Download presentation
Presentation is loading. Please wait.
Published byShanon Garrison Modified over 9 years ago
1
Page 1 NAACL-HLT 2010 Los Angeles, CA Training Paradigms for Correcting Errors in Grammar and Usage Alla Rozovskaya and Dan Roth University of Illinois at Urbana-Champaign TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: AAA
2
Page 2 Error correction tasks Context-sensitive spelling mistakes I would like a peace*/piece of cake. English as a Second Language (ESL) mistakes Mistakes involving prepositions To*/in my mind, this is a serious problem. Mistakes involving articles Nearly 30000 species of plants are under the*/a serious threat of disappearing. Laziness is the engine of the*/ progress.
3
Page 3 The standard training paradigm for error correction Example: Correcting article mistakes [Izumi et al., ’03; Han et al., ’06; De Felice and Pulman, ’08; Gamon et al., ’08] Cast the problem as a classification task Provide a set of candidates: {a,the,NONE} Task: select the appropriate candidate in context Define features based on the surrounding context and train a classifier on correct (native) data Laziness is the engine ofprogress[the] Features: w 1 B=of, w 1 A=progress, w 2 Bw 1 B=engine-of, …
4
Page 4 The standard training paradigm for error correction Correcting article mistakes [Izumi et al., ’03; Han et al., ’06; De Felice and Pulman, ’08; Gamon et al., ’08] Correcting preposition mistakes [Eeg-Olofsson and Knutsson, ’03; Gamon et al., ’08; Tetreault and Chodorow, ’08, others] Context-sensitive spelling correction [Golding and Roth, ’96,’99; Carlson et al., ’01, others]
5
Page 5 But this is a paradigm for a selection task! Selection task (e.g. WSD): We have a set of candidates Task: select the correct candidate from a set of candidates The selection paradigm is appropriate for WSD, because there is no proposed candidate in context
6
Page 6 The typical error correction training paradigm is the paradigm of a selection task! Why? Easy to obtain training data – can use correct text No need for annotation
7
Page 7 Outline The error correction task: Problem statement The error correction task: Problem statement The typical training paradigm – does selection rather than correction The typical training paradigm – does selection rather than correction Selection versus correction What is the appropriate training paradigm for the correction task? The ESL corpus Training paradigms for the error correction task Key idea Methods of error generation Experiments Conclusions
8
Page 8 Selection tasks versus error correction tasks Article selection task Nearly 30000 species of plants are under ___ serious threat of disappearing. Article correction task Nearly 30000 species of plants are under the serious threat of disappearing. Set of candidates: {a,the,NONE} source
9
Page 9 Correction versus selection Article selection classifier Accuracy on native English data 87-90% Baseline for the article selection task 60-70% (use the most common article) Non-native data accuracy >90% If we use the writer’s selection, the results are very good already! Conclusion: Need to use the proposed candidate (or will make more mistakes than there are in the data) Error rate=10% With a selection model – can use it as a threshold Can we do better if we use the proposed candidate in training?
10
Page 10 The proposed article is a useful resource We want to use the proposed article in training 90% of articles are used correctly Article mistakes are not random Selection paradigm: Can we use the proposed candidate in training? - No: In native data, the proposed article always corresponds to the label
11
Page 11 How can we use the proposed article in training? Using annotated data for training Laziness is the engine of progress. Annotating data for training is expensive *Need a method to generate training data for the error correction task without expensive annotation. sourcelabel
12
Page 12 Contributions of this work We propose a method to generate training data for the error correction task Avoid expensive data annotation We use the generated data to train classifiers in the paradigm of correction With the proposed candidate in training We show that error correction training paradigms are superior to the selection paradigm of training
13
Page 13 Outline The error correction task: Problem statement The error correction task: Problem statement The typical training paradigm – does selection rather than correction The typical training paradigm – does selection rather than correction Selection versus correction Selection versus correction What is the appropriate training paradigm for correction? The ESL corpus Training paradigms for the error correction task Key idea Methods of error generation Experiments Conclusions
14
Page 14 The annotated ESL corpus Annotated a corpus of ESL sentences (60K words) Extracted from two corpora of ESL essays: ICLE [Granger et al.,’02] CLEC [Gui and Yang,’03] Sentences written by ESL students of 9 first languages Each sentence is fully corrected and error tagged Annotated by native English speakers Experiments: Chinese, Czech, Russian
15
Page 15 The annotated ESL corpus Annotating ESL sentences with an annotation tool Sentence for annotation
16
Page 16 The annotated ESL corpus Each sentence is fully corrected and error-tagged For details about the annotation, please see [Rozovskaya and Roth, ’10, NAACL-BEA5] Before annotation “This time asks for looking at things with our eyes opened.” With annotation comments “This time @period, age, time@ asks $us$ for looking *look* at things with our eyes opened.” After annotation “This period asks us to look at things with our eyes opened.”
