A Computational Approach to Grammatical Coding of English Words

Klein, Sheldon; Simmons, Robert F.

doi:10.1145/321172.321180

Cited by 85 publications

(41 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rule-based approaches (cf. [115,138,141]) typically use a two-stage architecture. The first stage employs a dictionary to assign a list of potential parts-of-speech to each word, as illustrated in Table 2.5.…”

Section: Part-of-speech Taggingmentioning

confidence: 99%

Comparing and Aligning Process Representations

2018

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

Section: Part-of-speech Taggingmentioning

confidence: 99%

Comparing and Aligning Process Representations

2018

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

“…The collection of tags used for a particular task is known as a tag set. Some of the pos tags are Noun, adverb, adjective, conjunction etc [1][2] [3]. POS tagging determines lexical types of words in a text.…”

Section: Literature Reviewmentioning

confidence: 99%

Short Text Segmentation for Improved Query Processing

Selvi¹

2018

IJRASET

View full text Add to dashboard Cite

Understanding short texts is crucial to many applications, but challenges are many. Short texts do not always detect the syntax of a written language. As a result, traditional natural language processing tools, ranging from part-of-speech tagging to dependency parsing, cannot be easily applied. Semantic knowledge is required in order to better understand short texts. In this work, a model for short text understanding which exploits semantic knowledge is used. The results show that semantic knowledge is indispensable for short text understanding, and our knowledge-intensive approaches are both effective and efficient in discovering semantics of short texts. A query data set containing short text is pre-processed by removing punctuation marks, numbers, stop words removal and stemming. Then POS tagging is performed and Co-Occurrence network is formed to obtain the semantic similarity. Term Similarities are calculated and finally clustering is done using K-Means, hierarchical, PAM, CLARA, DIANA and AGNES methods and the result reveals that hierarchical clustering gives optimal clusters.

show abstract

“…POS tagging has a long history, dating back to the mid-1960s. The first well-known tagger that assigned tags to words on the basis of local syntactic information, as opposed to just looking up tags in a dictionary, was that of Klein and Simmons (1963). The first probabilistic tagger was probably that of Stolz et al (1965), which used conditional probabilities calculated from tag sequences to assign tags to words after some pre-processing steps.…”

Section: Part-of-speech Taggingmentioning

confidence: 99%

Logarithmic opinion pools for conditional random fields

Smith

Cohn

Osborne

2005

Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05

View full text Add to dashboard Cite

Since their recent introduction, conditional random fields (CRFs) have been successfully applied to a multitude of structured labelling tasks in many different domains.Examples include natural language processing (NLP), bioinformatics and computer vision. Within NLP itself we have seen many different application areas, like named entity recognition, shallow parsing, information extraction from research papers and language modelling. Most of this work has demonstrated the need, directly or indirectly, to employ some form of regularisation when applying CRFs in order to overcome the tendency for these models to overfit. To date a popular method for regularising CRFs has been to fit a Gaussian prior distribution over the model parameters.In this thesis we explore other methods of CRF regularisation, investigating their properties and comparing their effectiveness. We apply our ideas to sequence labelling problems in NLP, specifically part-of-speech tagging and named entity recognition.We start with an analysis of conventional approaches to CRF regularisation, and investigate possible extensions to such approaches. In particular, we consider choices of prior distribution other than the Gaussian, including the Laplacian and Hyperbolic;we look at the effect of regularising different features separately, to differing degrees, and explore how we may define an appropriate level of regularisation for each feature;we investigate the effect of allowing the mean of a prior distribution to take on nonzero values; and we look at the impact of relaxing the feature expectation constraints satisfied by a standard CRF, leading to a modified CRF model we call the inequality CRF. Our analysis leads to the general conclusion that although there is some capacity for improvement of conventional regularisation through modification and extension, this is quite limited. Conventional regularisation with a prior is in general hampered by the need to fit a hyperparameter or set of hyperparameters, which can be an expensive process.We then approach the CRF overfitting problem from a different perspective. Specifically, we introduce a form of CRF ensemble called a logarithmic opinion pool (LOP), where CRF distributions are combined under a weighted product. We show how a LOP has theoretical properties which provide a framework for designing new overfitting reduction schemes in terms of diverse models, and demonstrate how such diverse models may be constructed in a number of different ways. Specifically, we show that by constructing CRF models from manually crafted partitions of a feature set and combining them with equal weight under a LOP, we may obtain an ensemble that significantly iii outperforms a standard CRF trained on the entire feature set, and is competitive in performance to a standard CRF regularised with a Gaussian prior. The great advantage of LOP approach is that, unlike the Gaussian prior method, it does not require us to search a hyperparameter space.Having demonstrated the success of LOPs in the simple case, we then m...

show abstract

A Computational Approach to Grammatical Coding of English Words

Cited by 85 publications

References 1 publication

Comparing and Aligning Process Representations

Comparing and Aligning Process Representations

Short Text Segmentation for Improved Query Processing

Logarithmic opinion pools for conditional random fields

Contact Info

Product

Resources

About