Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

"chatbots": models, code, and papers

SentEmojiBot: Empathising Conversations Generation with Emojis

May 26, 2021
Akhilesh Ravi, Amit Yadav, Jainish Chauhan, Jatin Dholakia, Naman Jain, Mayank Singh

The increasing use of dialogue agents makes it extremely desirable for them to understand and acknowledge the implied emotions to respond like humans with empathy. Chatbots using traditional techniques analyze emotions based on the context and meaning of the text and lack the understanding of emotions expressed through face. Emojis representing facial expressions present a promising way to express emotions. However, none of the AI systems utilizes emojis for empathetic conversation generation. We propose, SentEmojiBot, based on the SentEmoji dataset, to generate empathetic conversations with a combination of emojis and text. Evaluation metrics show that the BERT-based model outperforms the vanilla transformer model. A user study indicates that the dialogues generated by our model were understandable and adding emojis improved empathetic traits in conversations by 9.8%

  

Conversational Agents: Theory and Applications

Feb 07, 2022
Mattias Wahde, Marco Virgolin

In this chapter, we provide a review of conversational agents (CAs), discussing chatbots, intended for casual conversation with a user, as well as task-oriented agents that generally engage in discussions intended to reach one or several specific goals, often (but not always) within a specific domain. We also consider the concept of embodied conversational agents, briefly reviewing aspects such as character animation and speech processing. The many different approaches for representing dialogue in CAs are discussed in some detail, along with methods for evaluating such agents, emphasizing the important topics of accountability and interpretability. A brief historical overview is given, followed by an extensive overview of various applications, especially in the fields of health and education. We end the chapter by discussing benefits and potential risks regarding the societal impact of current and future CA technology.

* preprint of a chapter to appear in Handbook of Computer Learning and Intelligence - Volume 1 
  

Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics

Jun 04, 2021
Thomas Conley, Jack St. Clair, Jugal Kalita

Although people have the ability to engage in vapid dialogue without effort, this may not be a uniquely human trait. Since the 1960's researchers have been trying to create agents that can generate artificial conversation. These programs are commonly known as chatbots. With increasing use of neural networks for dialog generation, some conclude that this goal has been achieved. This research joins the quest by creating a dialog generating Recurrent Neural Network (RNN) and by enhancing the ability of this network with auxiliary loss functions and a beam search. Our custom loss functions achieve better cohesion and coherence by including calculations of Maximum Mutual Information (MMI) and entropy. We demonstrate the effectiveness of this system by using a set of custom evaluation metrics inspired by an abundance of previous research and based on tried-and-true principles of Natural Language Processing.

* Proceedings of ICON-2018, Patiala, India. December 2018, pages 143--149 
  

Graph-Based Social Relation Reasoning

Jul 17, 2020
Wanhua Li, Yueqi Duan, Jiwen Lu, Jianjiang Feng, Jie Zhou

Human beings are fundamentally sociable -- that we generally organize our social lives in terms of relations with other people. Understanding social relations from an image has great potential for intelligent systems such as social chatbots and personal assistants. In this paper, we propose a simpler, faster, and more accurate method named graph relational reasoning network (GR2N) for social relation recognition. Different from existing methods which process all social relations on an image independently, our method considers the paradigm of jointly inferring the relations by constructing a social relation graph. Furthermore, the proposed GR2N constructs several virtual relation graphs to explicitly grasp the strong logical constraints among different types of social relations. Experimental results illustrate that our method generates a reasonable and consistent social relation graph and improves the performance in both accuracy and efficiency.

* ECCV 2020 
  

Automated Speech Generation from UN General Assembly Statements: Mapping Risks in AI Generated Texts

Jun 05, 2019
Joseph Bullock, Miguel Luengo-Oroz

Automated text generation has been applied broadly in many domains such as marketing and robotics, and used to create chatbots, product reviews and write poetry. The ability to synthesize text, however, presents many potential risks, while access to the technology required to build generative models is becoming increasingly easy. This work is aligned with the efforts of the United Nations and other civil society organisations to highlight potential political and societal risks arising through the malicious use of text generation software, and their potential impact on human rights. As a case study, we present the findings of an experiment to generate remarks in the style of political leaders by fine-tuning a pretrained AWD- LSTM model on a dataset of speeches made at the UN General Assembly. This work highlights the ease with which this can be accomplished, as well as the threats of combining these techniques with other technologies.

