Listen, Interact and Talk: Learning to Speak via Interaction

By Haonan Yu, Wei Xu. 2017

13 citations recorded by the source corpus.

One of the long-term goals of artificial intelligence is to build an agent that can communicate intelligently with human in natural language. Most existing work on natural language learning relies heavily on training over a pre-collected dataset with annotated labels, leading to an agent that essentially captures the statistics of the fixed external training data. As the training data is essentially a static snapshot representation of the knowledge from the annotator, the agent trained this way is limited in adaptiveness and generalization of its behavior. Moreover, this is very different from the language learning process of humans, where language is acquired during communication by taking speaking action and learning from the consequences of speaking action in an interactive manner. This paper presents an interactive setting for grounded natural language learning, where an agent learns natural language by interacting with a teacher and learning from feedback, thus learning and improving language skills while taking part in the conversation. To achieve this goal, we propose a model which incorporates both imitation and reinforcement by leveraging jointly sentence and reward feedbacks from the teacher. Experiments are conducted to validate the effectiveness of the proposed approach.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, methodology): “requested, existing methods typically require accompanying scalar rewards or adherence to particular templates or structure to ensure that the feedback is usable by the model (Rieser and Lemon, 2011; Zhang et al., 2017; Liu et al., 2018).”
Continuous and Interactive Factual Knowledge Learning in Veriﬁcation Dialogues (2020, background): “No existing dialogue systems [47, 25, 10, 52, 42, 57, 59, 29, 54] can train prediction models continually online using information retained in the past.”
Lifelong Knowledge Learning in Rule-based Dialogue Systems (2020, background): “2017) and (Zhang et al. 2017) whose goal is to train dialogue systems using human teachers who can ask and answer the system’s questions.”
Lifelong and Interactive Learning of Factual Knowledge in Dialogues (2019, background): “Li et al. (2017a,b) and Zhang et al. (2017) train chatbots using human teachers who can ask and answer the chatbot questions.”
Towards a Continuous Knowledge Learning Engine for Chatbots (2018, background): “Also, no existing dialogue systems (Vinyals and Le, 2015; Li et al., 2016a; Bordes and Weston, 2016; Weston, 2016; Zhang et al., 2017) employ lifelong learning to train prediction models by using information/knowledge retained in the past.”
Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game (2018, methodology): “, 2016) in the latent space of the control vector ct (Zhang et al., 2017).”