically interacting with different people. |
| Approach: | They propose an Interaction-Aware Topic Model (IATM) for microblog conversations by integrating network embedding and user attention. |
| Outcome: | The proposed model is based on three real-world microblog datasets. |
TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies focus on learning contextual information in conversations, neglecting acoustic and vision topic information. |
| Approach: | They propose a model-agnostic Topic-enriched Diffusion approach for capturing multimodal topic information in MCE tasks. |
| Outcome: | The proposed approach improves over the state-of-the-art MCE models and the existing models. |
Dynamic Topic Modeling by Clustering Embeddings from Pretrained Language Models: A Research Proposal (2022.aacl-srw)
Copied to clipboard
| Challenge: | Neural Topic Models (NTMs) are topic models that are created with the help of a pretrained language model. |
| Approach: | They propose to do Neural Topic Modeling by Clustering document Embeddings (NTM-CE) with a pretrained language model to create dynamic topic models. |
| Outcome: | The proposed model can be evaluated theoretically and practically using quantitative measurements of coherence and human evaluation to evaluate the model. |
Multi-source Neural Topic Modeling in Multi-view Embedding Spaces (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work has used pre-trained word embeddings to address data sparsity in short-text or small document collections. |
| Approach: | They propose a neural topic modeling framework using multi-view embedding spaces to improve topic quality and deal with polysemy. |
| Outcome: | The proposed framework improves topic quality and deal with polysemy. |
Continual Neural Topic Model (2026.eacl-long)
Copied to clipboard
| Challenge: | Continual Neural Topic Models (CoNTMs) learn topic models at subsequent time steps without forgetting what was previously learned. |
| Approach: | They propose a Continual Neural Topic Model which continuously learns topic models at subsequent time steps without forgetting what was previously learned. |
| Outcome: | The proposed model outperforms the dynamic topic model in topic quality and predictive perplexity while being able to capture topic changes online. |
Modeling Online Discourse with Coupled Distributed Topics (D18-1)
Copied to clipboard
| Challenge: | a topic model that incorporates structural relationships connecting documents in socially generated corpora is of limited application in the sciences. |
| Approach: | They propose a topic model that incorporates structural relationships connecting documents in socially generated corpora, such as online forums. |
| Outcome: | The proposed model captures discursive interactions along observed reply links and integrates latent distributed representations in a deep architecture. |
Dynamic Structured Neural Topic Model with Self-Attention Mechanism (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent topic models that capture the time-series evolution of topics assume that topics evolve independently without interaction. |
| Approach: | They propose a dynamic structured neural topic model which captures topic dependencies while capturing their dependencies. |
| Outcome: | The proposed model outperforms a prior dynamic embedded topic model regarding perplexity and coherence while maintaining sufficient diversity across topics. |
Topics as Entity Clusters: Entity-based Topics from Large Language Models and Graph Neural Networks (2024.lrec-main)
Copied to clipboard
| Challenge: | Topic models aim to reveal latent structures within corpus of text through term-frequency statistics over bag-of-words representations. |
| Approach: | They propose to use bimodal vector representations of entities to extract latent representations from large language models and graph neural networks trained on symbolic relations to derive the most salient aspects of these conceptual units. |
| Outcome: | The proposed approach is better suited to working with entities than state-of-the-art models. |
VIBE: Topic-Driven Temporal Adaptation for Twitter Classification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Language features are evolving in real-world social media, resulting in deteriorating performance of text classification. |
| Approach: | They propose a model that allows models to adapt to shifted data via latent topic evolution . they use two information bottleneck regularizers to distinguish past and future topics . |
| Outcome: | The proposed model outperforms state-of-the-art models on Twitter on three tasks with 3% of data. |
DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Neural Topic Models and Large Language Models (LLMs) primarily use contextual embeddings from LLMs, which are not optimal for clustering or topic generation. |
| Approach: | They propose a framework that leverages Encoder-Decoders to generate highly clusterable embeddings that could generate topics that exhibit enhanced clusterability and enhanced semantic coherence compared to existing methods. |
| Outcome: | The proposed framework is efficient to train and exhibits high adaptability, demonstrating its potential for a wide array of applications. |