Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userReading and Acting while Blindfolded: The Need for Semantics in Text Game Agents
القراءة والتصرف أثناء معصوب العينين: الحاجة إلى دلالات في وكلاء ألعاب النص
247
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الألعاب القائمة على النص محاكاة العالمين والتفاعل مع اللاعبين باستخدام اللغة الطبيعية. لقد استخدمها العمل الحديث كخطأ في وكلاء فهم اللغة المستقلة، مع وجود الدافع هو فهم معاني الكلمات أو الدلالات هو مكون رئيسي في كيفية فهم البشر والسبب والتصرف في هذه العوالم. ومع ذلك، لا يزال غير واضح إلى أي مدى يستخدم الوكلاء الاصطناعي الفهم الدلالي للنص. تحقيقا لهذه الغاية، نقوم بإجراء تجارب لتقليل كمية المعلومات الدلالية المتاحة لعامل التعلم. من المستغرب أن نجد أن الوكيل قادر على تحقيق درجات عالية حتى في الغياب التام للدليل اللغوي، مما يشير إلى أن الإعداد التجريبي الشهير حاليا قد تكون مصممة بشكل سيء لفهم واستفادة من نصوص اللعبة. لعلاج هذا النقص، نقترح فك تشفير ديناميات عكسية لتنظيم مساحة التمثيل وتشجيع الاستكشاف، مما يدل على تحسين الأداء في العديد من الألعاب بما في ذلك زورق الأول - نناقش الآثار المترتبة على نتائجنا لتصميم وكلاء في المستقبل مع فهم دلالي أقوى.
Text-based games simulate worlds and interact with players using natural language. Recent work has used them as a testbed for autonomous language-understanding agents, with the motivation being that understanding the meanings of words or semantics is a key component of how humans understand, reason, and act in these worlds. However, it remains unclear to what extent artificial agents utilize semantic understanding of the text. To this end, we perform experiments to systematically reduce the amount of semantic information available to a learning agent. Surprisingly, we find that an agent is capable of achieving high scores even in the complete absence of language semantics, indicating that the currently popular experimental setup and models may be poorly designed to understand and leverage game texts. To remedy this deficiency, we propose an inverse dynamics decoder to regularize the representation space and encourage exploration, which shows improved performance on several games including Zork I. We discuss the implications of our findings for designing future agents with stronger semantic understanding.
References used
https://aclanthology.org/
rate research
Read More
We seek to create agents that both act and communicate with other agents in pursuit of a goal. Towards this end, we extend LIGHT (Urbanek et al. 2019)---a large-scale crowd-sourced fantasy text-game---with a dataset of quests. These contain natural l
anguage motivations paired with in-game goals and human demonstrations; completing a quest might require dialogue or actions (or both). We introduce a reinforcement learning system that (1) incorporates large-scale language modeling-based and commonsense reasoning-based pre-training to imbue the agent with relevant priors; and (2) leverages a factorized action space of action commands and dialogue, balancing between the two. We conduct zero-shot evaluations using held-out human expert demonstrations, showing that our agents are able to act consistently and talk naturally with respect to their motivations.
Authors of text tend to predominantly use a single sense for a lemma that can differ among different authors. This might not be captured with an author-agnostic word sense disambiguation (WSD) model that was trained on multiple authors. Our work find
s that WordNet's first senses, the predominant senses of our dataset's genre, and the predominant senses of an author can all be different and therefore, author-agnostic models could perform well over the entire dataset, but poorly on individual authors. In this work, we explore methods for personalizing WSD models by tailoring existing state-of-the-art models toward an individual by exploiting the author's sense distributions. We propose a novel WSD dataset and show that personalizing a WSD system with knowledge of an author's sense distributions or predominant senses can greatly increase its performance.
The call for the amendment and reform of the international system which established
the United Nations has become an urgent demand of the Member States through a new set
of international legal norms to overcome the stalemate and paralysis in the Un
ited Nations
bodies and through activating the founding charter of the organization, which has been
defunct for more than half a century, the thing that negatively affected the role of these
bodies and lead to its failure in keeping international peace and security due to the control
exercised by the superpowers on the international system and the decisions taken by the
organization, especially in the Security Council.
Based on the above, we will study the reality and the future of the United Nations in
the light of the changes offered by the international system and how the organization can
respond and adapt to these changes and keep up to the challenges ahead of it and be in the
level of expectations of the international community, according to the statements in its
Constitution.
With the growing popularity of smart speakers, such as Amazon Alexa, speech is becoming one of the most important modes of human-computer interaction. Automatic speech recognition (ASR) is arguably the most critical component of such systems, as erro
rs in speech recognition propagate to the downstream components and drastically degrade the user experience. A simple and effective way to improve the speech recognition accuracy is to apply automatic post-processor to the recognition result. However, training a post-processor requires parallel corpora created by human annotators, which are expensive and not scalable. To alleviate this problem, we propose Back TranScription (BTS), a denoising-based method that can create such corpora without human labor. Using a raw corpus, BTS corrupts the text using Text-to-Speech (TTS) and Speech-to-Text (STT) systems. Then, a post-processing model can be trained to reconstruct the original text given the corrupted input. Quantitative and qualitative evaluations show that a post-processor trained using our approach is highly effective in fixing non-trivial speech recognition errors such as mishandling foreign words. We present the generated parallel corpus and post-processing platform to make our results publicly available.
Since the seminal work of Richard Montague in the 1970s, mathematical and logic tools have successfully been used to model several aspects of the meaning of natural language. However, visually impaired people continue to face serious difficulties in
getting full access to this important instrument. Our paper aims to present a work in progress whose main goal is to provide blind students and researchers with an adequate method to deal with the different resources that are used in formal semantics. In particular, we intend to adapt the Portuguese Braille system in order to accommodate the most common symbols and formulas used in this kind of approach and to develop pedagogical procedures to facilitate its learnability. By making this formalization compatible with the Braille coding (either traditional and electronic), we hope to help blind people to learn and use this notation, essential to acquire a better understanding of a great number of semantic properties displayed by natural language.
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
