paper-with-me

홈 › Papers

A Hierarchical Neural Model for Learning Sequences of Dialogue Acts

2017-04-01 · EACL 2017 4 · Quan Hung Tran, Ingrid Zukerman, Gholamreza Haffari

We propose a novel hierarchical Recurrent Neural Network (RNN) for learning sequences of Dialogue Acts (DAs). The input in this task is a sequence of utterances (i.e., conversational contributions) comprising a sequence of tokens, and the output is a sequence of DA labels (one label per utterance). Our model leverages the hierarchical nature of dialogue data by using two nested RNNs that capture long-range dependencies at the dialogue level and the utterance level. This model is combined with an attention mechanism that focuses on salient tokens in utterances. Our experimental results show that our model outperforms strong baselines on two popular datasets, Switchboard and MapTask; and our detailed empirical analysis highlights the impact of each aspect of our model.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech Recognition (ASR)Machine TranslationPart-Of-Speech TaggingSpeech Recognition

Similar Papers 제목 키워드 기반

User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational Systems

2022-02-07 · Yang Deng, Wenxuan Zhang, Wai Lam, Hong Cheng 외

User Satisfaction Estimation (USE) is an important yet challenging task in goal-oriented conversational systems. Whether the user is satisfied with the system largely depends on the fulfillment of the user's needs, which…

Beyond Adjacency Pairs: Hierarchical Clustering of Long Sequences for Human-Machine Dialogues

2020-11-01 · EMNLP (CODI) 2020 11 · Maitreyee Maitreyee

This work proposes a framework to predict sequences in dialogues, using turn based syntactic features and dialogue control functions. Syntactic features were extracted using dependency parsing, while dialogue control fun…

ClusteringDependency Parsingfeature selectionWord Embeddings

Dialogue-act-driven Conversation Model : An Experimental Study

2018-08-01 · COLING 2018 8 · Harshit Kumar, Arvind Agarwal, Sachindra Joshi

The utility of additional semantic information for the task of next utterance selection in an automated dialogue system is the focus of study in this paper. In particular, we show that additional information available in…

DecoderDialogue GenerationmodelText Generation

Dialogue Act Sequence Labeling using Hierarchical encoder with CRF

2017-09-13 · Harshit Kumar, Arvind Agarwal, Riddhiman Dasgupta, Sachindra Joshi 외

Dialogue Act recognition associate dialogue acts (i.e., semantic labels) to utterances in a conversation. The problem of associating semantic labels to utterances can be treated as a sequence labeling problem. In this wo…

Dialogue Act Classification

Modeling Dialogue Acts with Content Word Filtering and Speaker Preferences

2017-09-01 · EMNLP 2017 9 · Yohan Jo, Michael Yoder, Hyeju Jang, Carolyn Ros{\'e}

We present an unsupervised model of dialogue act sequences in conversation. By modeling topical themes as transitioning more slowly than dialogue acts in conversation, our model de-emphasizes content-related words in ord…

Language ModelingLanguage Modelling