Entity extraction is an important step in document understanding. Higher accuracy entity extraction on fine-grained entities can be achieved by combining the utility of Named Entity Recognition (NER) and Relation Extraction (RE) models. In this paper, a cascading model is proposed that implements NER and Relation extraction. This model utilizes relations between entities to infer context-dependent fine-grain named entities in text corpora. The RE module runs independent of the NER module, which reduces error accumulation from sequential steps. This process improves on the fine-grained NER F1-score of existing state-of-the-art from .4753 to .8563 on our data, albeit on a strictly limited domain. This provides the potential for further applications in historical document processing. These applications will enable automated searching of historical documents, such as those used in economics research and family history.

Digital Democracy is a CalMatters and California Polytechnic State University initia-tive to promote transparency in state government by increasing access to the Califor-nia legislature. While Digital Democracy is made up of many resources, one founda-tional step of the project is obtaining accurate, timely transcripts of California Senateand Assembly hearings. The information extracted from these transcripts providescrucial data for subsequent steps in the pipeline. In the context of Digital Democracy,upleveling is when humans verify, correct, and annotate the transcript results afterthe legislative hearings have been automatically transcribed. The upleveling processis done with the assistance of a software application called the Transcription Tool.The human upleveling process is the most costly and time-consuming step of the Dig-ital Democracy pipeline. In this thesis, we hypothesize that we can make significantreductions to the time needed for upleveling by using Natural Language Processing(NLP) systems and techniques. The main contribution of this thesis is engineeringa new automatic transcription pipeline. Specifically, this thesis integrates a new au-tomatic speech recognition service, a new speaker diarization model, additional textpost-processing changes, and a new process for speaker identification. To evaluate the system’s improvements, we measure the accuracy and speed of the newly integrated features and record editor upleveling time both before and after the additions.

Natural language processing (NLP) is a vibrant area of research with many practical applications today like sentiment analyses, text labeling, questioning an- swering, machine translation and automatic text summarizing. At the moment, research is mainly focused on the English language, although many other lan- guages are trying to catch up. This work focuses on an area within NLP called information extraction, and more specifically on relation extraction, that is, to ex- tract relations between entities in a text. What this work aims at is to use machine learning techniques to build a Swedish language processing pipeline with part-of- speech tagging, dependency parsing, named entity recognition and coreference resolution to use as a base for later relation extraction from archival texts. The obvious difficulty lies in the scarcity of Swedish annotated datasets. For exam- ple, no large enough Swedish dataset for coreference resolution exists today. An important part of this work, therefore, is to create a Swedish coreference solver using distantly supervised machine learning, which means creating a Swedish dataset by applying an English coreference solver on an unannotated bilingual corpus, and then using a word-aligner to translate this machine-annotated En- glish dataset to a Swedish dataset, and then training a Swedish model on this dataset. Using Allen NLP:s end-to-end coreference resolution model, both for creating the Swedish dataset and training the Swedish model, this work achieves an F1-score of 0.5. For named entity recognition this work uses the Swedish BERT models released by the Royal Library of Sweden in February 2020 and achieves an overall F1-score of 0.95. To put all of these NLP-models within a single Lan- guage Processing Pipeline, Spacy is used as a unifying framework. / Natural Language Processing (NLP) är ett stort och aktuellt forskningsområde idag med många praktiska tillämpningar som sentimentanalys, textkategoriser- ing, maskinöversättning och automatisk textsummering. Forskningen är för när- varande mest inriktad på det engelska språket, men många andra språkområ- den försöker komma ikapp. Det här arbetet fokuserar på ett område inom NLP som kallas informationsextraktion, och mer specifikt relationsextrahering, det vill säga att extrahera relationer mellan namngivna entiteter i en text. Vad det här ar- betet försöker göra är att använda olika maskininlärningstekniker för att skapa en svensk Language Processing Pipeline bestående av part-of-speech tagging, de- pendency parsing, named entity recognition och coreference resolution. Denna pipeline är sedan tänkt att användas som en bas for senare relationsextrahering från svenskt arkivmaterial. Den uppenbara svårigheten med detta ligger i att det är ont om stora, annoterade svenska dataset. Till exempel så finns det inget till- räckligt stort svenskt dataset för coreference resolution. En stor del av detta arbete går därför ut på att skapa en svensk coreference solver genom att implementera distantly supervised machine learning, med vilket menas att använda en engelsk coreference solver på ett oannoterat engelskt-svenskt corpus, och sen använda en word-aligner för att översätta detta maskinannoterade engelska dataset till ett svenskt, och sen träna en svensk coreference solver på detta dataset. Det här arbetet använder Allen NLP:s end-to-end coreference solver, både för att skapa det svenska datasetet, och för att träna den svenska modellen, och uppnår en F1-score på 0.5. Vad gäller named entity recognition så använder det här arbetet Kungliga Bibliotekets BERT-modeller som bas, och uppnår genom detta en F1- score på 0.95. Spacy används som ett enande ramverk för att samla alla dessa NLP-komponenter inom en enda pipeline.

