Natural Language Processing-Based Information Extraction and Abstraction for Lease Documents

Lease abstraction is the method of compartmentalization of key data from a lease document. Lease document for a property contains key business, money, and legal data about a property. A lease abstract report contains details concerning the property location and basic lease details, price schedules, key events, terms and conditions, automobile parking arrangements, and landowner and tenant obligations. Abstracting a true estate contract into electronic type facilitates easy access to key data, exchanging the tedious method of reading the whole contents of the contract every time. Language process may be used for data extraction and abstraction of knowledge from lease documents.

Ontology Creation

Neural networks are like the models of the brain and nervous system. It is highly parallel and processes information much more like the brain than a serial computer. It is very useful in learning information, using and executing very simple and complex behaviors, applications like powerful problem solvers and biological models. There are different types of neural networks like Biological, Feed Forward, Recurrent, and Elman. Biological Neural Networks require some biological data to predict information. In Feed Forward Networks, information flows in one way. In Recurrent Networks, information flows in multiple directions. Elman Networks feature Partial re-currency with a sense of time.

Emotion Recognition From Speech Using Perceptual Filter and Neural Network

This chapter on multi speaker independent emotion recognition encompasses the use of perceptual features with filters spaced in Equivalent rectangular bandwidth (ERB) and BARK scale and vector quantization (VQ) classifier for classifying groups and artificial neural network with back propagation algorithm for emotion classification in a group. Performance can be improved by using the large amount of data in a pertinent emotion to adequately train the system. With the limited set of data, this proposed system has provided consistently better accuracy for the perceptual feature with critical band analysis done in ERB scale.

Deep Learning Network

Artificial intelligence (AI) is defined as a machine that can do everything a human being can do and produce better results. Means AI enlightening that data can produce a solution for its own results. Inside the AI ellipsoidal, Machine learning (ML) has a wide variety of algorithms produce more accurate results. As a result of technology, improvement increasing amounts of data are available. But with ML and AI, it is very difficult to extract such high-level, abstract features from raw data, moreover hard to know what feature should be extracted. Finally, we now have deep learning; these algorithms are modeled based on how human brains process the data. Deep learning is a particular kind of machine learning that provides flexibility and great power, with its attempts to learn in multiple levels of representation with the operations of multiple layers. Deep learning brief overview, platforms, Models, Autoencoders, CNN, RNN, and Appliances are described appropriately. Deep learning will have many more successes in the near future because it requires very little engineering by hand.

Neural Network Applications in Hate Speech Detection

This chapter presents a literature survey of the current state of hate speech detection models with a focus on neural network applications in the area. The growth and freedom of social media has facilitated the dissemination of positive and negative ideas. Proponents of hate speech are one of the key abusers of the privileges allotted by social media, and the companies behind these networks have a vested interest in identifying such speech. Manual moderation is too cumbersome and slow to deal with the torrent of content generation on these social media sites, which is why many have turned to machine learning. Neural network applications in this area have been very promising and yielded positive results. However, there are newly discovered and unaddressed problems with the current state of hate speech detection. Authors' survey identifies the key techniques and methods used in identifying hate speech, and they discuss promising new directions for the field as well as newly identified issues.

Develop a Neural Model to Score Bigram of Words Using Bag-of-Words Model for Sentiment Analysis

A Bag-of-Words model is widely used to extract the features from text, which is given as input to machine learning algorithm like MLP, neural network. The dataset considered is movie reviews with both positive and negative comments further converted to Bag-of-Words model. Then the Bag-of-Word model of the dataset is converted into vector representation which corresponds to a number of words in the vocabulary. Each word in the review documents is assigned with a score and the scores are later represented in vector representation which is later fed as input to neural model. In the Kera's deep learning library, the neural models will be simple feedforward network models with fully connected layers called ‘Dense'. Bigram language models are developed to classify encoded documents as either positive or negative. At first, reviews are converted to lines of token and then encoded to bag-of-words model. Finally, a neural model is developed to score bigram of words with word scoring modes.

Deep Learning Approach for Extracting Catch Phrases from Legal Documents

Catch phrases are the important phrases that precisely explain the document. They represent the context of the whole document. They can also be used to retrieve relevant prior cases by the judges and lawyers for assuring justice in the domain of law. Currently, catch phrases are extracted using statistical methods, machine learning techniques, and deep learning techniques. The authors propose a sequence to sequence (Seq2Seq) deep neural network to extract catch phrases from legal documents. They have employed several layers, namely embedding layer, encoder-decoder layer, projection layer, and loss layer to build the deep neural network. The methodology is evaluated on IRLeD@FIRE-2017 dataset and the method has obtained 0.787 and 0.607 as mean average precision and recall scores respectively. Results show that the proposed method outperforms the existing systems.

Semantic Similarity Using Register Linear Question Classification (RLQC) for Question Classification

Question Classification(QC) mainly deals with syntactic parsing for finding the similarity. To improve the accuracy of classification, a semantic similarity approach of a question along with the question dataset is calculated. The semantic similarity of the question is initially achieved by syntactic parsing to extract the noun, verb, adverb, and adjective. However, adjectives and adverbs do give sentences an exact meaning that should also be considered for computing the semantic similarity. The proposed RLQC (Register Linear and Question Classification) model for semantic similarity of questions uses HSO (Hirst and St. Onge) measure with Gloss based measure to enhance the semantic similarity relatedness by considering the Noun, Verb, Adverb and Adjective. The semantic similarity of the question pairs for RLQC is 0.2% higher compared to HSO model. The highest semantic similarity of the proposed model achieves a better accuracy.

Knowledge Graph Generation

Nowadays, as computer systems are expected to be intelligent, techniques that help modern applications to understand human languages are in much demand. Amongst all the techniques, the latent semantic models are the most important. They exploit the latent semantics of lexicons and concepts of human languages and transform them into tractable and machine-understandable numerical representations. Without that, languages are nothing but combinations of meaningless symbols for the machine. To provide such learning representation, embedding models for knowledge graphs have attracted much attention in recent years since they intuitively transform important concepts and entities in human languages into vector representations, and realize relational inferences among them via simple vector calculation. Such novel techniques have effectively resolved a few tasks like knowledge graph completion and link prediction, and show the great potential to be incorporated into more natural language processing (NLP) applications.

Current Trends in Deep Learning Frameworks With Opportunities and Future Prospectus

Artificial Intelligence (AI) is going through its golden era by playing an important role in various real-time applications. Most AI applications are using Machine learning and it represents the most promising path to strong AI. On the other hand, Deep Learning (DL), which is itself a kind of Machine Learning (ML), is becoming more and more popular and successful at different use cases, and is at the peak of developments. Hence, DL is becoming a leader in this domain. To foster the growth of the DL community to a greater extent, many open source frameworks are available which implemented DL algorithms. Each framework is based on an algorithm with specific applications. This chapter provides a brief qualitative review of the most popular and comprehensive DL frameworks, and informs end users of trends in DL Frameworks. This helps them make an informed decision to choose the best DL framework that suits their needs, resources, and applications so they choose a proper career.