Hidden Topic Markov Models

By Amit Gruber, Yair Weiss, Michal Rosen-Zvi. International Conference on Artificial Intelligence and Statistics, 2007

321 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/9e8d2618749444abece74d2b980aed2a2e3b4902

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

How to Analyze Political Attention with Minimal Assumptions and Costs (2010, background): “…linguistics in areas of inquiry with similar structural needs: categorization of massive text collections by subject, with minimal assumptions about the underlying categories, and with minimal costs (Blei et al., 2003; Blei and Lafferty, 2006, 2007; Wang and McCallum, 2006; Gruber and Weiss, 2007).”
An Explanation of In-context Learning as Implicit Bayesian Inference (2021, unknown): “…conditional distribution of completions During pretraining, the language model (LM) implicitly learns to infer a latent concept (e.g., wiki bios, which typically transition between name (Albert Einstein) → nationality (German) → occupation (physicist) → ...) shared across sentences in a…”
Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships (2016, methodology): “We turn instead to the hidden topic Markov model (Gruber et al., 2007, HTMM ), which foregoes the bag-of-words assumption of LDA and NUBBI in favor of modeling topic segments within a document as a Markov chain.”
Sentence-Based Text Analysis for Customer Reviews (2016, background): “• Incorporating a dynamic topic structure by modelling documents from di↵erent periods (Blei and La↵erty, 2006) or assuming that topic assignments are conditional on the previous word (Wallach, 2006) or topic (Gruber et al., 2007).”
Probabilistic Frame Induction (2013, methodology): “The modeling component for frame and event transitions in ProFinder is similar to a sequential topic model (Gruber et al., 2007), and is inspired by the successful applications of such topic models in summarization (Barzilay and Lee, 2004; Daum´e III and Marcu, 2006; Haghighi and Vander-wende,…”
A biterm topic model for short texts (2013, background): “Similar approach can be found in [12], where words in each sentence are assumed to be drawn from the same topic.”
MedLDA: maximum margin supervised topic models (2012, result): “Here, we also compare with the hidden topic Markov model (HTMM) (Gruber et al., 2007), which assumes the words in the same sentence have the same topic assignment.”
Neural Net Models for Open-Domain Discourse Coherence (2016, methodology): “in Fig.1b), in which an HMM-LDA model provides the SEQ2SEQ model with global information for token generation, with two components: (1) Running HMM-LDA: we ﬁrst run a sentence-level HMM-LDA similar toGruber et al. (2007). Our implementation forces all words in a sentence to be generated from the sam”
Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels (2017, background): “They show that their deep model learns better representations than conceptually similar topic models (Gruber et al., 2007; Chang et al., 2009).”
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning (2021, unknown): “The memory-augmented HMM, depicted in Figure 2, can be viewed as a generative variant of memory networks [39, 33] and is closely related to Hidden Topic Markov Models [8].”
Modeling online reviews with multi-grain topic models (2008, methodology): “This problem can be addressed by explicitly modeling topic transitions [5, 15, 33, 32, 28, 16], but these topic n-gram models are considerably more computationally expensive.”
Interactive Topic Modeling (2011, background): “When presented with poor topics learned from data, users can offer a number of complaints:2 these documents should have similar topics but don’t (Daumé III, 2009); this topic should have syntactic coherence (Gruber et al., 2007; Boyd-Graber and Blei, 2008); this topic doesn’t make any sense at all (”
BTM: Topic Modeling over Short Texts (2014, background): “Index Terms—Short text, topic model, biterm, online algorithm, content analysis Ç”
A Joint Model of Text and Aspect Ratings for Sentiment Summarization (2008, methodology): “These simple techniques are capable of modeling local topics without more expensive modeling of topic transitions used in (Grif-ﬁths et al., 2004; Wang and McCallum, 2005; Wal-lach, 2006; Gruber et al., 2007).”
Syntactic Topic Models (2008, background): “Other techniques have attempted to combine local context with document coherence using linear sequence models [8, 9].”
Modeling the Detection of Textual Cyberbullying (2011, methodology): “Topic modeling techniques from Latent Dirichlet Allocation [16] (LDA) to Hidden Topic Markov Models (HTMM) [17] have been used in applications pertaining to information retrieval.”