Le traitement automatique des données complexes et variées est un processus fondamental dans les applications d'extraction d'information. L'explosion combinatoire dans la composition des textes journalistiques et l'évolution du vocabulaire rend la tâche d'extraction d'indicateurs sémantiques, tel que les entités nommées, plus complexe par les approches symboliques. Les modèles stochastiques structurels tel que les champs conditionnels aléatoires (CRF) permettent d'optimiser des systèmes d'extraction d'information avec une importante capacité de généralisation. La première contribution de cette thèse est consacrée à la définition du contexte optimal pour l'extraction des régularités entre les mots et les annotations dans la tâche de reconnaissance d'entités nommées. Nous allons intégrer diverses informations dans le but d'enrichir les observations et améliorer la qualité de prédiction du système. Dans la deuxième partie nous allons proposer une nouvelle approche d'adaptation d'annotations entre deux protocoles différents. Le principe de cette dernière est basé sur l'enrichissement d'observations par des données générées par d'autres systèmes. Ces travaux seront expérimentés et validés sur les données de la campagne ESTER. D'autre part, nous allons proposer une approche de couplage entre le niveau signal représenté par un indice de la qualité de voisement et le niveau sémantique. L'objectif de cette étude est de trouver le lien entre le degré d'articulation du locuteur et l'importance de son discours / Recent researches in Information Extraction are designed to extract fixed types of information from data. Sequence annotation systems are developed to associate structured annotations to input data presented in sequential form. The named entity recognition (NER) task consists of identifying and classifying every word in a document into some predefined categories such as person name, locations, organizations, and dates. The complexity of the NER is largely related to the definition of the task and to the complexity of the relationships between words and the semantic associated. Our first contribution is devoted to solving the NER problem using discriminative graphical models. The proposed approach investigates the use of various contexts of the words to improve recognition. NER systems are fixed in accordance with a specific annotation protocol. Thus, new applications are developed for new protocols. The challenge is how we can adapt an annotation system which is performed for a specific application to other target application? We will propose in this work an adaptation approach of sequence labelling task based on annotation enrichment using conditional random fields (CRF). Experimental results show that the proposed approach outperform rules-based approach in NER task. Finally, we propose a multimodal approach of NER by integrating low level features as contextual information in radio broadcast news data. The objective of this study is to measure the correlation between the speaker voicing quality and the importance of his speech

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal.

The thesis presents named-entity recognition in Czech historical newspapers from Modern Access to Historical Sources Project. Our goal was to create a specific corpus and annotation manual for the project and evaluate neural networks methods for named-entity recognition within the task. We created the corpus using scanned Czech historical newspapers. The scanned pages were converted to digitize text by optical character recognition (OCR) method. The data were preprocessed by deleting some OCR errors. We also defined specific named entities types for our task and created an annotation manual with examples for the project. Based on that, we annotated the final corpus. To find the most suitable neural networks model for our task, we experimented with different neural networks architectures, namely long short-term memory (LSTM), bidirectional LSTM and CNN-BiLSTM models. Moreover, we experimented with randomly initialized word embeddings that were trained during the training process and pretrained word embeddings for contemporary Czech published as open source by fastText. We achieved the best result F1 score 0.444 using CNN-BiLSTM model and the pretrained word embeddings by fastText. We found out that we do not need to normalize spelling of our historical texts to get closer to contemporary language if we use the neural network model. We provided a qualitative analysis of observed linguistics phenomena as well. We found out that some word forms and pair of words which were not frequent in our training data set were miss-tagged or not tagged at all. Based on that, we can say that larger data sets could improve the results.