* International Conference on Machine Learning AI for Social Good Workshop, Long Beach, United States, 2019 
* 5 pages 
  

Empirical study on BlenderBot 2.0 Errors Analysis in terms of Model, Data and User-Centric Approach

Jan 10, 2022
Jungseob Lee, Midan Shim, Suhyune Son, Yujin Kim, Chanjun Park, Heuiseok Lim

BlenderBot 2.0 is a dialogue model that represents open-domain chatbots by reflecting real-time information and remembering user information for an extended period using an internet search module and multi-session. Nonetheless, the model still has room for improvement. To this end, we examined BlenderBot 2.0 limitations and errors from three perspectives: model, data, and user. From the data point of view, we highlight the unclear guidelines provided to workers during the crowdsourcing process, as well as a lack of a process for refining hate speech in the collected data and verifying the accuracy of internet-based information. From a user perspective, we identify nine types of problems of BlenderBot 2.0, and their causes are thoroughly investigated. Furthermore, for each point of view, practical improvement methods are proposed, and we discuss several potential future research directions.

* English Version of "Empirical study on BlenderBot 2.0 errors analysis in terms of model, data and dialogue" (Journal of the Korea Convergence Society) 
  

Turn-level Dialog Evaluation with Dialog-level Weak Signals for Bot-Human Hybrid Customer Service Systems

Oct 25, 2020
Ruofeng Wen

We developed a machine learning approach that quantifies multiple aspects of the success or values in Customer Service contacts, at anytime during the interaction. Specifically, the value/reward function regarding to the turn-level behaviors across human agents, chatbots and other hybrid dialog systems is characterized by the incremental information and confidence gain between sentences, based on the token-level predictions from a multi-task neural network trained with only weak signals in dialog-level attributes/states. The resulting model, named Value Profiler, serves as a goal-oriented dialog manager that enhances conversations by regulating automated decisions with its reward and state predictions. It supports both real-time monitoring and scalable offline customer experience evaluation, for both bot- and human-handled contacts. We show how it improves Amazon customer service quality in several applications.

  

Discovering Textual Structures: Generative Grammar Induction using Template Trees

Sep 09, 2020
Thomas Winters, Luc De Raedt

Natural language generation provides designers with methods for automatically generating text, e.g. for creating summaries, chatbots and game content. In practise, text generators are often either learned and hard to interpret, or created by hand using techniques such as grammars and templates. In this paper, we introduce a novel grammar induction algorithm for learning interpretable grammars for generative purposes, called Gitta. We also introduce the novel notion of template trees to discover latent templates in corpora to derive these generative grammars. By using existing human-created grammars, we found that the algorithm can reasonably approximate these grammars using only a few examples. These results indicate that Gitta could be used to automatically learn interpretable and easily modifiable grammars, and thus provide a stepping stone for human-machine co-creation of generative models.

* Published in the Proceedings of the 11th International Conference on Computational Creativity, p177-180 
  

How Effective is Incongruity? Implications for Code-mix Sarcasm Detection

Feb 06, 2022
Aditya Shah, Chandresh Kumar Maurya

The presence of sarcasm in conversational systems and social media like chatbots, Facebook, Twitter, etc. poses several challenges for downstream NLP tasks. This is attributed to the fact that the intended meaning of a sarcastic text is contrary to what is expressed. Further, the use of code-mix language to express sarcasm is increasing day by day. Current NLP techniques for code-mix data have limited success due to the use of different lexicon, syntax, and scarcity of labeled corpora. To solve the joint problem of code-mixing and sarcasm detection, we propose the idea of capturing incongruity through sub-word level embeddings learned via fastText. Empirical results shows that our proposed model achieves F1-score on code-mix Hinglish dataset comparable to pretrained multilingual models while training 10x faster and using a lower memory footprint

* Published in ICON - ACL 2021 
  
<<
12
13
14
15
16
17
18
19
20
21
22
23
24
>>