Showing papers on "Shallow parsing published in 2019"

Language learning as language use: A cross-linguistic model of child language development.

Abstract: While usage-based approaches to language development enjoy considerable support from computational studies, there have been few attempts to answer a key computational challenge posed by usage-based theory: the successful modeling of language learning as language use. We present a usage-based computational model of language acquisition which learns in a purely incremental fashion, through online processing based on chunking, and which offers broad, cross-linguistic coverage while uniting key aspects of comprehension and production within a single framework. The model's design reflects memory constraints imposed by the real-time nature of language processing, and is inspired by psycholinguistic evidence for children's sensitivity to the distributional properties of multiword sequences and for shallow language comprehension based on local information. It learns from corpora of child-directed speech, chunking incoming words together to incrementally build an item-based "shallow parse." When the model encounters an utterance made by the target child, it attempts to generate an identical utterance using the same chunks and statistics involved during comprehension. High performance is achieved on both comprehension- and production-related tasks: the model's shallow parsing is evaluated across 79 single-child corpora spanning English, French, and German, while its production performance is evaluated across over 200 single-child corpora representing 29 languages from the CHILDES database. The model also succeeds in capturing findings from children's production of complex sentence types. Together, our modeling results suggest that much of children's early linguistic behavior may be supported by item-based learning through online processing of simple distributional cues, consistent with the notion that acquisition can be understood as learning to process language. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Using Chinese Glyphs for Named Entity Recognition

Abstract: Most Named Entity Recognition (NER) systems use additional features like part-of-speech (POS) tags, shallow parsing, gazetteers, etc. Such kind of information requires external knowledge like unlabeled texts and trained taggers. Adding these features to NER systems have been shown to have a positive impact. However, sometimes creating gazetteers or taggers can take a lot of time and may require extensive data cleaning. In this paper for Chinese NER systems, we do not use these traditional features but we use lexicographic features of Chinese characters. Chinese characters are composed of graphical components called radicals and these components often have some semantic indicators. We propose CNN based models that incorporate this semantic information and use them for NER. Our models show an improvement over the baseline BERT-BiLSTM-CRF model. We set a new baseline score for Chinese OntoNotes v5.0 and show an improvement of +.64 F1 score. We present a state-of-the-art F1 score on Weibo dataset of 71.81 and show a competitive improvement of +0.72 over baseline on ResumeNER dataset.

IceNLP Natural Language Processing toolkit

Abstract: IceNLP is an open source Natural Language Processing (NLP) toolkit for analyzing and processing Icelandic text The toolkit is implemented in Java IceNLP er safn malgreiningartola, gefið ut með opnu leyfi, til þess að greina og vinna islenskan texta Tolin eru unnin i Java

A Shallow Parsing Model for Hindi Using Conditional Random Field

Abstract: In Natural Language Parsing, in order to perform sequential labeling and segmenting tasks, a probabilistic framework named Conditional Random Field (CRF) have an advantage over Hidden Markov Models (HMMs) and Maximum Entropy Markov Models (MEMMs). This research work is an attempt to develop an efficient model for shallow parsing which is based on CRF. For training the model, around 1,000 handcrafted chunked sentences of Hindi language were used. The developed model is tested on 864 sentences and evaluation is done by comparing the results with gold data. The accuracy is measured by precision, recall, and F-measure and is found to be 98.04, 98.04, and 98.04, respectively.

Word sense disambiguation, named entity recognition, and shallow parsing tasks for Turkish

Abstract: People interactions are based on sentences. The process of understanding sentences is thru converging, parsing the words and making sense of words. The ultimate goal of Natural Language Processing is to understand the meaning of sentences. There are three main areas that are the topics of this thesis, namely, Named Entity Recognition, Shallow Parsing, and Word Sense Disambiguation. The Natural Language Processing algorithms that learn entities, like person, location, time etc. are called Named Entity Recognition algorithms. Parsing sentences is one of the biggest challenges in Natural Language Processing. Since time efficiency and accuracy are inversely proportional with each other, one of the best ideas is to use shallow parsing algorithms to deal with this challenge. Many of words have more than one meaning. Recognizing the correct meaning that is used in a sentence is a difficult problem. In Word Sense Disambiguation literature there are lots of algorithms that can help to solve this problem. This thesis tries to find solutions to these three challenges by applying machine learning trained algorithms. Experiments are done on a dataset, containing 9,557 sentences.

“Majorly Adapted Translator”: Towards Major Adaptation in ITS

Abstract: Culturally Aware Learning Systems are intelligent systems that adapt learning materials or techniques to the culture of learners having different “country, hobbies, experiences, etc.”, helping them better understand the topics being taught. In higher education, many learning sessions involve students of different majors. As observed, many instructors tend to manually modify the exercises several times, once for every major to adapt to the culture, which is tedious and impractical. Therefore, in this paper we propose an approach to making learning sessions adaptable to the major of the learner. Specifically, this work introduces an Artificial Intelligent system, “Majorly Adapted Translator (MAT)”, which aims at translating and adapting exercises from one major to another. MAT has two main phases, the first identifies the parts of an exercise that needs changing and creates an exercise template. The second translates and adapts the exercise. This work, highlights the first phase, the Feature Extract phase, which relies on our own relation extraction method to identify variables which extracts relations specific to named entities by using dependency relations and shallow parsing. Moreover, we report the performance of the system that was tested on a number of probability exercises.