• Corpus ID: 209071986

AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue

  title={AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue},
  author={Gaurav Kumar and Rishabh Joshi and Jaspreet Singh and Promod Yenigalla},
The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic and contextual information for a given query and fail to completely account for syntactic and external knowledge which are crucial for generating responses in a chit-chat system. To overcome this problem, we propose an end to end multi-stream deep learning architecture that learns unified embeddings for… 

Figures and Tables from this paper

CASA: Conversational Aspect Sentiment Analysis for Dialogue Understanding

The task of conversational aspect sentiment analysis (CASA) is introduced that can provide useful fine-grained sentiment information for dialogue understanding and planning and extends the standard aspect-based sentiment analysis to the conversational scenario with several major adaptations.

Dialogue Context Encoder Structure Encoder Graph Encoding ( GAT ) Structure Encoder u 1 u 2 u 3 u 4 Graph Pooling Graph Pooling Graph Encoding ( GAT ) GCN-ASAPGCN-ASAP Utterance Embedding Utterance Generation

DIALOGRAPH is presented, a negotiation system that incorporates pragmatic strategies in a negotiation dialogue using graph neural networks and qualitatively shows further benefits of learned strategy-graphs in providing explicit associations between effective negotiation strategies over the course of the dialogue, leading to interpretable and strategic dialogues.

ResPer: Computationally Modelling Resisting Strategies in Persuasive Conversations

This work proposes a generalised framework for identifying resisting strategies in persuasive conversations and instantiates this framework on two distinct datasets comprising persuasion and negotiation conversations, using a hierarchical sequence-labelling neural architecture to infer the aforementioned resisting strategies automatically.

Keeping up Appearances: Computational Modeling of Face Acts in Persuasion Oriented Discussions

A generalized framework for modeling face acts in persuasion conversations is proposed, resulting in a reliable coding manual, an annotated corpus, and computational models that reveal insights about differences in face act utilization between asymmetric roles in persuasion conversation.

LTIatCMU at SemEval-2020 Task 11: Incorporating Multi-Level Features for Multi-Granular Propaganda Span Identification

A BERT-BiLSTM based span-level propaganda classification model that identifies which token spans within the sentence are indicative of propaganda, which is a majority-voting ensemble which learns different propaganda class boundaries by leveraging different subsets of incorporated knowledge.



Multi-turn Dialogue Response Generation in an Adversarial Learning Framework

The hredGAN shows improved performance over existing methods: (1) it generalizes better than networks trained using only the log-likelihood criterion, and (2) it generates longer, more informative and more diverse responses with high utterance and topic relevance even with limited training data.

A Neural Conversational Model

A simple approach to conversational modeling which uses the recently proposed sequence to sequence framework, and is able to extract knowledge from both a domain specific dataset, and from a large, noisy, and general domain dataset of movie subtitles.

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation

A new class of models called multiresolution recurrent neural networks, which explicitly model natural language generation at multiple levels of abstraction, are introduced, which outperform competing models by a substantial margin and generate more fluent, relevant and goal-oriented responses.

Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots

A sequential matching network (SMN) first matches a response with each utterance in the context on multiple levels of granularity, and distills important matching information from each pair as a vector with convolution and pooling operations.

End-to-End Reinforcement Learning of Dialogue Agents for Information Access

This paper proposes KB-InfoBot - a multi-turn dialogue agent which helps users search Knowledge Bases without composing complicated queries by replacing symbolic queries with an induced “soft” posterior distribution over the KB that indicates which entities the user is interested in.

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

A version of graph convolutional networks (GCNs), a recent class of neural networks operating on graphs, suited to model syntactic dependency graphs, is proposed, observing that GCN layers are complementary to LSTM ones.

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

A neural network-based generative architecture, with stochastic latent variables that span a variable number of time steps, that improves upon recently proposed models and that the latent variables facilitate both the generation of meaningful, long and diverse responses and maintaining dialogue state is proposed.

AirDialogue: An Environment for Goal-Oriented Dialogue Research

AirDialogue is presented, a large dataset that contains 301,427 goal-oriented conversations and its experimental results indicate that state-of-the-art dialogue models can only achieve a score of 0.17 while humans can reach a scoreOf 0.91, which suggests significant opportunities for future improvement.

A Network-based End-to-End Trainable Task-oriented Dialogue System

This work introduces a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework that can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

A benchmark of nine diverse NLU tasks, an auxiliary dataset for probing models for understanding of specific linguistic phenomena, and an online platform for evaluating and comparing models, which favors models that can represent linguistic knowledge in a way that facilitates sample-efficient learning and effective knowledge-transfer across tasks.