scholarly journals A quantum search decoder for natural language processing

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Johannes Bausch ◽  
Sathyawageeswar Subramanian ◽  
Stephen Piddock
Keyword(s):  
Language Processing ◽  
Power Law ◽  
Short Term Memory ◽  
Success Probability ◽  
Quantum Algorithm ◽  
Beam Width ◽  
Language Models ◽  
Neural Net ◽  
Beam Search ◽  
Classical Counterpart

AbstractProbabilistic language models, e.g. those based on recurrent neural networks such as long short-term memory models (LSTMs), often face the problem of finding a high probability prediction from a sequence of random variables over a set of tokens. This is commonly addressed using a form of greedy decoding such as beam search, where a limited number of highest-likelihood paths (the beam width) of the decoder are kept, and at the end the maximum-likelihood path is chosen. In this work, we construct a quantum algorithm to find the globally optimal parse (i.e. for infinite beam width) with high constant success probability. When the input to the decoder follows a power law with exponent k > 0, our algorithm has runtime Rnf(R, k), where R is the alphabet size, n the input length; here f < 1/2, and $f\rightarrow 0$ f → 0 exponentially fast with increasing k, hence making our algorithm always more than quadratically faster than its classical counterpart. We further modify our procedure to recover a finite beam width variant, which enables an even stronger empirical speedup while still retaining higher accuracy than possible classically. Finally, we apply this quantum beam search decoder to Mozilla’s implementation of Baidu’s DeepSpeech neural net, which we show to exhibit such a power law word rank frequency.

scholarly journals Efficient Embedded Decoding of Neural Network Language Models in a Machine Translation System

2018 ◽  
Vol 28 (09) ◽  
pp. 1850007
Author(s):  
Francisco Zamora-Martinez ◽  
Maria Jose Castro-Bleda
Keyword(s):  
Neural Network ◽  
Machine Translation ◽  
Language Processing ◽  
Traditional Approach ◽  
Computational Cost ◽  
Integrated Approach ◽  
Language Models ◽  
Translation System ◽  
Neural Net ◽  
Network Language

Neural Network Language Models (NNLMs) are a successful approach to Natural Language Processing tasks, such as Machine Translation. We introduce in this work a Statistical Machine Translation (SMT) system which fully integrates NNLMs in the decoding stage, breaking the traditional approach based on [Formula: see text]-best list rescoring. The neural net models (both language models (LMs) and translation models) are fully coupled in the decoding stage, allowing to more strongly influence the translation quality. Computational issues were solved by using a novel idea based on memorization and smoothing of the softmax constants to avoid their computation, which introduces a trade-off between LM quality and computational cost. These ideas were studied in a machine translation task with different combinations of neural networks used both as translation models and as target LMs, comparing phrase-based and [Formula: see text]-gram-based systems, showing that the integrated approach seems more promising for [Formula: see text]-gram-based systems, even with nonfull-quality NNLMs.

scholarly journals Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies

2016 ◽  
Vol 4 ◽  
pp. 521-535 ◽  
Author(s):  
Tal Linzen ◽  
Emmanuel Dupoux ◽  
Yoav Goldberg
Keyword(s):  
Language Processing ◽  
Short Term Memory ◽  
Structural Information ◽  
Syntactic Structure ◽  
Language Modeling ◽  
Language Models ◽  
Grammatical Structure ◽  
Long Distance ◽  
Target Number ◽  
Statistical Regularities

The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Linguistic regularities are often sensitive to syntactic structure; can such dependencies be captured by LSTMs, which do not have explicit structural representations? We begin addressing this question using number agreement in English subject-verb dependencies. We probe the architecture’s grammatical competence both using training objectives with an explicit grammatical target (number prediction, grammaticality judgments) and using language models. In the strongly supervised settings, the LSTM achieved very high overall accuracy (less than 1% errors), but errors increased when sequential and structural information conflicted. The frequency of such errors rose sharply in the language-modeling setting. We conclude that LSTMs can capture a non-trivial amount of grammatical structure given targeted supervision, but stronger architectures may be required to further reduce errors; furthermore, the language modeling signal is insufficient for capturing syntax-sensitive dependencies, and should be supplemented with more direct supervision if such dependencies need to be captured.

scholarly journals DICE: A Drug Indication Classification and Encyclopedia for AI-Based Indication Extraction

