User Feedback
Related Papers
Combining Multiple Forms of Evidence While Filtering
This paper studies how to go beyond relevance and enable a filtering system to learn more in- teresting and detailed data driven user models from multiple forms of evidence. We …...
Opinion Mining using Econometrics: A Case Study on Reputation Systems
Deriving the polarity and strength of opinions is an important research topic, attracting sig- nificant attention over the last few years. In this work, to measure the strength and po- …...
Topic-wise, Sentiment-wise, or Otherwise? Identifying the Hidden Dimension for Unsupervised Text Classification
While traditional work on text clustering has largely focused on grouping docu- ments by topic, it is conceivable that a user may want to cluster documents along other dimensions, such …...
Rapidly Testing the Interaction Model of a Pronunciation Training System via Wizard-of-Oz
AbstractThis paper describes a prototype of a computer-assisted pronunciation training system called MySpeech. The interface of the MySpeech system is web-based and it currently enables users to practice pronunciation by …...
JUST.ASK, a QA system that learns to answer new questions from previous interactions
AbstractWe present JUST.ASK, a publicly available Question Answering system, which is freely available. Its architecture is composed of the usual Question Processing, Passage Retrieval and Answer Extraction components. Several details …...
Evaluating Interactive System Adaptation
AbstractEnabling users of intelligent systems to enhance the system performance by providing feedback on their errors is an important need. However, the ability of systems to learn from user feedback …...
Deep Active Learning for Dialogue Generation
AbstractWe propose an online, end-to-end, neural generative conversational model for open-domain dialogue. It is trained using a unique combination of offline two-phase supervised learning and online human-in-the-loop active learning. While …...
Learning a Neural Semantic Parser from User Feedback
AbstractWe present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal intervention. …...
EmpDG: Multi-resolution Interactive Empathetic Dialogue Generation
AbstractA humanized dialogue system is expected to generate empathetic replies, which should be sensitive to the users’ expressed emotion. The task of empathetic dialogue generation is proposed to address this …...
When and Who? Conversation Transition Based on Bot-Agent Symbiosis Learning Network
AbstractIn online customer service applications, multiple chatbots that are specialized in various topics are typically developed separately and are then merged with other human agents to a single platform, presenting …...
A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI Systems
AbstractNatural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request. We propose …...
Contextual Rephrase Detection for Reducing Friction in Dialogue Systems
AbstractFor voice assistants like Alexa, Google Assistant, and Siri, correctly interpreting users’ intentions is of utmost importance. However, users sometimes experience friction with these assistants, caused by errors from different …...
Feedback Attribution for Counterfactual Bandit Learning in Multi-Domain Spoken Language Understanding
AbstractWith counterfactual bandit learning, models can be trained based on positive and negative feedback received for historical predictions, with no labeled data needed. Such feedback is often available in real-world …...
Online Learning over Time in Adaptive Neural Machine Translation
AbstractAdaptive Machine Translation purports to dynamically include user feedback to improve translation quality. In a post-editing scenario, user corrections of machine translation output are thus continuously incorporated into translation models, …...
Federated Learning with Noisy User Feedback
AbstractMachine Learning (ML) systems are getting increasingly popular, and drive more and more applications and services in our daily life. Thishas led to growing concerns over user privacy, since human …...
Memory-assisted prompt editing to improve GPT-3 after deployment
AbstractLarge LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret “What word is similar to good?” to mean …...
Named Entity Recognition to Detect Criminal Texts on the Web
AbstractThis paper presents a toolkit that applies named-entity extraction techniques to identify information related to criminal activity in texts from the Polish Internet. The methodological and technical assumptions were established …...
Simulating Bandit Learning from User Feedback for Extractive Question Answering
AbstractWe study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several …...
Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement
AbstractOur goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. …...
A User-Centered, Interactive, Human-in-the-Loop Topic Modelling System
AbstractHuman-in-the-loop topic modelling incorporates users’ knowledge into the modelling process, enabling them to refine the model iteratively. Recent research has demonstrated the value of user feedback, but there are still …...