Do you want to publish a course? Click here

Consistent Accelerated Inference via Confident Adaptive Transformers

الاستدلال المتسابقين متسقين عبر المحولات التكيفية الواثقة

472   0   0   0.0 ( 0 )
 Publication date 2021
and research's language is English
 Created by Shamra Editor




Ask ChatGPT about the research

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase efficiency, but can come with unpredictable performance costs. In this work, we present CATs -- Confident Adaptive Transformers -- in which we simultaneously increase computational efficiency, while guaranteeing a specifiable degree of consistency with the original model with high confidence. Our method trains additional prediction heads on top of intermediate layers, and dynamically decides when to stop allocating computational effort to each input using a meta consistency classifier. To calibrate our early prediction stopping rule, we formulate a unique extension of conformal prediction. We demonstrate the effectiveness of this approach on four classification and regression tasks.



References used
https://aclanthology.org/
rate research

Read More

This work demonstrates the development process of a machine learning architecture for inference that can scale to a large volume of requests. We used a BERT model that was fine-tuned for emotion analysis, returning a probability distribution of emoti ons given a paragraph. The model was deployed as a gRPC service on Kubernetes. Apache Spark was used to perform inference in batches by calling the service. We encountered some performance and concurrency challenges and created solutions to achieve faster running time. Starting with 200 successful inference requests per minute, we were able to achieve as high as 18 thousand successful requests per minute with the same batch job resource allocation. As a result, we successfully stored emotion probabilities for 95 million paragraphs within 96 hours.
We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other. High-quality CPC models can significan tly benefit applications such as comparative question answering and review-based recommendation. Among the existing approaches, non-deep learning methods suffer from inferior performances. The state-of-the-art graph neural network-based ED-GAT (Ma et al., 2020) only considers syntactic information while ignoring the critical semantic relations and the sentiments to the compared entities. We propose Sentiment Analysis Enhanced COmparative Network (SAECON) which improves CPC accuracy with a sentiment analyzer that learns sentiments to individual entities via domain adaptive knowledge transfer. Experiments on the CompSent-19 (Panchenko et al., 2019) dataset present a significant improvement on the F1 scores over the best existing CPC approaches.
Formal semantics in the Montagovian tradition provides precise meaning characterisations, but usually without a formal theory of the pragmatics of contextual parameters and their sensitivity to background knowledge. Meanwhile, formal pragmatic theori es make explicit predictions about meaning in context, but generally without a well-defined compositional semantics. We propose a combined framework for the semantic and pragmatic interpretation of sentences in the face of probabilistic knowledge. We do so by (1) extending a Montagovian interpretation scheme to generate a distribution over possible meanings, and (2) generating a posterior for this distribution using a variant of the Rational Speech Act (RSA) models, but generalised to arbitrary propositions. These aspects of our framework are tied together by evaluating entailment under probabilistic uncertainty. We apply our model to anaphora resolution and show that it provides expected biases under suitable assumptions about the distributions of lexical and world-knowledge. Further, we observe that the model's output is robust to variations in its parameters within reasonable ranges.
Transformer and its variants have achieved great success in natural language processing. Since Transformer models are huge in size, serving these models is a challenge for real industrial applications. In this paper, we propose , a highly efficient i nference library for models in the Transformer family. includes a series of GPU optimization techniques to both streamline the computation of Transformer layers and reduce memory footprint. supports models trained using PyTorch and Tensorflow. Experimental results on standard machine translation benchmarks show that achieves up to 14x speedup compared with TensorFlow and 1.4x speedup compared with , a concurrent CUDA implementation. The code will be released publicly after the review.
We probe pre-trained transformer language models for bridging inference. We first investigate individual attention heads in BERT and observe that attention heads at higher layers prominently focus on bridging relations in-comparison with the lower an d middle layers, also, few specific attention heads concentrate consistently on bridging. More importantly, we consider language models as a whole in our second approach where bridging anaphora resolution is formulated as a masked token prediction task (Of-Cloze test). Our formulation produces optimistic results without any fine-tuning, which indicates that pre-trained language models substantially capture bridging inference. Our further investigation shows that the distance between anaphor-antecedent and the context provided to language models play an important role in the inference.

suggested questions

comments
Fetching comments Fetching comments
Sign in to be able to follow your search criteria
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا