An empirical investigation of sparse log-linear models for improved dialogue act classification

By Yun-Nung (Vivian) Chen, William Yang Wang, Alexander I. Rudnicky. 2013

19 citations recorded by the source corpus.

Previous work on dialogue act classification have primarily focused on dense generative and discriminative models. However, since the automatic speech recognition (ASR) outputs are often noisy, dense models might generate biased estimates and overfit to the training data. In this paper, we study sparse modeling approaches to improve dialogue act classification, since the sparse models maintain a compact feature space, which is robust to noise. To test this, we investigate various element-wise frequentist shrinkage models such as lasso, ridge, and elastic net, as well as structured sparsity models and a hierarchical sparsity model that embed the dependency structure and interaction among local features. In our experiments on a real-world dataset, when augmenting N-best word and phone level ASR hypotheses with confusion network features, our best sparse log-linear model obtains a relative improvement of 19.7% over a rule-based baseline, a 3.7% significant improvement over a traditional non-sparse log-linear model, and outperforms a state-of-the-art SVM model by 2.2%.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Diversity-Promoting Objective Function for Neural Conversation Models (2015, background): “…heuristic-driven even where there is a statistical component (Levin et al., 2000; Oh and Rudnicky, 2000; Ratna-parkhi, 2002; Walker et al., 2003; Pieraccini et al., 2009; Young et al., 2010; Wang et al., 2011; Banchs and Li, 2012; Chen et al., 2013; Ameixa et al., 2014; Nio et al., 2014).”
A Persona-Based Neural Conversation Model (2016, background): “, 2011) or learning generation rules from a minimal set of authored rules or labels (Oh and Rudnicky, 2000; Ratnaparkhi, 2002; Banchs and Li, 2012; Ameixa et al., 2014; Nio et al., 2014; Chen et al., 2013).”
Word-Based Dialog State Tracking with Recurrent Neural Networks (2014, background): “The state-of-the-art in dialog act classification with very similar data also uses sparse weights Chen et al. (2013). on the slot).”
Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts (2018, methodology): “Popular approaches for dialogue act classiﬁcation include support vector machine (SVM) [29], Naive Bayes [26, 30, 31], logistic regression [32], and recur-a”
Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection (2016, background): “Dialogue act (DA) detection [15–17] is about categorizing the intention behind the speaker’s move in conversations, and recognition of a speaker’s act may help reason the entire dialogue.”