Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHow Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus
كيف يجب أن يسأل الوكلاء أسئلة للتعلم المنشأ؟حوار مشروح كوربوس
339
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
سيحتاج الوكلاء الذكيون الذين يشترفون بمفاهيم جديدة في البيئات المحددة إلى طلب أسئلة زملائهم البشريين الذين يتعلمون عن العالم المادي.لفهم هذه المشكلة بشكل أفضل، نحتاج إلى بيانات حول طرح الأسئلة في التفاعلات القائمة على المهمة المحددة.تحقيقا لهذه الغاية، نقدم كوربوس لتعلم الحوار البشري الروبوت (HURDL) - وهو جوربوس حوار رواية تم جمعها في بيئة افتراضية تفاعلية عبر الإنترنت التي يلعب فيها المشاركين البشري دور الروبوت الذي يؤدي مهمة تنظيم أدوات تعاونية.نحن نصف بيانات Corpus ومخطط التوضيح المقابل لتقديم نظرة ثاقبة في شكل ومضمون الأسئلة التي يطلبها البشر تسهيل التعلم في بيئة داخلية.نحن نقدم كوربوس كمورد مضمون تجريبيا لتحسين توليد السؤال في الوكلاء الذكيين المحتملين.
Intelligent agents that are confronted with novel concepts in situated environments will need to ask their human teammates questions to learn about the physical world. To better understand this problem, we need data about asking questions in situated task-based interactions. To this end, we present the Human-Robot Dialogue Learning (HuRDL) Corpus - a novel dialogue corpus collected in an online interactive virtual environment in which human participants play the role of a robot performing a collaborative tool-organization task. We describe the corpus data and a corresponding annotation scheme to offer insight into the form and content of questions that humans ask to facilitate learning in a situated environment. We provide the corpus as an empirically-grounded resource for improving question generation in situated intelligent agents.
References used
https://aclanthology.org/
rate research
Read More
In this paper we argue that to make dialogue systems able to actively explain their decisions they can make use of enthymematic reasoning. We motivate why this is an appropriate strategy and integrate it within our own proof-theoretic dialogue manage
r framework based on linear logic. In particular, this enables a dialogue system to provide reasonable answers to why-questions that query information previously given by the system.
Vector representations have become a central element in semantic language modelling, leading to mathematical overlaps with many fields including quantum theory. Compositionality is a core goal for such representations: given representations for wet'
and fish', how should the concept wet fish' be represented? This position paper surveys this question from two points of view. The first considers the question of whether an explicit mathematical representation can be successful using only tools from within linear algebra, or whether other mathematical tools are needed. The second considers whether semantic vector composition should be explicitly described mathematically, or whether it can be a model-internal side-effect of training a neural network. A third and newer question is whether a compositional model can be implemented on a quantum computer. Given the fundamentally linear nature of quantum mechanics, we propose that these questions are related, and that this survey may help to highlight candidate operations for future quantum implementation.
Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior. We introduce a new human-and-model-in-the-loop framework for evaluati
ng the toxicity of such models, and compare a variety of existing methods in both the cases of non-adversarial and adversarial users that expose their weaknesses. We then go on to propose two novel methods for safe conversational agents, by either training on data from our new human-and-model-in-the-loop framework in a two-stage system, or ''baking-in'' safety to the generative model itself. We find our new techniques are (i) safer than existing models; while (ii) maintaining usability metrics such as engagingness relative to state-of-the-art chatbots. In contrast, we expose serious safety issues in existing standard systems like GPT2, DialoGPT, and BlenderBot.
Communication between human and mobile agents is getting increasingly important as such agents are widely deployed in our daily lives. Vision-and-Dialogue Navigation is one of the tasks that evaluate the agent's ability to interact with humans for as
sistance and navigate based on natural language responses. In this paper, we explore the Navigation from Dialogue History (NDH) task, which is based on the Cooperative Vision-and-Dialogue Navigation (CVDN) dataset, and present a state-of-the-art model which is built upon Vision-Language transformers. However, despite achieving competitive performance, we find that the agent in the NDH task is not evaluated appropriately by the primary metric -- Goal Progress. By analyzing the performance mismatch between Goal Progress and other metrics (e.g., normalized Dynamic Time Warping) from our state-of-the-art model, we show that NDH's sub-path based task setup (i.e., navigating partial trajectory based on its correspondent subset of the full dialogue) does not provide the agent with enough supervision signal towards the goal region. Therefore, we propose a new task setup called NDH-Full which takes the full dialogue and the whole navigation path as one instance. We present a strong baseline model and show initial results on this new task. We further describe several approaches that we try, in order to improve the model performance (based on curriculum learning, pre-training, and data-augmentation), suggesting potential useful training methods on this new NDH-Full task.
Recently, the Machine Translation (MT) community has become more interested in document-level evaluation especially in light of reactions to claims of human parity'', since examining the quality at the level of the document rather than at the sentenc
e level allows for the assessment of suprasentential context, providing a more reliable evaluation. This paper presents a document-level corpus annotated in English with context-aware issues that arise when translating from English into Brazilian Portuguese, namely ellipsis, gender, lexical ambiguity, number, reference, and terminology, with six different domains. The corpus can be used as a challenge test set for evaluation and as a training/testing corpus for MT as well as for deep linguistic analysis of context issues. To the best of our knowledge, this is the first corpus of its kind.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
