Modeling Long-Range Context for Concurrent Dialogue Acts Recognition

Abstract

In dialogues, an utterance is a chain of consecutive sentences produced by one speaker which ranges from a short sentence to a thousand-word post. When studying dialogues at the utterance level, it is not uncommon that an utterance would serve multiple functions. For instance, "Thank you. It works great. " expresses both gratitude and positive feedback in the same utterance. Multiple dialogue acts (DA) for one utterance breeds complex dependencies across dialogue turns. Therefore, DA recognition challenges a model's predictive power over long utterances and complex DA context. We term this problem Concurrent Dialogue Acts (CDA) recognition. Previous work on DA recognition either assumes one DA per utterance or fails to realize the sequential nature of dialogues. In this paper, we present an adapted Convolutional Recurrent Neural Network (CRNN) which models the interactions between utterances of long-range context. Our model significantly outperforms existing work on CDA recognition on a tech forum dataset.

Towards Emotion-aided Multi-modal Dialogue Act Classification

“…Source distribution and major speakers statistics of the dataset are shown in Figures 3a and 3b, respectively. Since DAC and ER tasks are known to exploit the contextual features, i.e., dialogue history (Yu et al, 2019) so, utterances in the dataset are accompanied with their corresponding contextual utterances, which are typically preceding dialogue turns by the speakers participating in the dialogue. Each of the utterances contains three modalities: video, audio, and text.…”

“…A contextual self-attention system fused with hierarchical recurrent units was proposed by the authors of (Raheja and Tetreault, 2019) to develop a sequence label classifier. The authors of (Yu et al, 2019) proposed a method for the capture of long-range interactions that span a series of words using a Convolutional Network based approach. In (Saha et al, 2019), authors proposed several ML and DL based approaches such as Conditional Random Fields, clustering and word embeddings to identify DAs.…”

Integrating User History into Heterogeneous Graph for Dialogue Act Recognition

“…In our experiments, we split training/validation/testing datasets following Yu et al (2019) for MSDialog and Lee and Dernoncourt (2016) for MRDA. For two datasets, we first strip punctuation, and then we convert the characters into lower-case and tokenize the texts with NLTK 1 .…”

“…4) GA-Seq (Colombo et al, 2020) leverages a sequence to sequence approach to improving the modeling of tag sequentiality. 5) CRNN (Yu et al, 2019) is an adapted Convolutional Recurrent Neural Network (CRNN) that models the interactions between utterances of long-range context. 6) Di-alogueGCN (Ghosal et al, 2019) proposes a graph-based model that leverages self and inter-speaker interaction of the interlocutors to model conversational context for emotion recognition.…”

“…We encode utterance through BERT alongwith a feedforward network for classification. (Kumar et al, 2018) 63.8 69.5 67.3 67.5 CNN-CR (Qu et al, 2019) 63.5 † 70.3 † 67.6 67.4 CASA (Raheja and Tetreault, 2019) 66.4 72.1 67.9 68.2 GA-Seq (Colombo et al, 2020) 66.4 72.4 68.5 68.9 CRNN (Yu et al, 2019) 68.2 † 73.4 † 68.4 68.5 DialogueGCN (Ghosal et al, 2019) 68.5 73.9 68.5 68.9 BERT (Devlin et al, 2019) 70…”