Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDecoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning
فك تشفير وسريعة وبطيئة: دراسة حالة حول موازنة المفاضلات في التفكير التزايدي والشخصية
207
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
اعتمدت العمل الحديث نماذج من التفكير العملي لتوليد لغة إعلامية، على سبيل المثال، تعليق الصورة.نقترح استرخاء بسيط ولكنه فعال للغاية من فك التشفير العقلاني تماما، بناء على نهج متزايدي وتزايدي على مستوى الشخصيات لمعلومات التصوير العصبي المعني بالمعلومات بشكل غير رسمي.نحن نطبق مكتوبة وسريعة "وبطيئة"، المتكلم الذي ينطبق على التفكير العملي في بعض الأحيان (الكلمة فقط - في البداية)، مع عدم انسقاد نموذج اللغة.في تقييمنا، نجد أن المعلومات المتزايدة من خلال فك التشفير العملي تنخفض بشكل عام الجودة وعلى نحو حد ما بشكل حدسي، يزيد من التكرار في التسميات التوضيحية.ومع ذلك، فإن متحدثنا المختلط يحقق توازنا جيدا بين الجودة والمعلوماتية.
Recent work has adopted models of pragmatic reasoning for the generation of informative language in, e.g., image captioning. We propose a simple but highly effective relaxation of fully rational decoding, based on an existing incremental and character-level approach to pragmatically informative neural image captioning. We implement a mixed, fast' and slow', speaker that applies pragmatic reasoning occasionally (only word-initially), while unrolling the language model. In our evaluation, we find that increased informativeness through pragmatic decoding generally lowers quality and, somewhat counter-intuitively, increases repetitiveness in captions. Our mixed speaker, however, achieves a good balance between quality and informativeness.
References used
https://aclanthology.org/
rate research
Read More
thinking fast and slow, thinking fast and slow, thinking fast and slow, thinking fast and slow, thinking fast and slow, thinking fast and slow, thinking fast and slow, thinking fast and slow, thinking fast and slow, thinking fast and slow, thinking f
ast and slow, thinking fast and slow, thinking fast and slow, thinking fast and slow,
Abstract Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined s
lot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method outperforms the state-of-the-art methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human--human dialogue dataset across multiple domains.
Narrative generation is an open-ended NLP task in which a model generates a story given a prompt. The task is similar to neural response generation for chatbots; however, innovations in response generation are often not applied to narrative generatio
n, despite the similarity between these tasks. We aim to bridge this gap by applying and evaluating advances in decoding methods for neural response generation to neural narrative generation. In particular, we employ GPT-2 and perform ablations across nucleus sampling thresholds and diverse decoding hyperparameters---specifically, maximum mutual information---analyzing results over multiple criteria with automatic and human evaluation. We find that (1) nucleus sampling is generally best with thresholds between 0.7 and 0.9; (2) a maximum mutual information objective can improve the quality of generated stories; and (3) established automatic metrics do not correlate well with human judgments of narrative quality on any qualitative metric.
We often use perturbations to regularize neural models. For neural encoder-decoders, previous studies applied the scheduled sampling (Bengio et al., 2015) and adversarial perturbations (Sato et al., 2019) as perturbations but these methods require co
nsiderable computational time. Thus, this study addresses the question of whether these approaches are efficient enough for training time. We compare several perturbations in sequence-to-sequence problems with respect to computational time. Experimental results show that the simple techniques such as word dropout (Gal and Ghahramani, 2016) and random replacement of input tokens achieve comparable (or better) scores to the recently proposed perturbations, even though these simple methods are faster.
Many statistical models have high accuracy on test benchmarks, but are not explainable, struggle in low-resource scenarios, cannot be reused for multiple tasks, and cannot easily integrate domain expertise. These factors limit their use, particularly
in settings such as mental health, where it is difficult to annotate datasets and model outputs have significant impact. We introduce a micromodel architecture to address these challenges. Our approach allows researchers to build interpretable representations that embed domain knowledge and provide explanations throughout the model's decision process. We demonstrate the idea on multiple mental health tasks: depression classification, PTSD classification, and suicidal risk assessment. Our systems consistently produce strong results, even in low-resource scenarios, and are more interpretable than alternative methods.
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
