Recurrent Convolutional Neural Networks for Discourse Compositionality

The compositionality of meaning extends beyond the single sentence. Just as words combine to form the meaning of sentences, so do sentences combine to form the meaning of paragraphs, dialogues and general discourse. We introduce both a sentence model and a discourse model corresponding to the two levels of compositionality. The sentence model adopts convolution as the central operation for composing semantic vectors and is based on a novel hierarchical convolutional neural network. The discourse model extends the sentence model and is based on a recurrent neural network that is conditioned in a novel way both on the current sentence and on the current speaker. The discourse model is able to capture both the sequentiality of sentences and the interaction between different speakers. Without feature engineering or pretraining and with simple greedy decoding, the discourse model coupled to the sentence model obtains state of the art performance on a dialogue act classification experiment.

• Publication year

  2013

• Venue

  CVSM@ACL

• Publication date

  2013-06-15

• Fields of study

  Computer Science

• Identifiers
  arXiv 1306.3584
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The Role of Syntax in Vector Space Models of Compositional Semantics

  2013cited by this paper
• Cutting Recursive Autoencoder Trees

  2013cited by this paper
• The Stanford Encyclopedia of Philosophy

  2013cited by this paper
• Baselines and Bigrams: Simple, Good Sentiment and Topic Classification

  2012cited by this paper
• Semantic Compositionality through Recursive Matrix-Vector Spaces

  2012cited by this paper
• A belief tracking challenge task for spoken dialog systems

  2012cited by this paper
• A Comparison of Vector-based Representations for Semantic Composition

  2012cited by this paper
• Generating Text with Recurrent Neural Networks

  2011cited by this paper
• Concrete Sentence Spaces for Compositional Distributional Models of Meaning

  2010cited by this paper
• Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space

  2010cited by this paper
• From Frequency to Meaning: Vector Space Models of Semantics

  2010cited by this paper
• Recurrent neural network based language model

  2010cited by this paper
• Composition in Distributional Models of Semantics

  2010cited by this paper
• The NXT-format Switchboard Corpus: a rich resource for investigating the syntax, semantics, pragmatics and prosody of dialogue

  2010cited by this paper
• How to Do Things With Words

  2009cited by this paper
• How to Do Things with Words之脉络分析

  2009cited by this paper
• A unified architecture for natural language processing: deep neural networks with multitask learning

  2008cited by this paper
• Generating query substitutions

  2006cited by this paper
• Pragmatics

  2006cited by this paper
• Stanford Encyclopedia of Philosophy: a dynamic reference work

  2003cited by this paper
• The Oxford handbook of computational linguistics

  2003cited by this paper
• The Oxford Handbook of Computational Linguistics

  2003cited by this paper
• Dialogue act modeling for automatic tagging and recognition of conversational speech

  2000cited by this paper
• Dialog Act Modeling for Automatic Tagging and Recognition of Conversational Speech

  2000influential reference
• Gradient-based learning applied to document recognition

  1998cited by this paper
• Learning internal representations by error propagation

  1986cited by this paper
• How to do things with words

  1962cited by this paper
• Über Sinn und Bedeutung

  year unknowncited by this paper

• Text classification using SVD, BERT, and GRU optimized by improved Seagull optimization (ISO) algorithm

  2025cites this paper
• Comparative study of low resource Digaru language using SMT and NMT

  2024cites this paper
• Optimal Kernel Tuning Parameter Prediction using Deep Sequence Models

  2024cites this paper
• Research on dialogue mode recognition in meeting scenes

  2024cites this paper
• Cinnalyst: A Sales Meeting Analysis System

  2023cites this paper
• Deep Learning for Natural Language Processing: A Survey

  2023cites this paper
• A Comprehensive Review of Sign Language Translation Technologies Using Linguistic Approaches

  2023cites this paper
• HAG: Hierarchical Attention with Graph Network for Dialogue Act Classification in Conversation

  2023cites this paper
• Chaos to Clarity with Semantic Inferencing for Python Source Code Snippets

  2023cites this paper
• Improving Classroom Dialogue Act Recognition from Limited Labeled Data with Self-Supervised Contrastive Learning Classifiers

  2023cites this paper
• Supervised Contrastive Learned Deep Model for Question Continuation Evaluation

