Improving mention detection for Basque based on a deep error analysis

2016 ◽  
Vol 23 (3) ◽  
pp. 351-384 ◽  
Author(s):  
ANDER SORALUZE ◽  
OLATZ ARREGI ◽  
XABIER ARREGI ◽  
ARANTZA DÍAZ DE ILARRAZA
Keyword(s):  
Error Analysis ◽  
Coreference Resolution ◽  
Linguistic Processing ◽  
Exact Matching ◽  
Standard Data ◽  
Percentage Points ◽  
Classification Of Error ◽  
F Measure ◽  
Error Types

AbstractThis paper presents the improvement process of a mention detector for Basque. The system is rule-based and takes into account the characteristics of mentions in Basque. A classification of error types is proposed based on the errors that occur during mention detection. A deep error analysis distinguishing error types and causes is presented and improvements are proposed. At the final stage, the system obtains an F-measure of 74.57% under the Exact Matching protocol and of 80.57% under Lenient Matching. We also show the performance of the mention detector with gold standard data as input, in order to omit errors caused by the previous stages of linguistic processing. In this scenario, we obtain an F-measure of 85.89% with Strict Matching and of 89.06% with Lenient Matching, i.e., a difference of 11.32 and 8.49 percentage points, respectively. Finally, how improvements in mention detection affect coreference resolution is analysed.

scholarly journals ERROR ANALYSIS IN WRITING OF THE TENTH GRADE STUDENTS OF MAN 1 PALU

2020 ◽  
Vol 1 (1) ◽  
pp. 10-18
Author(s):  
Nur Intan ◽  
Darwis Jauhari Bandu ◽  
Yuni Amelia
Keyword(s):  
Error Analysis ◽  
Qualitative Method ◽  
First Language ◽  
Grammatical Error ◽  
Tenth Grade ◽  
Classification Of Error ◽  
Cause Of Error ◽  
Descriptive Writing ◽  
Types Of Error

Error analysis is an activity to identify, classify and interpreted or describe the errors made by someone in speaking or in writing and it is carried out to obtain information on common difficulties faced by someone in speaking or in writing English sentences. For students, error analysis is needed to show them in what aspect in grammar which is difficult for them, to show the errors made by the students, to know the source or the cause of the error and how the students can learn from their mistakes in order that they will not make some errors repeatedly. The purpose of this research is to describe the type of grammatical error faced by students in writing. This research used descriptive qualitative method. This research was carried out in using descriptive writing text to find out what types of error made by students of the tenth grade students MAN 1 Palu in writing and what causes of the students error in writing. The result of the research showed that the tenth grade students MAN 1 Palu still made 41 errors in their writing. They are three classification of error based on surface strategy taxonomy. The high frequency of error is selection (63,41%), omission (26,82), and The lowest frequency of error is addition (9,75). On the other hand, the highest cause of error is carelessness (75,6%), %), first language (7 or 17,07 %), while the lowest cause of error is translation (7.31%).

scholarly journals Coconuts and curtain cakes: The production of wh-questions in ASD

2021 ◽  
Vol 6 ◽  
pp. 239694152098295
Author(s):  
Nufar Sukenik ◽  
Eléonore Morin ◽  
Naama Friedmann ◽  
Philippe Prevost ◽  
Laurice Tuller
Keyword(s):  
Error Analysis ◽  
Language Disorder ◽  
Syntactic Structure ◽  
Autism Spectrum ◽  
Production Rates ◽  
Fine Grained ◽  
Depth Analysis ◽  
Wh Questions ◽  
Analysis Of Error ◽  
Error Types

Background and aims Children with autism spectrum disorders (ASD) have been found to exhibit difficulties in wh-question production. It is unclear whether these difficulties are pragmatic or syntactic in nature. The current study used a question elicitation task to assess the production of subject and object wh-questions of children with ASD in two different languages (Hebrew and French) wherein the syntactic structure of wh-questions is different, a fact that may contribute to better understanding of the underlying deficits affecting wh-question production. Crucially, beyond the general correct/error rate we also performed an in-depth analysis of error types, comparing syntactic to pragmatic errors and comparing the distribution of errors in the ASD group to that of children with typical development (TD) and children with Developmental Language Disorder (DLD). Results Correct production rates were found to be similar for the ASD and DLD groups, but error analysis revealed important differences between the ASD groups in the two languages and the DLD group. The Hebrew- and French ASD groups were found to produce pragmatic errors, which were not found in children with DLD. The pragmatic errors were similar in the two ASD groups. Syntactic errors were affected by the structure of each language. Conclusions Our results have shown that although the two ASD groups come from different countries and speak different languages, the correct production rates and more importantly, the error types were very similar in the two ASD groups, and very different compared to TD children and children with DLD. Implications: Our results highlight the importance of creating research tasks that test different linguistic functions independently and strengthen the need for conducting fine-grained error analysis to differentiate between groups and gain insights into the deficits underlying each of them.

