Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding
المنطق المتدرج للفيزياء البديهية: نحو فهم لغة المنطقية يمكن التحقق منه
535
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
وقد حققت نماذج اللغة المدربة على نطاق واسع (LMS) أداء مستوى بشري على اتساع مهام فهم اللغة.ومع ذلك، فإن التقييمات فقط بناء على أداء المهام النهائي ألقت الضوء قليلا على الآلات القدرة الحقيقية في فهم اللغة والتفكير.في هذه الورقة، نسلط الضوء على أهمية تقييم عملية التفكير الأساسية بالإضافة إلى الأداء النهائي.نحو هذا الهدف، نقدم المنطق المتدرج في الفيزياء البديهية (الرحلة)، وهناك مجموعة بيانات المنطق الرواية المنطقية مع شروح كثيفة تمكن التقييم متعدد المتدرج لعملية التفكير الآلات.تظهر نتائج التجريبية الخاصة بنا أنه في حين أن LMS كبيرة يمكن أن تحقق أداء متطورا للغاية، إلا أنهم يكافحون لدعم تنبؤاتهم بأدلة داعمة صالحة.ستحفز مجموعة بيانات الرحلة ونتائج أساسية لدينا لتحفيز تقييم يمكن التحقق منه من المنطق المنطقي وتسهيل البحوث المستقبلية نحو تطوير نماذج أفضل لغات وتفكير اللغة.
Large-scale, pre-trained language models (LMs) have achieved human-level performance on a breadth of language understanding tasks. However, evaluations only based on end task performance shed little light on machines' true ability in language understanding and reasoning. In this paper, we highlight the importance of evaluating the underlying reasoning process in addition to end performance. Toward this goal, we introduce Tiered Reasoning for Intuitive Physics (TRIP), a novel commonsense reasoning dataset with dense annotations that enable multi-tiered evaluation of machines' reasoning process. Our empirical results show that while large LMs can achieve high end performance, they struggle to support their predictions with valid supporting evidence. The TRIP dataset and our baseline results will motivate verifiable evaluation of commonsense reasoning and facilitate future research toward developing better language understanding and reasoning models.
References used
https://aclanthology.org/
rate research
Read More
Temporal commonsense reasoning is a challenging task as it requires temporal knowledge usually not explicit in text. In this work, we propose an ensemble model for temporal commonsense reasoning. Our model relies on pre-trained contextual representat
ions from transformer-based language models (i.e., BERT), and on a variety of training methods for enhancing model generalization: 1) multi-step fine-tuning using carefully selected auxiliary tasks and datasets, and 2) a specifically designed temporal masked language model task aimed to capture temporal commonsense knowledge. Our model greatly outperforms the standard fine-tuning approach and strong baselines on the MC-TACO dataset.
In this paper, we propose a definition and taxonomy of various types of non-standard textual content -- generally referred to as noise'' -- in Natural Language Processing (NLP). While data pre-processing is undoubtedly important in NLP, especially wh
en dealing with user-generated content, a broader understanding of different sources of noise and how to deal with them is an aspect that has been largely neglected. We provide a comprehensive list of potential sources of noise, categorise and describe them, and show the impact of a subset of standard pre-processing strategies on different tasks. Our main goal is to raise awareness of non-standard content -- which should not always be considered as noise'' -- and of the need for careful, task-dependent pre-processing. This is an alternative to blanket, all-encompassing solutions generally applied by researchers through standard'' pre-processing pipelines. The intention is for this categorisation to serve as a point of reference to support NLP researchers in devising strategies to clean, normalise or embrace non-standard content.
Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot fillin
g and intent detection are sharing semantic knowledge. Furthermore, attention mechanism boosts joint learning to achieve state-of-the-art results. However, current joint learning models ignore the following important facts: 1. Long-term slot context is not traced effectively, which is crucial for future slot filling. 2. Slot tagging and intent detection could be mutually rewarding, but bi-directional interaction between slot filling and intent detection remains seldom explored. In this paper, we propose a novel approach to model long-term slot context and to fully utilize the semantic correlation between slots and intents. We adopt a key-value memory network to model slot context dynamically and to track more important slot tags decoded before, which are then fed into our decoder for slot tagging. Furthermore, gated memory information is utilized to perform intent detection, mutually improving both tasks through global optimization. Experiments on benchmark ATIS and Snips datasets show that our model achieves state-of-the-art performance and outperforms other methods, especially for the slot filling task.
Abstract Despite the progress made in recent years in addressing natural language understanding (NLU) challenges, the majority of this progress remains to be concentrated on resource-rich languages like English. This work focuses on Persian language,
one of the widely spoken languages in the world, and yet there are few NLU datasets available for this language. The availability of high-quality evaluation datasets is a necessity for reliable assessment of the progress on different NLU tasks and domains. We introduce ParsiNLU, the first benchmark in Persian language that includes a range of language understanding tasks---reading comprehension, textual entailment, and so on. These datasets are collected in a multitude of ways, often involving manual annotations by native speakers. This results in over 14.5k new instances across 6 distinct NLU tasks. Additionally, we present the first results on state-of-the-art monolingual and multilingual pre-trained language models on this benchmark and compare them with human performance, which provides valuable insights into our ability to tackle natural language understanding challenges in Persian. We hope ParsiNLU fosters further research and advances in Persian language understanding.1
This paper presents a production Semi-Supervised Learning (SSL) pipeline based on the student-teacher framework, which leverages millions of unlabeled examples to improve Natural Language Understanding (NLU) tasks. We investigate two questions relate
d to the use of unlabeled data in production SSL context: 1) how to select samples from a huge unlabeled data pool that are beneficial for SSL training, and 2) how does the selected data affect the performance of different state-of-the-art SSL techniques. We compare four widely used SSL techniques, Pseudo-label (PL), Knowledge Distillation (KD), Virtual Adversarial Training (VAT) and Cross-View Training (CVT) in conjunction with two data selection methods including committee-based selection and submodular optimization based selection. We further examine the benefits and drawbacks of these techniques when applied to intent classification (IC) and named entity recognition (NER) tasks, and provide guidelines specifying when each of these methods might be beneficial to improve large scale NLU systems.
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