2021 ◽  
Vol 4 ◽  
Author(s):  
Arjun Bhatt ◽  
Ruth Roberts ◽  
Xi Chen ◽  
Ting Li ◽  
Skylar Connor ◽  
...  
Keyword(s):  
Language Processing ◽  
Clinical Decision Making ◽  
Short Term Memory ◽  
Drug Repositioning ◽  
External Validation ◽  
Clinical Decision ◽  
Language Models ◽  
Free Text ◽  
Drug Labeling ◽  
Real World Evidence

Drug labeling contains an ‘INDICATIONS AND USAGE’ that provides vital information to support clinical decision making and regulatory management. Effective extraction of drug indication information from free-text based resources could facilitate drug repositioning projects and help collect real-world evidence in support of secondary use of approved medicines. To enable AI-powered language models for the extraction of drug indication information, we used manual reading and curation to develop a Drug Indication Classification and Encyclopedia (DICE) based on FDA approved human prescription drug labeling. A DICE scheme with 7,231 sentences categorized into five classes (indications, contradictions, side effects, usage instructions, and clinical observations) was developed. To further elucidate the utility of the DICE, we developed nine different AI-based classifiers for the prediction of indications based on the developed DICE to comprehensively assess their performance. We found that the transformer-based language models yielded an average MCC of 0.887, outperforming the word embedding-based Bidirectional long short-term memory (BiLSTM) models (0.862) with a 2.82% improvement on the test set. The best classifiers were also used to extract drug indication information in DrugBank and achieved a high enrichment rate (&gt;0.930) for this task. We found that domain-specific training could provide more explainable models without performance sacrifices and better generalization for external validation datasets. Altogether, the proposed DICE could be a standard resource for the development and evaluation of task-specific AI-powered, natural language processing (NLP) models.

scholarly journals Hierarchical Phoneme Classification for Improved Speech Recognition

2021 ◽  
Vol 11 (1) ◽  
pp. 428
Author(s):  
Donghoon Oh ◽  
Jeong-Sik Park ◽  
Ji-Hwan Kim ◽  
Gil-Jin Jang
Keyword(s):  
Speech Recognition ◽  
Language Processing ◽  
Confusion Matrix ◽  
Critical Factor ◽  
Recognition System ◽  
Classification Performance ◽  
Language Models ◽  
Successful Implementation ◽  
Phoneme Classification ◽  
Improved Performance

Speech recognition consists of converting input sound into a sequence of phonemes, then finding text for the input using language models. Therefore, phoneme classification performance is a critical factor for the successful implementation of a speech recognition system. However, correctly distinguishing phonemes with similar characteristics is still a challenging problem even for state-of-the-art classification methods, and the classification errors are hard to be recovered in the subsequent language processing steps. This paper proposes a hierarchical phoneme clustering method to exploit more suitable recognition models to different phonemes. The phonemes of the TIMIT database are carefully analyzed using a confusion matrix from a baseline speech recognition model. Using automatic phoneme clustering results, a set of phoneme classification models optimized for the generated phoneme groups is constructed and integrated into a hierarchical phoneme classification method. According to the results of a number of phoneme classification experiments, the proposed hierarchical phoneme group models improved performance over the baseline by 3%, 2.1%, 6.0%, and 2.2% for fricative, affricate, stop, and nasal sounds, respectively. The average accuracy was 69.5% and 71.7% for the baseline and proposed hierarchical models, showing a 2.2% overall improvement.

A Hybrid Siamese Neural Network for Natural Language Inference in Cyber-Physical Systems

2021 ◽  
Vol 21 (2) ◽  
pp. 1-25
Author(s):  
Pin Ni ◽  
Yuming Li ◽  
Gangmin Li ◽  
Victor Chang
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Short Term Memory ◽  
Physical World ◽  
Heterogeneous Data ◽  
Cyber Physical Systems ◽  
Physical Systems ◽  
Language Data ◽  
Text Language ◽  
Different Sources

Cyber-Physical Systems (CPS), as a multi-dimensional complex system that connects the physical world and the cyber world, has a strong demand for processing large amounts of heterogeneous data. These tasks also include Natural Language Inference (NLI) tasks based on text from different sources. However, the current research on natural language processing in CPS does not involve exploration in this field. Therefore, this study proposes a Siamese Network structure that combines Stacked Residual Long Short-Term Memory (bidirectional) with the Attention mechanism and Capsule Network for the NLI module in CPS, which is used to infer the relationship between text/language data from different sources. This model is mainly used to implement NLI tasks and conduct a detailed evaluation in three main NLI benchmarks as the basic semantic understanding module in CPS. Comparative experiments prove that the proposed method achieves competitive performance, has a certain generalization ability, and can balance the performance and the number of trained parameters.