Classification of Error in Abdominal Imaging: Pearls and Pitfalls for Radiologists

2018 ◽  
Vol 69 (4) ◽  
pp. 409-416 ◽  
Author(s):  
Csilla Egri ◽  
Kathryn E. Darras ◽  
Elena P. Scali ◽  
Alison C. Harris
Keyword(s):  
Peer Review ◽  
Diagnostic Errors ◽  
Diagnostic Error ◽  
Abdominal Imaging ◽  
Patient Harm ◽  
Contributing Factors ◽  
Abdominal Radiology ◽  
Pictorial Review ◽  
Classification Of Error

Peer review for radiologists plays an important role in identifying contributing factors that can lead to diagnostic errors and patient harm. It is essential that all radiologists be aware of the multifactorial causes of diagnostic error in radiology and the methods available to reduce it. This pictorial review provides readers with an overview of common errors that occur in abdominal radiology and strategies to reduce them. This review aims to make readers more aware of pitfalls in abdominal imaging so that these errors can be avoided in the future. This essay also provides a systematic approach to classifying abdominal imaging errors that will be of value to all radiologists participating in peer review.

scholarly journals The Durable Differential Deterrent Effects of Strict Photo Identification Laws

2020 ◽  
Author(s):  
Justin Grimmer ◽  
Jesse Yoder
Keyword(s):  
North Carolina ◽  
Administrative Data ◽  
Differential Effect ◽  
General Election ◽  
Exact Matching ◽  
Difference In Differences ◽  
Primary Election ◽  
Photo Identification ◽  
Percentage Points ◽  
The Law

An increasing number of states have adopted laws that require voters to show photo identification to vote. We show that the differential effect of the laws on turnout among those who lack ID persists even after the laws are repealed. We leverage administrative data from North Carolina and a photo ID law in effect for a primary, but not the sub- sequent general, election. Using exact matching and a difference-in-differences design, we show that for the 3% of voters who lack ID in North Carolina, the ID law caused a 0.7 percentage point turnout decrease in the 2016 primary election relative to those with ID. After the law was suspended this effect persisted: those without ID were 2.6 percentage points less likely to turnout in the 2016 general election and 1.7 percentage points less likely to turnout in the 2018 general.

Classification of Error Correction Methods, a Broad View

2011 ◽  
pp. 85-94
Author(s):  
Georgi Radulov ◽  
Patrick Quinn ◽  
Hans Hegt ◽  
Arthur van Roermund
Keyword(s):  
Error Correction ◽  
Broad View ◽  
Classification Of Error

Disambiguation and Filtering Methods in Using Web Knowledge for Coreference Resolution

2012 ◽  
pp. 185-201 ◽  
Author(s):  
Olga Uryupina ◽  
Massimo Poesio ◽  
Claudio Giuliano ◽  
Kateryna Tymoshenko
Keyword(s):  
Semantic Information ◽  
Knowledge Bases ◽  
Coreference Resolution ◽  
Number Of Solutions ◽  
Web Resources ◽  
Percentage Points ◽  
Resolution System ◽  
Semantic Compatibility ◽  
Additional Constraints ◽  
Web Knowledge

The authors investigate two publicly available Web knowledge bases, Wikipedia and Yago, in an attempt to leverage semantic information and increase the performance level of a state-of-the-art coreference resolution engine. They extract semantic compatibility and aliasing information from Wikipedia and Yago, and incorporate it into a coreference resolution system. The authors show that using such knowledge with no disambiguation and filtering does not bring any improvement over the baseline, mirroring the previous findings (Ponzetto & Poesio, 2009). They propose, therefore, a number of solutions to reduce the amount of noise coming from Web resources: using disambiguation tools for Wikipedia, pruning Yago to eliminate the most generic categories and imposing additional constraints on affected mentions. The evaluation experiments on the ACE-02 corpus show that the knowledge, extracted from Wikipedia and Yago, improves the system’s performance by 2-3 percentage points.

Taxonomy and Epidemiology of Error in Radiology

2019 ◽  
pp. 29-74
Author(s):  
Michael A. Bruno
Keyword(s):  
Working Memory ◽  
Cognitive Biases ◽  
Confirmation Bias ◽  
Diagnostic Error ◽  
Attentional Focus ◽  
Relative Contribution ◽  
Anchoring Bias ◽  
Classification Of Error

This chapter provides an overview of the prevalence and classification of error types in radiology, including the frequency and types of errors made by radiologists. We will review the relative contribution of perceptual error—in which findings are simply not seen—as compared to other common types of error. This error epidemiology will be considered in the light of the underlying variability and uncertainties present in the radiological process. The role of key cognitive biases will also be reviewed, including anchoring bias, confirmation bias, and availability bias. The role of attentional focus, working memory, and problems caused by fatigue and interruption will also be explored. Finally, the problem of radiologist error will be considered in the context of the overall problem of diagnostic error in medicine.

Sign in / Sign up

Export Citation Format

Share Document