= Automatic language correction = [[https://is.muni.cz/auth/predmet/fi/ia161|IA161]] [[en/AdvancedNlpCourse|Advanced NLP Course]], Course Guarantee: Aleš Horák Prepared by: Aleš Horák, Ján Švec == State of the Art == Language correction nowadays has many potential applications on large amount of informal and unedited text generated online, among other things: web forums, tweets, blogs, and email. Automatic language correction can consist of many areas including: spell checking, grammar checking and word completion. In the theoretical lesson we will introduce and compare various methods to automatically propose and choose a correction for an incorrectly written word. Spell checking is the process of detecting and sometimes providing spelling suggestions for incorrectly spelled words in a text. The lesson will also focus on grammatical checking problems, which are the most difficult and complex type of language errors, because grammar is made up of a very extensive number of rules and exceptions. We will also say a few words about word completion. The lesson will also answer a question "How difficult is to develop a spell-checker?". And also describe a system that performs spell-checking and autocorrection. === References === 1. CHOUDHURY, Monojit, et al. "How Difficult is it to Develop a Perfect Spell-checker? A Cross-linguistic Analysis through Complex Network Approach" Graph-Based Algorithms for Natural Language Processing, pages 81–88, Rochester, 2007. [[http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=52A3B869596656C9DA285DCE83A0339F?doi=10.1.1.146.4390&rep=rep1&type=pdf|Source]] 1. WHITELAW, Casey, et al. "Using the Web for Language Independent Spellchecking and Autocorrection" Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 890–899, Singapore, 2009. [[http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/36180.pdf|Source]] 1. GUPTA, Neha, MATHUR, Pratistha. "Spell Checking Techniques in NLP: A Survey" International Journal of Advanced Research in Computer Science and Software Engineering, volume 2, issue 12, pages 217-221, 2012. [[http://www.ijarcsse.com/docs/papers/12_December2012/Volume_2_issue_12_December2012/V2I12-0164.pdf|Source]] 1. HLADEK, Daniel, STAS, Jan, JUHAR, Jozef. "Unsupervised Spelling Correction for the Slovak Text." Advances in Electrical and Electronic Engineering 11 (5), pages 392-397, 2013. [[http://advances.utc.sk/index.php/AEEE/article/view/898|Source]] == Practical Session == There are 2 tasks, you may choose one or both: 1. [wiki:/en/AdvancedNlpCourse/AutomaticCorrection#task1 statistical spell checker for English] 2. [wiki:/en/AdvancedNlpCourse/AutomaticCorrection#task2 rule based grammar checker (punctuation) for Czech] == Task 1: Statistical spell checker for English == #task1 In theoretical lesson we have become acquainted with various approaches how spelling correctors work. Now we will get to know how a simple spellchecker based on '''edit distance''' works. The example is based on Peter Norvig's [[http://norvig.com/spell-correct.html|Spelling Corrector]] in python. The spelling corrector will be trained with a large text file consisting of about a million words. We will test this tool on prepared data. Your goal will be to enhance spellchecker's accuracy. 1. Download prepared script [[raw-attachment:spell.py|spell.py]] and training data collection [[raw-attachment:big.txt|big.txt]]. 1. Test the script ` python ./spell.py ` in your working directory. 