Related papers: Challenging Neural Dialogue Models with Natural Da…
We propose Autolearn, a framework that enables language models to learn from documents they read, with no external supervision. Passages that produce anomalously high per-token loss are flagged, verified through a self-generated Q&A chain,…
Sample efficiency and systematic generalization are two long-standing challenges in reinforcement learning. Previous studies have shown that involving natural language along with other observation modalities can improve generalization and…
A class of explainable NLP models for reasoning tasks support their decisions by generating free-form or structured explanations, but what happens when these supporting structures contain errors? Our goal is to allow users to interactively…
Despite important progress, conversational systems often generate dialogues that sound unnatural to humans. We conjecture that the reason lies in their different training and testing conditions: agents are trained in a controlled "lab"…
Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and generated responses as effects, recognizing that changes in…
Rapid progress in machine learning for natural language processing has the potential to transform debates about how humans learn language. However, the learning environments and biases of current artificial learners and humans diverge in…
Conversational agents (CAs) play an important role in human computer interaction. Creating believable movements for CAs is challenging, since the movements have to be meaningful and natural, reflecting the coupling between gestures and…
Prediction in language has traditionally been studied using simple designs in which neural responses to expected and unexpected words are compared in a categorical fashion. However, these designs have been contested as being `prediction…
In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more…
Commonsense reasoning is intuitive for humans but has been a long-term challenge for artificial intelligence (AI). Recent advancements in pretrained language models have shown promising results on several commonsense benchmark datasets.…
The progress of Natural Language Processing (NLP), although fast in recent years, is not at the same pace for all languages. African languages in particular are still behind and lack automatic processing tools. Some of these tools are very…
Deep neural networks (DNNs) are known for extracting useful information from large amounts of data. However, the representations learned in DNNs are typically hard to interpret, especially in dense layers. One crucial issue of the classical…
The ubiquitous nature of chatbots and their interaction with users generate an enormous amount of data. Can we improve chatbots using this data? A self-feeding chatbot improves itself by asking natural language feedback when a user is…
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…
Much of human dialogue occurs in semi-cooperative settings, where agents with different goals attempt to agree on common decisions. Negotiations require complex communication and reasoning skills, but success is easy to measure, making this…
State-of-the-art conversational AI systems raise concerns due to their potential risks of generating unsafe, toxic, unethical, or dangerous content. Previous works have developed datasets to teach conversational agents the appropriate…
Despite the growing progress in Natural Language Inference (NLI) research, resources for the Bengali language remain extremely limited. Existing Bengali NLI datasets exhibit several inconsistencies, including annotation errors, ambiguous…
Automatic dialogue evaluation plays a crucial role in open-domain dialogue research. Previous works train neural networks with limited annotation for conducting automatic dialogue evaluation, which would naturally affect the evaluation…
Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are…
This paper presents a dataset collected from natural dialogs which enables to test the ability of dialog systems to learn new facts from user utterances throughout the dialog. This interactive learning will help with one of the most…