scholarly journals Identifying protein subcellular localisation in scientific literature using bidirectional deep recurrent neural network

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rakesh David ◽  
Rhys-Joshua D. Menezes ◽  
Jan De Klerk ◽  
Ian R. Castleden ◽  
Cornelia M. Hooper ◽  
...  
Keyword(s):  
Neural Network ◽  
Language Processing ◽  
Data Dissemination ◽  
Short Term Memory ◽  
Biological Data ◽  
Experimental Methodology ◽  
Subcellular Localisation ◽  
Crop Species ◽  
Deep Recurrent Neural Network ◽  
Functional Features

AbstractThe increased diversity and scale of published biological data has to led to a growing appreciation for the applications of machine learning and statistical methodologies to gain new insights. Key to achieving this aim is solving the Relationship Extraction problem which specifies the semantic interaction between two or more biological entities in a published study. Here, we employed two deep neural network natural language processing (NLP) methods, namely: the continuous bag of words (CBOW), and the bi-directional long short-term memory (bi-LSTM). These methods were employed to predict relations between entities that describe protein subcellular localisation in plants. We applied our system to 1700 published Arabidopsis protein subcellular studies from the SUBA manually curated dataset. The system combines pre-processing of full-text articles in a machine-readable format with relevant sentence extraction for downstream NLP analysis. Using the SUBA corpus, the neural network classifier predicted interactions between protein name, subcellular localisation and experimental methodology with an average precision, recall rate, accuracy and F1 scores of 95.1%, 82.8%, 89.3% and 88.4% respectively (n = 30). Comparable scoring metrics were obtained using the CropPAL database as an independent testing dataset that stores protein subcellular localisation in crop species, demonstrating wide applicability of prediction model. We provide a framework for extracting protein functional features from unstructured text in the literature with high accuracy, improving data dissemination and unlocking the potential of big data text analytics for generating new hypotheses.

scholarly journals Multi-Transformer: A New Neural Network-Based Architecture for Forecasting S&P Volatility

Mathematics ◽  
2021 ◽  
Vol 9 (15) ◽  
pp. 1794
Author(s):  
Eduardo Ramos-Pérez ◽  
Pablo J. Alonso-González ◽  
José Javier Núñez-Velázquez
Keyword(s):  
Neural Network ◽  
Language Processing ◽  
Short Term Memory ◽  
Risk Measures ◽  
Hybrid Models ◽  
Stock Volatility ◽  
Management Actions ◽  
Equity Risk ◽  
Hedging Strategies ◽  
Volatility Models

Events such as the Financial Crisis of 2007–2008 or the COVID-19 pandemic caused significant losses to banks and insurance entities. They also demonstrated the importance of using accurate equity risk models and having a risk management function able to implement effective hedging strategies. Stock volatility forecasts play a key role in the estimation of equity risk and, thus, in the management actions carried out by financial institutions. Therefore, this paper has the aim of proposing more accurate stock volatility models based on novel machine and deep learning techniques. This paper introduces a neural network-based architecture, called Multi-Transformer. Multi-Transformer is a variant of Transformer models, which have already been successfully applied in the field of natural language processing. Indeed, this paper also adapts traditional Transformer layers in order to be used in volatility forecasting models. The empirical results obtained in this paper suggest that the hybrid models based on Multi-Transformer and Transformer layers are more accurate and, hence, they lead to more appropriate risk measures than other autoregressive algorithms or hybrid models based on feed forward layers or long short term memory cells.