  2023cites this paper
• Role of Context in Unsupervised Sentence Representation Learning: the Case of Dialog Act Modeling

  2023cites this paper
• Multimodal Deep Learning Crime Prediction Using Tweets

  2023cites this paper
• Implicit n-grams Induced by Recurrence

  2022cites this paper
• Can we learn from developer mistakes? Learning to localize and repair real bugs from real bug fixes

  2022cites this paper
• Sentence Ambiguity, Grammaticality and Complexity Probes

  2022cites this paper
• Dialog Acts for Task Driven Embodied Agents

  2022cites this paper
• Imbalanced Traffic Accident Text Classification Based on Bert-RCNN

  2022cites this paper
• A Universality-Individuality Integration Model for Dialog Act Classification

  2022influential citation
• Automatic Recognition of the General-Purpose Communicative Functions Defined by the ISO 24617-2 Standard for Dialog Act Annotation

  2022cites this paper
• Unsupervised English Intelligent Machine Translation in Wireless Network Environment

  2022cites this paper
• Research on the Construction of a Bidirectional Neural Network Machine Translation Model Fused with Attention Mechanism

  2022cites this paper
• Neural Natural Language Generation: A Survey on Multilinguality, Multimodality, Controllability and Learning

  2022cites this paper
• Supervised Classification of Healthcare Text Data Based on Context-Defined Categories

  2022cites this paper
• User intent classification in noisy texts: an investigation on neural language models

  2022cites this paper
• Algorithm metadata vocabulary: A representational model and metadata vocabulary for describing and maintaining algorithms

  2022cites this paper
• Rare-Class Dialogue Act Tagging for Alzheimer’s Disease Diagnosis

  2021cites this paper
• A ConvBiLSTM Deep Learning Model-Based Approach for Twitter Sentiment Classification

  2021cites this paper
• Sentence encoding for Dialogue Act classification

  2021influential citation
• Dialogue Act Recognition using Branch Architecture with Attention Mechanism for Imbalanced Data

  2021cites this paper
• A Neural Question Answering System for Basic Questions about Subroutines

  2021cites this paper
• Contrastive Word Embedding Learning for Neural Machine Translation

  2021cites this paper
• Text Classification Based on Convolutional Neural Networks and Word Embedding for Low-Resource Languages: Tigrinya

  2021cites this paper
• Large-scale text pre-training helps with dialogue act recognition, but not without fine-tuning

  2021cites this paper
• BERT-Caps: A Transformer-Based Capsule Network for Tweet Act Classification

  2020cites this paper
• Information Seeking in the Spirit of Learning: A Dataset for Conversational Curiosity

  2020cites this paper
• If Beam Search Is the Answer, What Was the Question?

  2020cites this paper
• Intention Detection Based on Siamese Neural Network With Triplet Loss

  2020cites this paper
• Speaker-change Aware CRF for Dialogue Act Classification

  2020cites this paper
• A Deep Multi-task Model for Dialogue Act Classification, Intent Detection and Slot Filling

  2020cites this paper
• Solving Sequential Text Classification as Board-Game Playing

  2020cites this paper
• Addressing Posterior Collapse with Mutual Information for Improved Variational Neural Machine Translation

  2020cites this paper
• DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification

  2020cites this paper
• Towards Emotion-aided Multi-modal Dialogue Act Classification

  2020cites this paper
• General-Purpose Communicative Function Recognition using a Hierarchical Network with Cascading Outputs and Maximum a Posteriori Path Estimation

  2020cites this paper
• Would you Like to Talk about Sports Now?: Towards Contextual Topic Suggestion for Open-Domain Conversational Agents

  2020cites this paper
• A Novel Recurrent Convolutional Neural Network-Based Estimation Method for Switching Guidance Law

  2020cites this paper
• A new method of emotional analysis based on CNN–BiLSTM hybrid neural network

  2020cites this paper
• Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition

  2020cites this paper
• TMUDS at the NTCIR-15 DialEval-1 Task

  2020cites this paper
• On the effects of using word2vec representations in neural networks for dialogue act recognition

  2020influential citation
• A novel LMAEB-CNN model for Chinese microblog sentiment analysis

  2020cites this paper
• Two-level classification for dialogue act recognition in task-oriented dialogues

