Incorporating Loose-Structured Knowledge into Conversation Modeling via Recall-Gate LSTM

Xu, Zhen; Liu, Bingquan; Wang, Baoxun; Sun, Chengjie; Wang, Xiaolong

doi:10.48550/arxiv.1605.05110

Cited by 11 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, some researchers have gone beyond matching textual objects by leveraging external knowledge to enhance the ranking performance. These research works can be grouped into two categories: 1) learning with external structured knowledge such as knowledge bases [133,29,134,135,136,137]; 2) learning with external unstructured knowledge such as retrieved top results, topics or tags [30,138,139]. We now briefly review this work.…”

Section: Learning With External Knowledgementioning

confidence: 99%

A Deep Look into neural ranking models for information retrieval

Guo

Fan

Pang

et al. 2020

Information Processing & Management

236

147

View full text Add to dashboard Cite

Ranking models lie at the heart of research on information retrieval (IR). During the past decades, different techniques have been proposed for constructing ranking models, from traditional heuristic methods, probabilistic methods, to modern machine learning methods. Recently, with the advance of deep learning technology, we have witnessed a growing body of work in applying shallow or deep neural networks to the ranking problem in IR, referred to as neural ranking models in this paper. The power of neural ranking models lies in the ability to learn from the raw text inputs for the ranking problem to avoid many limitations of hand-crafted features. Neural networks have sufficient capacity to model complicated tasks, which is needed to handle the complexity of relevance estimation in ranking. Since there have been a large variety of neural ranking models proposed, we believe it is the right time to summarize the current status, learn from existing methodologies, and gain some insights for future development. In contrast to existing reviews, in this survey, we will take a deep look into the neural ranking models from different dimensions to analyze their underlying assumptions, major design principles, and learning strategies. We compare these models through benchmark tasks to obtain a comprehensive empirical understanding of the existing techniques. We will also discuss what is missing in the current literature and what are the promising and desired future directions.

show abstract

Section: Learning With External Knowledgementioning

confidence: 99%

A Deep Look into neural ranking models for information retrieval

Guo

Fan

Pang

et al. 2020

Information Processing & Management

236

147

View full text Add to dashboard Cite

show abstract

“…Open domain dialogue generation (Ritter et al, 2011;Sordoni et al, 2015;Xu et al, 2016;Li et al, 2016b;Serban et al, 2016c aims at generating meaningful and coherent dialogue responses given the dialogue history. Prior systems, e.g., phrase-based machine translation systems (Ritter et al, 2011;Sordoni et al, 2015) or end-to-end neural systems (Shang et al, 2015;Vinyals and Le, 2015;Li et al, 2016a;Yao et al, 2015;Luan et al, 2016) approximate such a goal by predicting the next dialogue utterance given the dialogue history using the maximum likelihood estimation (MLE) objective.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Learning for Neural Dialogue Generation

Li¹,

Monroe²,

Shi³

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

704

523

View full text Add to dashboard Cite

In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning (RL) problem where we jointly train two systems, a generative model to produce response sequences, and a discriminator-analagous to the human evaluator in the Turing test-to distinguish between the human-generated dialogues and the machine-generated ones. The outputs from the discriminator are then used as rewards for the generative model, pushing the system to generate dialogues that mostly resemble human dialogues.In addition to adversarial training we describe a model for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls. Experimental results on several metrics, including adversarial evaluation, demonstrate that the adversarially-trained system generates higher-quality responses than previous baselines.

show abstract

“…Dialog generation in NLP Text-only dialog generation [15,16,23,30,39] has been studied for many years in the Natural Language Processing (NLP) literature, and has leaded to many applications. Recently, the popular 'Xiaoice' produced by Microsoft and the 'Its Alive' chatbot created by Facebook have attracted significant public attention.…”

Section: Related Workmentioning

confidence: 99%

Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning

Wang

Shen

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

132

114

View full text Add to dashboard Cite

The Visual Dialogue task requires an agent to engage in a conversation about an image with a human. It represents an extension of the Visual Question Answering task in that the agent needs to answer a question about an image, but it needs to do so in light of the previous dialogue that has taken place. The key challenge in Visual Dialogue is thus maintaining a consistent, and natural dialogue while continuing to answer questions correctly. We present a novel approach that combines Reinforcement Learning and Generative Adversarial Networks (GANs) to generate more human-like responses to questions. The GAN helps overcome the relative paucity of training data, and the tendency of the typical MLE-based approach to generate overly terse answers. Critically, the GAN is tightly integrated into the attention mechanism that generates humaninterpretable reasons for each answer. This means that the discriminative model of the GAN has the task of assessing whether a candidate answer is generated by a human or not, given the provided reason. This is significant because it drives the generative model to produce high quality answers that are well supported by the associated reasoning. The method also generates the state-of-the-art results on the primary benchmark.

show abstract

Incorporating Loose-Structured Knowledge into Conversation Modeling via Recall-Gate LSTM

Cited by 11 publications

References 0 publications

A Deep Look into neural ranking models for information retrieval

A Deep Look into neural ranking models for information retrieval

Adversarial Learning for Neural Dialogue Generation

Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning

Contact Info

Product

Resources

About