Quantum Transfer Learning for Acceptability Judgements
- URL: http://arxiv.org/abs/2401.07777v1
- Date: Mon, 15 Jan 2024 15:40:16 GMT
- Title: Quantum Transfer Learning for Acceptability Judgements
- Authors: Giuseppe Buonaiuto, Raffaele Guarasci, Aniello Minutolo, Giuseppe De
Pietro, Massimo Esposito
- Abstract summary: This work shows potential advantages of quantum transfer learning algorithms trained on embedding vectors extracted from a large language model.
The approach has been tested on sentences extracted from ItaCoLa, a corpus that collects Italian sentences labeled with their acceptability judgment.
The evaluation phase shows results for the quantum transfer learning pipeline comparable to state-of-the-art classical transfer learning algorithms.
- Score: 5.90817406672742
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Hybrid quantum-classical classifiers promise to positively impact critical
aspects of natural language processing tasks, particularly
classification-related ones. Among the possibilities currently investigated,
quantum transfer learning, i.e., using a quantum circuit for fine-tuning
pre-trained classical models for a specific task, is attracting significant
attention as a potential platform for proving quantum advantage.
This work shows potential advantages, both in terms of performance and
expressiveness, of quantum transfer learning algorithms trained on embedding
vectors extracted from a large language model to perform classification on a
classical Linguistics task: acceptability judgments. Acceptability judgment is
the ability to determine whether a sentence is considered natural and
well-formed by a native speaker. The approach has been tested on sentences
extracted from ItaCoLa, a corpus that collects Italian sentences labeled with
their acceptability judgment. The evaluation phase shows results for the
quantum transfer learning pipeline comparable to state-of-the-art classical
transfer learning algorithms, proving current quantum computers' capabilities
to tackle NLP tasks for ready-to-use applications. Furthermore, a qualitative
linguistic analysis, aided by explainable AI methods, reveals the capabilities
of quantum transfer learning algorithms to correctly classify complex and more
structured sentences, compared to their classical counterpart. This finding
sets the ground for a quantifiable quantum advantage in NLP in the near future.
Related papers
- A Few Shot Learning Scheme for Quantum Natural Language Processing [0.0]
We develop a framework to implement Few Shot Learning for Quantum Natural Language Processing.
This framework is put to the test to explore its behaviour and its power in extracting useful work from each call to a quantum system.
arXiv Detail & Related papers (2024-09-18T16:24:51Z) - Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties?
We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.
We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
arXiv Detail & Related papers (2024-08-22T08:21:28Z) - Separable Power of Classical and Quantum Learning Protocols Through the Lens of No-Free-Lunch Theorem [70.42372213666553]
The No-Free-Lunch (NFL) theorem quantifies problem- and data-independent generalization errors regardless of the optimization process.
We categorize a diverse array of quantum learning algorithms into three learning protocols designed for learning quantum dynamics under a specified observable.
Our derived NFL theorems demonstrate quadratic reductions in sample complexity across CLC-LPs, ReQu-LPs, and Qu-LPs.
We attribute this performance discrepancy to the unique capacity of quantum-related learning protocols to indirectly utilize information concerning the global phases of non-orthogonal quantum states.
arXiv Detail & Related papers (2024-05-12T09:05:13Z) - Classical Verification of Quantum Learning [42.362388367152256]
We develop a framework for classical verification of quantum learning.
We propose a new quantum data access model that we call "mixture-of-superpositions" quantum examples.
Our results demonstrate that the potential power of quantum data for learning tasks, while not unlimited, can be utilized by classical agents.
arXiv Detail & Related papers (2023-06-08T00:31:27Z) - Adapting Pre-trained Language Models for Quantum Natural Language
Processing [33.86835690434712]
We show that pre-trained representation can bring 50% to 60% increases to the capacity of end-to-end quantum models.
On quantum simulation experiments, the pre-trained representation can bring 50% to 60% increases to the capacity of end-to-end quantum models.
arXiv Detail & Related papers (2023-02-24T14:59:02Z) - A Survey on Quantum Reinforcement Learning [2.5882725323376112]
Quantum reinforcement learning is an emerging field at the intersection of quantum computing and machine learning.
With a focus on already available noisy intermediate-scale quantum devices, these include variational quantum circuits acting as function approximators.
In addition, we survey quantum reinforcement learning algorithms based on future fault-tolerant hardware, some of which come with a provable quantum advantage.
arXiv Detail & Related papers (2022-11-07T11:25:47Z) - Anticipative measurements in hybrid quantum-classical computation [68.8204255655161]
We present an approach where the quantum computation is supplemented by a classical result.
Taking advantage of its anticipation also leads to a new type of quantum measurements, which we call anticipative.
In an anticipative quantum measurement the combination of the results from classical and quantum computations happens only in the end.
arXiv Detail & Related papers (2022-09-12T15:47:44Z) - Implementation and Empirical Evaluation of a Quantum Machine Learning
Pipeline for Local Classification [0.0]
This paper presents an implementation in Python of a QML pipeline for local classification.
Specifically, it consists of a quantum k-NN and a quantum binary classifier.
The results have shown the quantum pipeline's equivalence (in terms of accuracy) to its classical counterpart in the ideal case.
arXiv Detail & Related papers (2022-05-11T08:18:57Z) - Quantum Semantic Communications for Resource-Efficient Quantum Networking [52.3355619190963]
This letter proposes a novel quantum semantic communications (QSC) framework exploiting advancements in quantum machine learning and quantum semantic representations.
The proposed framework achieves approximately 50-75% reduction in quantum communication resources needed, while achieving a higher quantum semantic fidelity.
arXiv Detail & Related papers (2022-05-05T03:49:19Z) - When BERT Meets Quantum Temporal Convolution Learning for Text
Classification in Heterogeneous Computing [75.75419308975746]
This work proposes a vertical federated learning architecture based on variational quantum circuits to demonstrate the competitive performance of a quantum-enhanced pre-trained BERT model for text classification.
Our experiments on intent classification show that our proposed BERT-QTC model attains competitive experimental results in the Snips and ATIS spoken language datasets.
arXiv Detail & Related papers (2022-02-17T09:55:21Z) - Facial Expression Recognition on a Quantum Computer [68.8204255655161]
We show a possible solution to facial expression recognition using a quantum machine learning approach.
We define a quantum circuit that manipulates the graphs adjacency matrices encoded into the amplitudes of some appropriately defined quantum states.
arXiv Detail & Related papers (2021-02-09T13:48:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.