A Bi-Encoder LSTM Model For Learning Unstructured Dialogs
@article{Shekhar2021ABL,
title={A Bi-Encoder LSTM Model For Learning Unstructured Dialogs},
author={Diwanshu Shekhar and Pooran Singh Negi and Mohammad H. Mahoor},
journal={ArXiv},
year={2021},
volume={abs/2104.12269}
}Creating a data-driven model that is trained on a large dataset of unstructured dialogs is a crucial step in developing a Retrieval-based Chatbot systems. [] Key Result We also show results on experiments performed by using several similarity functions, model hyper-parameters and word embeddings on the proposed architecture.
Figures and Tables from this paper
figure 1.1 
table 1.1 
figure 1.10 
figure 1.11 
figure 1.2 
figure 1.3 
figure 1.4 
figure 1.5 
figure 1.6 
figure 1.8 
figure 1.9 
figure 2.1 
table 2.1 
figure 2.2 
table 2.2 
figure 3.1 
table 3.1 
figure 3.2 
table 3.2 
figure 3.3 
table 3.3 
figure 3.4 
table 3.4 
figure 3.5 
table 3.5 
figure 3.6 
table 3.6 
figure 3.7 
table 3.7 
table A.1 
table B.1 
table C.1
References
SHOWING 1-10 OF 55 REFERENCES
The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems
- Computer ScienceSIGDIAL Conference
- 2015
This paper introduces the Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This provides a unique…
A Dataset for Research on Short-Text Conversations
- Computer ScienceEMNLP
- 2013
This paper introduces a dataset of short-text conversation based on the real-world instances from Sina Weibo, which provides rich collection of instances for the research on finding natural and relevant short responses to a given short text, and useful for both training and testing of conversation models.
Improved Deep Learning Baselines for Ubuntu Corpus Dialogs
- Computer ScienceArXiv
- 2015
An in-house implementation of previously reported models are used to do an independent evaluation and an ensemble is created by averaging predictions of multiple models to achieve a state-of-the-art result for the next utterance ranking on the Ubuntu Dialog Corpus.
Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus
- Computer ScienceDialogue Discourse
- 2017
In this paper, we construct and train end-to-end neural network-based dialogue systems using an updated version of the recent Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn…
DocChat: An Information Retrieval Approach for Chatbot Engines Using Unstructured Documents
- Computer ScienceACL
- 2016
This paper presents DocChat, a novel information retrieval approach for chatbot engines that can leverage unstructured documents, instead of Q-R pairs, to respond to utterances.
Filter, Rank, and Transfer the Knowledge: Learning to Chat
- Computer Science
- 2010
A three phase ranking approach for predicting suitable responses to a query in a conversation is used, and sentences are first filtered, then efficiently ranked, and then more precisely re-ranked in order to select the most suitable response.
Sequence to Sequence Learning with Neural Networks
- Computer ScienceNIPS
- 2014
This paper presents a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure, and finds that reversing the order of the words in all source sentences improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
- Computer ScienceEMNLP
- 2015
A statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure that can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates.
A unified architecture for natural language processing: deep neural networks with multitask learning
- Computer ScienceICML '08
- 2008
We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semantic…
A Survey of Available Corpora for Building Data-Driven Dialogue Systems
- Computer ScienceDialogue Discourse
- 2018
A wide survey of publicly available datasets suitable for data-driven learning of dialogue systems is carried out and important characteristics of these datasets are discussed and how they can be used to learn diverse dialogue strategies.