Deep Active Learning for Dialogue Generation

Asghar, Nabiha; Poupart, Pascal; Jiang, Xin; Li, Hang

doi:10.18653/v1/s17-1008

Cited by 40 publications

(31 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, 2014). We experimented with various beam sizes (Graves, 2012), but greedy decoding performed better according to all metrics, also observed previously (Asghar et al, 2017;Shao et al, 2017;Tandon et al, 2017).…”

Section: Datasetsupporting

confidence: 59%

Improving Neural Conversational Models with Entropy-Based Data Filtering

Csáky¹,

Purgai²,

Recski³

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances. Priors such as persona, emotion, or topic provide additional information to dialog models to aid response generation, but annotating a dataset with priors is expensive and such annotations are rarely available. While previous methods for improving the quality of open-domain response generation focused on either the underlying model or the training objective, we present a method of filtering dialog datasets by removing generic utterances from training data using a simple entropy-based approach that does not require human supervision. We conduct extensive experiments with different variations of our method, and compare dialog models across 17 evaluation metrics to show that training on datasets filtered this way results in better conversational quality as chatbots learn to output more diverse responses.

show abstract

Section: Datasetsupporting

confidence: 59%

Improving Neural Conversational Models with Entropy-Based Data Filtering

Csáky¹,

Purgai²,

Recski³

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…As opposed to offline learning, [87] proposed an interactive based reinforcement learning mechanism whereby for each answer generated by the model, user feedback is obtained and feedback to the model to update model param based on single question-answer pair. This method of updating model parameters based on a single example is called one-shot learning [88].…”

Section: ) Deep Reinforcement Learning (Drl)mentioning

confidence: 99%

Enhancements to the Sequence-to-Sequence-Based Natural Answer Generation Models

et al. 2020

View full text Add to dashboard Cite

There is a great interest shown by academic researchers to continuously improve the sequence-to-sequence (Seq2Seq) model for natural answer generation (NAG) in chatbots. The Seq2Seq model shows a weakness whereby the model tends to generate answers that are generic, meaningless and inconsistent with the questions. However, a comprehensive literature review on the factors contributing to the weakness and potential solutions are still missing. Therefore, this review article fills the gap by reviewing Seq2Seq based natural answer generation-based literature to identify those factors and proposed methods to address the weakness. This literature review identified several factors such as input question is not sufficient to determine a meaningful output, usage of cross-entropy function as the loss function during training, infrequent words in training data, language model influence which generates answers not relevant to the question, utilization of teacher forcing method during training which results in exposure bias, long sentences and inability to consider dialogue history as the factors. Additionally, this literature review also identified and reviewed the methods proposed to address the weakness such as utilizing additional embedding and encoders, using different loss functions and training approaches, as well as utilizing other mechanisms like copying source word(s) and paying attention to a certain portion of the input. For discussion, these methods are categorized into four broad categories which are Structural Modifications, Augmented Learning, Beam Search and Complementary Mechanisms. Additionally, the paper highlights unexplored areas in Seq2Seq modeling and proposes potential future works for natural answer generation. INDEX TERMS Seq2Seq, natural answer generation, natural language processing, dialogue generation, chatbot.

show abstract

“…Several heuristic criteria are proposed in (Li et al, 2016a,b) as objectives to optimize. Asghar et al (2017) proposes humans-in-the-loop to select the best response out of a few generated candidates. Cheng et al (2018) uses an additional input signal -the specificity level of a response, which is estimated by certain heuristics at training time and can be varied during evaluation.…”

Section: Related Workmentioning

confidence: 99%

Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner

Zemlyanskiy

Sha

2018

Proceedings of the 22nd Conference on Computational Natural Language Learning

View full text Add to dashboard Cite

There have been several attempts to define a plausible motivation for a chit-chat dialogue agent that can lead to engaging conversations. In this work, we explore a new direction where the agent specifically focuses on discovering information about its interlocutor. We formalize this approach by defining a quantitative metric. We propose an algorithm for the agent to maximize it. We validate the idea with human evaluation where our system outperforms various baselines. We demonstrate that the metric indeed correlates with the human judgments of engagingness.

show abstract

Deep Active Learning for Dialogue Generation

Cited by 40 publications

References 23 publications

Improving Neural Conversational Models with Entropy-Based Data Filtering

Improving Neural Conversational Models with Entropy-Based Data Filtering

Enhancements to the Sequence-to-Sequence-Based Natural Answer Generation Models

Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner

Contact Info

Product

Resources

About