paper-with-me

Papers

Integrating topic modeling and word embedding to characterize violent deaths

2021-06-28 · Alina Arseniev-Koehler, Susan D. Cochran, Vickie M. Mays, Kai-Wei Chang, Jacob Gates Foster

There is an escalating need for methods to identify latent patterns in text data from many domains. We introduce a new method to identify topics in a corpus and represent documents as topic sequences. Discourse Atom Topic Modeling draws on advances in theoretical machine learning to integrate topic modeling and word embedding, capitalizing on the distinct capabilities of each. We first identify a set of vectors ("discourse atoms") that provide a sparse representation of an embedding space. Atom vectors can be interpreted as latent topics: Through a generative model, atoms map onto distributions over words; one can also infer the topic that generated a sequence of words. We illustrate our method with a prominent example of underutilized text: the U.S. National Violent Death Reporting System (NVDRS). The NVDRS summarizes violent death incidents with structured variables and unstructured narratives. We identify 225 latent topics in the narratives (e.g., preparation for death and physical aggression); many of these topics are not captured by existing structured variables. Motivated by known patterns in suicide and homicide by gender, and recent research on gender biases in semantic space, we identify the gender bias of our topics (e.g., a topic about pain medication is feminine). We then compare the gender bias of topics to their prevalence in narratives of female versus male victims. Results provide a detailed quantitative picture of reporting about lethal violence and its gendered nature. Our method offers a flexible and broadly applicable approach to model topics in text data.

📄 PDF Abstract BibTeX arXiv:2106.14365

Code (1)

arsena-k/discourse_atoms

Similar Papers 제목 키워드 기반

Integrating Topic Modeling with Word Embeddings by Mixtures of vMFs

2016-12-01 · COLING 2016 12 · Xi-Ming Li, Jinjin Chi, Changchun Li, Jihong Ouyang 외

Gaussian LDA integrates topic modeling with word embeddings by replacing discrete topic distribution over word types with multivariate Gaussian distribution on the embedding space. This can take semantic information of w…

Topic ModelsWord Embeddings

Poisson-Process Topic Model for Integrating Knowledge from Pre-trained Language Models

2025-03-22 · Morgane Austern, Yuanchuan Guo, Zheng Tracy Ke, Tianle Liu

Topic modeling is traditionally applied to word counts without accounting for the context in which words appear. Recent advancements in large language models (LLMs) offer contextualized word embeddings, which capture dee…

Word Embeddings

Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling

2021-04-11 · NAACL 2021 4 · Aaron Mueller, Mark Dredze

Neural topic models can augment or replace bag-of-words inputs with the learned representations of deep pre-trained transformer-based word prediction models. One added benefit when using representations from multilingual…

ClassificationCross-Lingual TransferGeneral ClassificationTopic Classification+1

Latent Topic Embedding

2016-12-01 · COLING 2016 12 · Di Jiang, Lei Shi, Rongzhong Lian, Hua Wu

Topic modeling and word embedding are two important techniques for deriving latent semantics from data. General-purpose topic models typically work in coarse granularity by capturing word co-occurrence at the document/se…

SentenceTopic ModelsWord Embeddings

Multi-source Neural Topic Modeling in Multi-view Embedding Spaces

2021-04-17 · NAACL 2021 4 · Pankaj Gupta, Yatin Chaudhary, Hinrich Schütze

Though word embeddings and topics are complementary representations, several past works have only used pretrained word embeddings in (neural) topic modeling to address data sparsity in short-text or small collection of d…

Information RetrievalRetrievalWord Embeddings