  2020cites this paper
• Findings of the LoResMT 2020 Shared Task on Zero-Shot for Low-Resource languages

  2020influential citation
• Summarizing Medical Conversations via Identifying Important Utterances

  2020cites this paper
• Conversation Management in Task-oriented Turkish Dialogue Agents with Dialogue Act Classification

  2020cites this paper
• Intent Detection Problem Solving via Automatic DNN Hyperparameter Optimization

  2020cites this paper
• Development of Kazakh Named Entity Recognition Models

  2020cites this paper
• A Transformer based Approach for Identification of Tweet Acts

  2020cites this paper
• Building A User-Centric and Content-Driven Socialbot

  2020cites this paper
• Dialogue Act Classification for Virtual Agents for Software Engineers during Debugging

  2020cites this paper
• Emotion Aided Dialogue Act Classification for Task-Independent Conversations in a Multi-modal Framework

  2020cites this paper
• Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions

  2020cites this paper
• Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification

  2020cites this paper
• Deep Neural Models and Retrofitting for Arabic Text Categorization

  2020cites this paper
• Modeling Long-Range Context for Concurrent Dialogue Acts Recognition

  2019cites this paper
• Hierarchical Recurrent and Convolutional Neural Network Based on Attention for Chinese Document Classification

  2019influential citation
• Modeling Long-Range Context for Concurrent Dialogue Acts Recognition

  2019cites this paper
• Leveraging Contextual Sentences for Text Classification by Using a Neural Attention Model

  2019cites this paper
• Neural Machine Translation for Indian Languages

  2019cites this paper
• A Deep Learning-Based Approach for Measuring the Domain Similarity of Persian Texts

  2019cites this paper
• Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations

  2019cites this paper
• Hierarchical Multi-Label Dialog Act Recognition on Spanish Data

  2019cites this paper
• Spanish-Swedish neural machine translation for the civil engineering domain

  2019cites this paper
• Neural Networks for Text Classification

  2019cites this paper
• Text classification with deep neural networks

  2019cites this paper
• Weakly supervised sentiment analysis and opinion extraction

  2019cites this paper
• Dialogue Act Classification in Group Chats with DAG-LSTMs

  2019cites this paper
• Dialog Acts Classification with Semantic and Structural Information

  2019cites this paper
• English-Bhojpuri SMT System: Insights from the Karaka Model

  2019cites this paper
• MoonGrad at SemEval-2019 Task 3: Ensemble BiRNNs for Contextual Emotion Detection in Dialogues

  2019cites this paper
• A Dynamic Speaker Model for Conversational Interactions

  2019influential citation
• Short Text Conversation Based on Deep Neural Network and Analysis on Evaluation Measures

  2019cites this paper
• English-Bhojpuri SMT System: Insights from the Karaka Model

  2019cites this paper
• Ensemble Sentiment Analysis Method based on R-CNN and C-RNN with Fusion Gate

  2019cites this paper
• Compositional representations of language structures in multilingual joint-vector space

  2019cites this paper
• Dialogue Act Classification with Context-Aware Self-Attention

  2019influential citation
• Dialogue-Act Prediction of Future Responses Based on Conversation History

  2019cites this paper
• Rubrication and Analysis Based on Fuzzy Relations of Difference between Their Syntactical Characteristics

  2019cites this paper
• Automated extraction of attributes from natural language attribute-based access control (ABAC) Policies

  2019cites this paper
• A survey of word embeddings based on deep learning

  2019cites this paper
• A Multilingual and Multidomain Study on Dialog Act Recognition Using Character-Level Tokenization

  2019cites this paper
• Modeling Long-Range Context for Concurrent Dialogue Acts Recognition

  2019cites this paper
• Low Data Dialogue Act Classification for Virtual Agents during Debugging

  2019cites this paper
• Joint dialog act segmentation and recognition in human conversations using attention to dialog context

  2019cites this paper
• Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions

  2019cites this paper
• A Novel Semantic Inference Model With a Hierarchical Act Labels Embedded for Dialogue Act Recognition

  2019cites this paper
• Contextualized Representations for Low-resource Utterance Tagging

  2019cites this paper
• Conceptual Representations for Computational Concept Creation

  2019cites this paper
• TextNAS: A Neural Architecture Search Space tailored for Text Representation

  2019influential citation