1. Open it in your favourite editor and we will walk through its functionality. === Spellchecker functionality with examples === 1. Spellchecker is '''trained''' from file `big.txt` which is a concatenation of several public domain books from '''Project Gutenberg''' and lists of most frequent words from '''Wiktionary''' and the '''British National Corpus'''. Function `train` stores how many times each word occurs in the text file. `NWORDS[w]` holds a count of how many times the word '''w has been seen'''. {{{ def words(text): return re.findall('[a-z]+', text.lower()) def train(features): model = collections.defaultdict(lambda: 1) for f in features: model[f] += 1 return model NWORDS = train(words(file('big.txt').read())) }}} 1. '''Edit distance 1''' is represented as function `edits1` - it represents deletion (remove one letter), a transposition (swap adjacent letters), an alteration (change one letter to another) or an insertion (add a letter). For a word of length '''n''', there will be '''n deletions''', '''n-1 transpositions''', '''26n alterations''', and '''26(n+1) insertions''', for a '''total of 54n+25'''. Example: len(edits1('something')) = 494 words. {{{ def edits1(word): splits = [(word[:i], word[i:]) for i in range(len(word) + 1)] deletes = [a + b[1:] for a, b in splits if b] transposes = [a + b[1] + b[0] + b[2:] for a, b in splits if len(b)>1] replaces = [a + c + b[1:] for a, b in splits for c in alphabet if b] inserts = [a + c + b for a, b in splits for c in alphabet] return set(deletes + transposes + replaces + inserts) }}} 1. '''Edit distance 2'''(`edits2`) - applied edits1 to all the results of edits1. Example: len(edits2('something')) = 114 324 words, which is a high number. To enhance speed we can only keep the candidates that are actually known words (`known_edits2`). Now known_edits2('something') is a set of just 4 words: {'smoothing', 'seething', 'something', 'soothing'}. 1. The function `correct` chooses as the set of candidate words the set with the '''shortest edit distance''' to the original word. {{{ def known(words): return set(w for w in words if w in NWORDS) def correct(word): candidates = known([word]) or known(edits1(word)) or \ known_edits2(word) or [word] return max(candidates, key=NWORDS.get) }}} 1. For '''evaluation''' there are prepared two test sets - development(`test1`) and final test set(`test2`). === Task 1 === 1. Create ``, a text file named `ia161-UCO-13.txt` where UCO is your university ID. 2. Run `spell.py` with development and final test sets (`tests1` and `tests2` within the script), write the results in ``. 3. Explain the given results in few words and write it in ``. 4. Modify the code of `spell.py` to increase accuracy at tests2 by 10 %. Describe your changes and write your new accuracy results to ``. === Upload `` and edited `spell.py` === == Task 2: Rule based grammar checker (punctuation) for Czech == #task2 The second task choice consists in adapting specific syntactic grammar of Czech to improve the results of ''punctuation detection'', i.e. placement of ''commas'' in the requested position in a sentence. === Task 2 === 1. login to aurora: `ssh aurora` 1. download: 1. [raw-attachment:punct.set syntactic grammar] for punctuation detection for the [http://nlp.fi.muni.cz/projects/set SET parser] 1. [raw-attachment:test-nopunct.txt testing text with no commas] 1. [raw-attachment:eval-gold.txt evaluation text with correct punctuation] 1. [raw-attachment:evalpunct_robust.py evaluation script] which computes recall and precision with both texts 1. run the parser to fill punctuation to the testing text {{{ cat test-nopunct.txt \ | /nlp/projekty/set/unitok.py \ | /nlp/projekty/rule_ind/stat/desamb.utf8.majka.sh \ | /nlp/projekty/set/set/set.py --commas --grammar=punct.set \ > test.txt }}} (takes a long time, about 30 s) 1. evaluate the result {{{ PYTHONIOENCODING=UTF-8 python evalpunct_robust.py eval-gold.txt test.txt > results.txt cat results.txt }}} 1. edit the grammar `punct.set` and add 1-2 rules to increase the F-score (combined recall and precision) of 10%. You may need to go through general information about the [https://nlp.fi.muni.cz/trac/set/wiki/documentation#Rulesstructure SET grammar format]. Information about adapting the grammar for the task of ''punctuation detection'' can be found the this [raw-attachment:tsd2014.pdf published paper]. Current best results achieved with an extended grammar are 91.2 % of precision and 55 % recall. 6. upload the modified `punct.set` and the respective `results.txt`. Do not forget to upload your resulting files to the [/en/AdvancedNlpCourse homework vault (odevzdávárna)].