17
Page 17 Outline The error correction task: Problem statement The error correction task: Problem statement The typical training paradigm – does selection rather than correction The typical training paradigm – does selection rather than correction Selection versus correction Selection versus correction What is the appropriate training paradigm for correction? The ESL data used in the evaluation The ESL data used in the evaluation Training paradigms for the error correction task Key idea Methods of error generation Experiments Conclusions
18
Page 18 Training paradigms for the error correction task Generate artificial article errors in native training data The source article can be used in training as a feature Constraint: We want training data to be similar to non-native text Other works that use artificial errors do not take into account error patterns in non-native data [Sjöbergh and Knutsson, ’05; Brockett et al., ’06, Foster and Andersen, ’09] Key idea: We want to be able to use the proposed candidate in training
19
Page 19 Training paradigms for the error correction task We examine article errors in the annotated data: Add errors selectively Mimic the article distribution the error rate the error patterns of the non-native text
20
Page 20 Error rates in article usage Very common mistakes made by non-native speakers of English TOEFL essays by Russian, Chinese, and Japanese speakers: 13% of noun phrases have article mistakes [Han et al., ’06] Essays by advanced Chinese, Czech, Russian learners of ESL: 10% of noun phrases have article mistakes.
21
Page 21 Distribution of articles in the annotated ESL data Source language Examples total Error rate Errors total Classes atheNone Chinese17139.2%1588.528.263.3 Czech10619.6%1029.122.968.0 Russian214610.4%22410.521.767.9 English Wikipedia 9.629.161.4 This error rate sets the baseline for the task around 90%
22
Page 22 Distribution of article errors in the annotated ESL text Not all confusions are equally likely Errors are dependent on the first language of the writer
23
Page 23 Characteristics of the non-native data: Summary Article distribution Error rates Error patterns of the non-native text We use this knowledge to generate errors for error correction training paradigms
24
Page 24 Error correction training paradigm 1: General General Add errors uniformly at random with error rate conf, where conf 2 {5%,10%,12%,14%,16%,18%} Example: Let error rate=10% replace(the, a, 0.05) replace(the,NONE,0.05) theaNONE replace(a, the, 0.05) replace(a,NONE,0.05) replace(NONE, a, 0.05) replace(NONE,the,0.05)
25
Page 25 Error correction training paradigm 2: ArticleDistr ArticleDistr atheNONE Czech9.122.968.0 English Wikipedia 9.629.161.4 Mimic the distribution of the ESL source articles in training the replace(the, a, p 1 ) replace(the,NONE,p 2 ) Constraints: (1) Prob Train (the)=Prob Czech (the) (2) p 1, p 2 ¸ minConf, where minConf 2 {0.02, 0.03, 0.04, 0.05} Example : A linear program is set up to find p 1 and p 2
26
Page 26 Error correction training paradigm 3: ErrorDistr ErrorDistr Add article mistakes to mimic the error rate and confusion patterns observed in the ESL data. Example : Chinese Error rate: 9.2% Article confusions by error type
27
Page 27 Error correction training paradigms: Summary Key idea: generate artificial errors in native training data We can use the source article in training as a feature Important constraints: Errors mimic the error patterns of the ESL text Error rate Distribution of different article confusions
28
Page 28 Error correction training paradigms: Costs 3 error generation methods Use different knowledge (and have different costs) Paradigm 1 (error rate in the data) Paradigm 2 (distribution of articles in the ESL data) – no annotation required Paradigm 3 (error rate and article confusions) – requires annotated data (the most costly method)
29
Page 29 Outline The error correction task: Problem statement The error correction task: Problem statement The typical training paradigm – does selection rather than correction The typical training paradigm – does selection rather than correction Selection versus correction Selection versus correction What is the appropriate training paradigm for correction? The ESL data used in the evaluation The ESL data used in the evaluation Training paradigms for the error correction task Training paradigms for the error correction task Key idea Methods of error generation Experiments Conclusions
30
Page 30 Experimental setup Train a TrainClean classifier using the selection paradigm 3 classifiers are Trained With artificial Errors (TWE classifiers) Online learning paradigm and the Averaged Perceptron Algorithm.
31
Page 31 Features Features are based on the 3-word window around the target. If we take [a] brief look back if-IN we-PRP take-VBP [a] brief-JJ look-NN back-RB Word features : headWord=look, w 3 B=if, w 2 B=we,w 1 B=take, w 1 A=brief, etc. Tag features : p 3 B=IN, p 2 B=PRP, etc. Composite features : w 2 Bw 1 B=we-take w 1 Bw 1 A= take-brief, etc. source feature – TWE systems only
32
Page 32 Performance on the data by Russian speakers Training Paradigm AccuracyError reduction TrainClean90.62%5.92% TWE (General)91.25%12.24% TWE (Article Distr.)91.52%14.94% TWE (Error Distr.)91.63%16.05% Baseline90.03% All TWE’s outperform the selection paradigm TrainClean for all languages On average, TWE (Error Distr.) provides the best improvement
33
Page 33 Improvement due to training with errors Source language BaselineTrain Clean TWEError reduction Chinese92.03%91.85%92.67%10.06% Czech90.88%91.82%92.22%4.89% Russian90.03%90.62%91.63%10.77%
34
Page 34 Conclusions We argued that the error correction task should be studied in the error correction paradigm rather than the current selection paradigm The baseline for the error correction task is high Mistakes are not random We have proposed a method to generate training data for error correction tasks using artificial errors The artificial errors mimic error rates and error patterns in the non- native text The method allows us to train with the proposed candidate, in the paradigm of error correction The error correction training paradigms are superior to the typical selection training paradigm
35
Page 35 Thank you! Questions?
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.