Named entity recognition (NER) is the task of identifying the named entities (NEs) in the texts and classifying them into semantic categories such as person, organization, and place names and time, date, monetary, and percent expressions. NER has two principal aims: identification of NEs and classification of them into semantic categories. The local grammar (LG) approach has recently been shown to be superior to other NER techniques such as the probabilistic approach, the symbolic approach, and the hybrid approach in terms of being able to work with untagged corpora. The LG approach does not require using any dictionaries and gazetteers, which are lists of proper nouns (PNs) used in NER applications, unlike most of the other NER systems. As a consequence, it is able to recognize NEs in previously unseen texts at minimal costs. Most of the NER systems are costly due to manual rule compilation especially in large tagged corpora. They also require some semantic and syntactic analyses to be applied before pattern generation process, which can be avoided by using the LG approach. In this thesis, we tried to acquire LGs for person names from a large untagged Turkish financial news corpus by using an approach successfully applied to a Reuter&rsquo / s financial English news corpus recently by H. N. Traboulsi. We explored its applicability to Turkish language by using frequency, collocation, and concordance analyses. In addition, we constructed a list of Turkish reporting verbs. It is an important part of this study because there is no major study about reporting verbs in Turkish.

Information Extraction (IE) is the process of extracting structured and important pieces of information from a set of unstructured text documents in natural language. The final goal of structured information extraction is to populate a database and reach data effectively. Our study focuses on named entity recognition (NER) which is an important subtask of IE. NER is the task that deals with extraction of named entities like person, location, organization names, temporal expressions (date and time) and numerical expressions (money and percent). NER research on Turkish is known to be rare. There are rule-based, learning based and hybrid systems for NER on Turkish texts. Some of the learning approaches used for NER in Turkish are conditional random fields (CRF), rote learning, rule extraction and generalization. In this thesis, we propose a learning based named entity recognizer for Turkish texts which employs a modified version of Bayesian learning as the learning scheme. To the best of our knowledge, this is the first learning based system that uses Bayesian approach for NER in Turkish. Several features (like token length, capitalization, lexical meaning, etc.) are used in the system to see the effects of different features on NER process. We also propose hybrid system where the Bayesian learning-based system is utilized along with a rule-based recognition system. There are two different versions of the hybrid system. Output of rule-based recognizer is utilized in different phases in these versions. We observed increase in F-Measure values for both hybrid versions. When partial scoring is active, hybrid system reached 91.44% F-Measure value / where rule-based system result is 87.43% and learning-based system result is 88.41%. The hybrid system can be improved by utilizing rule-based and learning-based components differently in the future. Hybrid system can also be improved by using different learning approaches and combining them with existing hybrid system or forming the hybrid system with a completely new approach.

An important core technology in the development of human language technology applications is an automatic morphological analyser. Such a morphological analyser consists of various modules, one of which is a tokeniser. At present no tokeniser exists for Afrikaans and it has therefore been impossible to develop a morphological analyser for Afrikaans. Thus, in this research project such a tokeniser is being developed, and the project therefore has two objectives: i)to postulate a tag set for integrated tokenisation, and ii) to develop an algorithm for integrated tokenisation. In order to achieve the first object, a tag set for the tagging of sentences, named-entities, words, abbreviations and punctuation is proposed specifically for the annotation of Afrikaans texts. It consists of 51 tags, which can be expanded in future in order to establish a larger, more specific tag set. The postulated tag set can also be simplified according to the level of specificity required by the user. It is subsequently shown that an effective tokeniser cannot be developed using only linguistic, or only statistical methods. This is due to the complexity of the task: rule-based modules should be used for certain processes (for example sentence recognition), while other processes (for example named-entity recognition) can only be executed successfully by means of a machine-learning module. It is argued that a hybrid system (a system where rule-based and statistical components are integrated) would achieve the best results on Afrikaans tokenisation. Various rule-based and statistical techniques, including a TiMBL-based classifier, are then employed to develop such a hybrid tokeniser for Afrikaans. The final tokeniser achieves an ∫-score of 97.25% when the complete set of tags is used. For sentence recognition an ∫-score of 100% is achieved. The tokeniser also recognises 81.39% of named entities. When a simplified tag set (consisting of only 12 tags) is used to annotate named entities, the ∫-score rises to 94.74%. The conclusion of the study is that a hybrid approach is indeed suitable for Afrikaans sentencisation, named-entity recognition and tokenisation. The tokeniser will improve if it is trained with more data, while the expansion of gazetteers as well as the tag set will also lead to a more accurate system / Thesis (M.A. (Applied Language and Literary Studies))--North-West University, Potchefstroom Campus, 2006.

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal