Papers with topic model
Improving Privacy Guarantee and Efficiency of Latent Dirichlet Allocation Model Training Under Differential Privacy (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Latent Dirichlet allocation (LDA) is a widely used topic model to discover the latent semantic of text data. |
| Approach: | They propose to combine a subsampling method with CGS to improve efficiency while amplifying privacy by using a novel metric, the efficiency–privacy function. |
| Outcome: | The proposed algorithm improves efficiency while amplifying privacy while subsampling in CGS increases efficiency while preserving privacy. |
LTV: Labeled Topic Vector (C18-2)
Copied to clipboard
| Challenge: | Using nnDDC, we generate labeled topic classifications based on the Dewey Decimal Classification (DDC) Unlike related approaches, we use classifiers to define the dimensions of CISS, which are directly labeles by the underlying target class. |
| Approach: | They propose a website and API that generates labeled topic classifications based on the Dewey Decimal Classification (DDC) they propose nnDDC, a largely language-independent natural network-based classifier for DDC, which is language-dependent . |
| Outcome: | The proposed model is language-independent and performs well in 40 languages. |
On Fake News Detection with LLM Enhanced Semantics Mining (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting fake news use only news embeddings to capture the lexical semantics between tokens. |
| Approach: | They propose a topic-based model with prompts to extract news embeddings from LLMs and a generalized page-rank model to extract local and global semantics. |
| Outcome: | The proposed model shows superior performance on five benchmark datasets over seven baseline methods. |
Friendly Topic Assistant for Transformer Based Abstractive Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive document summarization is a comprehensive task in natural language processing. |
| Approach: | They propose a topic assistant that rearranges and learns document semantics . they propose TA that is compatible with Transformer-based models and user-friendly . |
| Outcome: | The proposed model is compatible with Transformer-based models and user-friendly. |
PaRe: A Paper-Reviewer Matching Approach Using a Common Topic Space (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to reviewer-paper matching are less effective to deal with the vocabulary mismatch and partial topic overlap between the submission and reviewer. |
| Approach: | They propose to combine the common topic model and abstract topic vectors to model the topics common to the submission and the reviewer's profile while relying on abstract topic vectors. |
| Outcome: | The proposed model improves on the existing model on two datasets. |
Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese (P19-1)
Copied to clipboard
| Challenge: | Currently, most studies on implicit discourse relation recognition use sentence-level representations . Chinese is a paratactic language that tends to pro-drop clause connectives . |
| Approach: | They propose a topic tensor network to recognize Chinese implicit discourse relations with both sentence-level and topic-level representations. |
| Outcome: | The proposed model outperforms state-of-the-art models in micro and macro F1 scores on a Chinese discourse corpus. |
Topic Modeling by Clustering Language Model Embeddings: Human Validation on an Industry Dataset (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Topic models are powerful tools to get overview of large collections of text data. |
| Approach: | They propose to use a tool called STELLAR for interactive topic browsing to evaluate topics from a real-world dataset. |
| Outcome: | The proposed model performs better than LDA models in the real-world and is scalable. |
Modeling Temporality of Human Intentions by Domain Adaptation (D18-1)
Copied to clipboard
| Challenge: | Recent research shows that themes and words within a conversation change across time, whereas topics and the patient's attitude towards their willingness to change might shift. |
| Approach: | They propose a method that models the temporal factor by using domain adaptation on clinical dialogue corpora, Motivational Interviewing (MI). |
| Outcome: | The proposed method improves on a college alcoholism dataset using a bi-LSTM and topic model to learn language usage change across different time sessions. |
Automatic Evaluation of Local Topic Quality (P19-1)
Copied to clipboard
Jeffrey Lund, Piper Armstrong, Wilson Fearn, Stephen Cowley, Courtni Byun, Jordan Boyd-Graber, Kevin Seppi
| Challenge: | Topic models are evaluated with global topic distributions but without local topic assignments. |
| Approach: | They propose a task to elicit human judgments of token-level topic assignments . they propose to use global metrics to evaluate topic models at a local level . |
| Outcome: | The proposed task elicits human judgments of token-level topic assignments . global metrics agree poorly with human assignments, the authors show . |
Learning VAE-LDA Models with Rounded Reparameterization Trick (2020.emnlp-main)
Copied to clipboard
| Challenge: | No reparameterization form of Dirichlet distributions is known to date for topic models . |
| Approach: | They propose a method to reparameterize Dirichlet distributions for the learning of VAE-LDA models by using a latent Dirichlets prior. |
| Outcome: | The proposed method outperforms existing neural topic models on benchmark datasets and on a synthetic dataset. |
Scalable Collapsed Inference for High-Dimensional Topic Models (N19-1)
Copied to clipboard
| Challenge: | Existing methods have achieved two out of three criteria simultaneously, but never all three at once. |
| Approach: | They propose an online inference algorithm which leverages stochasticity to scale well in the number of documents and sparsity to achieve accurate inference. |
| Outcome: | The proposed algorithm scales well in the number of documents and topics while achieving accurate inference. |
Topic Model or Topic Twaddle? Re-evaluating Semantic Interpretability Measures (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for topic model evaluation use automated measures modeled on human evaluation tests that are dissimilar to applied usage. |
| Approach: | They propose to use a novel experimental framework to evaluate topic models and assess their coherence for specialized collections in an applied setting. |
| Outcome: | The proposed framework is reflective of human evaluations using open labeling, typical of applied research. |
Subtopic-driven Multi-Document Summarization (D19-1)
Copied to clipboard
| Challenge: | Experimental results show that the proposed model outperforms state-of-the-art methods on benchmark datasets. |
| Approach: | They propose a multi-document summarization model that assumes a set of documents to be summarized is on the same topic. |
| Outcome: | The proposed model outperforms state-of-the-art methods on benchmark datasets. |
Inductive Topic Variational Graph Auto-Encoder for Text Classification (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for text classification do not assume explicit latent semantic structure of documents, making them less effective and difficult to interpret. |
| Approach: | They propose a model that integrates a topic model into variational graph-auto-encoder to capture hidden semantic information between documents and words. |
| Outcome: | The proposed model outperforms existing models on supervised and semi-supervised text classification and unsupervised representation learning. |
CAST: Corpus-Aware Self-similarity Enhanced Topic modelling (2025.naacl-long)
Copied to clipboard
Yanan Ma, Chenghao Xiao, Chenhan Yuan, Sabine N Van Der Veer, Lamiece Hassan, Chenghua Lin, Goran Nenadic
| Challenge: | Existing topic modelling methods encode contextual information of documents while ignoring contextual details of candidate centroid words. Existing methods are limited by the contextualization gap. |
| Approach: | They propose a topic modelling method that builds upon candidate centroid word embeddings contextualized on the dataset and a self-similarity-based method to filter out less meaningful tokens. |
| Outcome: | The proposed method significantly enhances the coherence and diversity of generated topics, and handles noisy data, outperforming strong baselines. |
Learning Adverbs with Spectral Mixture Kernels (2024.findings-acl)
Copied to clipboard
| Challenge: | In order for robots to collaborate with humans, it is important to share and understand their experiences through language. |
| Approach: | They propose a hierarchical Dirichlet Process-Spectral Mixture Latent Dirichlets Allocation model which learns the relationship between human motions and adverbs by capturing frequency kernels that represent motion characteristics and shared topics of a given aadverts. |
| Outcome: | The proposed model outperforms representative neural network models in terms of perplexity score and predicts more appropriate adverbs. |
Platform-Invariant Topic Modeling via Contrastive Learning to Mitigate Platform-Induced Bias (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing topic models that analyze documents from multiple platforms are not able to capture the authentic topics due to platform-induced biases. |
| Approach: | They propose to use a platform-invariant contrastive learning algorithm to reduce platform influence in topic models by removing platform-specific jargon word sets. |
| Outcome: | The proposed model reduces platform influence in topic models by developing a platform-invariant contrastive learning algorithm and removing platform-specific jargon word sets. |
FoTo: Targeted Visual Topic Modeling for Focused Analysis of Short Texts (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing topic models perform a full corpus analysis that treats all topics equally, making them not on target. |
| Approach: | They propose a targeted topic model for semantic short-text embedding which aims to learn all topics and low-dimensional visual representations of documents while preserving relevant topics. |
| Outcome: | The proposed model learns all topics and low-dimensional visual representations while preserving relevant topics in the visualization space. |
A Bayesian Topic Model for Human-Evaluated Interpretability (2022.lrec-1)
Copied to clipboard
| Challenge: | Topic modeling is an effective way to analyze unstructured textual data. |
| Approach: | They propose to combine nonparametric and weakly-supervised topic models to produce interpretable topics. |
| Outcome: | The proposed model outperforms weakly-supervised models in the field of topic modeling. |
Leveraging Hashtag Networks for Multimodal Popularity Prediction of Instagram Posts (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing popularity prediction approaches reduce hashtags to simple features such as hashtag length or number of hashtags in a post. |
| Approach: | They propose a multimodal framework to predict popular influencer posts on Instagram using post captions, image, hashtag network and topic model. |
| Outcome: | The proposed framework outperforms baseline models and unimodal models on popular influencer posts in Taiwan . it uses post captions, image, hashtag network, and topic model to predict popular influence post . |
Topic Modeling: Contextual Token Embeddings Are All You Need (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current neural approaches to topic modeling have not been able to solve all of the problems. |
| Approach: | They propose a topic modeling approach that uses document contextual token embeddings to find topics and find topic spans within documents. |
| Outcome: | The proposed model outperforms the current state-of-the-art models on a comprehensive set of topic model evaluation metrics. |
Labeling Results of Topic Models: Word Sense Disambiguation as Key Method for Automatic Topic Labeling with GermaNet (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for topic modeling are not suitable for document classification, but they can be used to generate training data from large corpus. |
| Approach: | They propose to use topic modeling and automatic topic labeling to understand large corpora of text. |
| Outcome: | The proposed method is more accurate than existing methods. |
AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing tools for persuasion are well-equipped to identify which of a pre-existing set of messages is most persuasive, but they do not offer causal evidence on whether or how they have succeeded. |
| Approach: | They propose a framework for identifying topical components of persuasive arguments that are autopersuade. |
| Outcome: | The proposed framework validates the results through human studies and out-of-sample predictions. |