Towards corpus and model: Hierarchical structured-attention-based features for Indonesian named entity recognition

2021 ◽  
pp. 1-12
Author(s):  
Yingwen Fu ◽  
Nankai Lin ◽  
Xiaotian Lin ◽  
Shengyi Jiang
Keyword(s):  
Language Processing ◽  
State Of The Art ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Language Models ◽  
Neural Models ◽  
Performance Models ◽  
Named Entity ◽  
High Resource ◽  
Benchmark Datasets

Named entity recognition (NER) is fundamental to natural language processing (NLP). Most state-of-the-art researches on NER are based on pre-trained language models (PLMs) or classic neural models. However, these researches are mainly oriented to high-resource languages such as English. While for Indonesian, related resources (both in dataset and technology) are not yet well-developed. Besides, affix is an important word composition for Indonesian language, indicating the essentiality of character and token features for token-wise Indonesian NLP tasks. However, features extracted by currently top-performance models are insufficient. Aiming at Indonesian NER task, in this paper, we build an Indonesian NER dataset (IDNER) comprising over 50 thousand sentences (over 670 thousand tokens) to alleviate the shortage of labeled resources in Indonesian. Furthermore, we construct a hierarchical structured-attention-based model (HSA) for Indonesian NER to extract sequence features from different perspectives. Specifically, we use an enhanced convolutional structure as well as an enhanced attention structure to extract deeper features from characters and tokens. Experimental results show that HSA establishes competitive performance on IDNER and three benchmark datasets.

Adaptive particle swarm optimization algorithm based long short-term memory networks for sentiment analysis

2021 ◽  
pp. 1-17
Author(s):  
J. Shobana ◽  
M. Murali
Keyword(s):  
Particle Swarm Optimization ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Short Term Memory ◽  
Contextual Information ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Swarm Optimization ◽  
Adaptive Particle Swarm Optimization ◽  
Proposed Model

Text Sentiment analysis is the process of predicting whether a segment of text has opinionated or objective content and analyzing the polarity of the text’s sentiment. Understanding the needs and behavior of the target customer plays a vital role in the success of the business so the sentiment analysis process would help the marketer to improve the quality of the product as well as a shopper to buy the correct product. Due to its automatic learning capability, deep learning is the current research interest in Natural language processing. Skip-gram architecture is used in the proposed model for better extraction of the semantic relationships as well as contextual information of words. However, the main contribution of this work is Adaptive Particle Swarm Optimization (APSO) algorithm based LSTM for sentiment analysis. LSTM is used in the proposed model for understanding complex patterns in textual data. To improve the performance of the LSTM, weight parameters are enhanced by presenting the Adaptive PSO algorithm. Opposition based learning (OBL) method combined with PSO algorithm becomes the Adaptive Particle Swarm Optimization (APSO) classifier which assists LSTM in selecting optimal weight for the environment in less number of iterations. So APSO - LSTM ‘s ability in adjusting the attributes such as optimal weights and learning rates combined with the good hyper parameter choices leads to improved accuracy and reduces losses. Extensive experiments were conducted on four datasets proved that our proposed APSO-LSTM model secured higher accuracy over the classical methods such as traditional LSTM, ANN, and SVM. According to simulation results, the proposed model is outperforming other existing models.

Sentence similarity evaluation using Sent2Vec and siamese neural network with parallel structure

2021 ◽  
pp. 1-10
Author(s):  
Hye-Jeong Song ◽  
Tak-Sung Heo ◽  
Jong-Dae Kim ◽  
Chan-Young Park ◽  
Yu-Seop Kim
Keyword(s):  
Neural Network ◽  
Language Processing ◽  
Short Term Memory ◽  
Parallel Structure ◽  
Short Term ◽  
Similarity Estimation ◽  
Accurate Judgment ◽  
Proposed Model ◽  
Sentence Similarity ◽  
Long Short Term Memory

Sentence similarity evaluation is a significant task used in machine translation, classification, and information extraction in the field of natural language processing. When two sentences are given, an accurate judgment should be made whether the meaning of the sentences is equivalent even if the words and contexts of the sentences are different. To this end, existing studies have measured the similarity of sentences by focusing on the analysis of words, morphemes, and letters. To measure sentence similarity, this study uses Sent2Vec, a sentence embedding, as well as morpheme word embedding. Vectors representing words are input to the 1-dimension convolutional neural network (1D-CNN) with various sizes of kernels and bidirectional long short-term memory (Bi-LSTM). Self-attention is applied to the features transformed through Bi-LSTM. Subsequently, vectors undergoing 1D-CNN and self-attention are converted through global max pooling and global average pooling to extract specific values, respectively. The vectors generated through the above process are concatenated to the vector generated through Sent2Vec and are represented as a single vector. The vector is input to softmax layer, and finally, the similarity between the two sentences is determined. The proposed model can improve the accuracy by up to 5.42% point compared with the conventional sentence similarity estimation models.

Sign in / Sign up

Export Citation Format

Share Document