Content Writing Optimization with ReWriter
Download as PPTX, PDF1 like369 views
The document discusses content writing optimization using a rewriter tool. It outlines the rewriter's capabilities such as providing paraphrases through synonyms, support verb transformations, and other linguistic rules. The rewriter has been developed to aid writing, translation, and machine translation. Evaluation results show the rewriter improves translation quality by paraphrasing complex linguistic constructs like support verb constructions. The document also discusses the rewriter's interface and linguistic resources and rules, and how the tool could benefit writers, translators and language learners.
![TRANSFORMATIONS FOR THE NEAR FUTURE
[Popular versus technical terms]
around the orbit of the eye ≡ periorbital
[If clauses]
if it is necessary ≡ if necessary
[Passives into actives - whenever suitable]
That book was written by Saramago in 2008 > Saramago wrote that book in 2008
Florida was hit by a tornado > A tornado hit Florida
[Coordinated noun phrases - conjoining or disjoining]
linguistic resources for teaching and for research > linguistic resources for teaching and research
[Subjunctive clauses - into infinitives]
we ask the favor that you confirm your attendance > we ask the favor to confirm your attendance
[Marked-up constructions]
if the end-user need is to create controlled language text > if the end-user needs to create
controlled language text
[Vague and undefined or null subject sentences] (whenever the real subject/actor is known)
[-] there was shouting in the street > [N-PRON]/someone shouted in the street
Translating and the Computer Conference 2010
Anabela Barreiro London, 18-19 November 2010](https://image.slidesharecdn.com/contentwritingoptimizationwithrewriter-130516174108-phpapp01/85/Content-Writing-Optimization-with-ReWriter-20-320.jpg)
![IMPROVEMENT OF REWRITER
Writing (pedagogical) exercises – students learning how to improve
their writing skills in a native or foreign language
Professional writers and translators using (and testing) the
tool, marking [informal], [idiomatic], [slang] and other uses of the
terminology
Detection of errors (words that are not synonyms, or not in a
particular context)
Define linguistic rules to improve precision in specific contexts (e.g.:
[bring(vt)) N(charge; action) > present(vt) N(idem)]
Include “revision memories” (recycling validated reviewed
sentences, structures or phrases)
Translating and the Computer Conference 2010
Anabela Barreiro London, 18-19 November 2010](https://image.slidesharecdn.com/contentwritingoptimizationwithrewriter-130516174108-phpapp01/85/Content-Writing-Optimization-with-ReWriter-23-320.jpg)
Content Writing Optimization with ReWriter
- 1. CONTENT WRITING OPTIMIZATION WITH REWRITER Anabela Barreiro ab@metatrad.com Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 2. OUTLINE LINGUISTIC QUALITY ASSURANCE HOW TO ACHIEVE WRITING OPTIMIZATION REWRITER PARAPHRASES COVERED BY REWRITER REWRITER V0.1 AND V0.2 – INTERFACE AND MODUS OPERANDI LINGUISTIC RESOURCES USED BY REWRITER EVALUATION RESULTS TRANSFORMATIONS FOR THE NEAR FUTURE WHO COULD BENEFIT FROM REWRITER? FROM REWRITER TO MACHINE TRANSLATION IMPROVEMENT OF REWRITER Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 3. LINGUISTIC QUALITY ASSURANCE Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 Reassures that a certain level of linguistic quality is guaranteed in texts Uses techniques to verify the quality of specialized documentation Helps individuals/businesses connect with their target audience in a clear and understandable way by achieving: • strategic, high quality, meaningful content • relevant content written and optimized specifically for a particular purpose (or for a particular business) • custom content (relevant keywords and adequate terminologies) • original texts (creative writing) or domain specific texts (technical writing) • readable / publishable content
- 4. LINGUISTIC QUALITY ASSURANCE Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 Professional text writing and revision • Orthographic, grammatical, stylistic and terminological verification of the technical documents • Use of tools Spell and grammar checkers Writing/authoring aids Style guides Terminologies (technical domains) Controlled language • Consistent, direct, and simple language • Restricted grammar (avoid certain types of construction) • Avoid complex reasoning, figures of speech, metaphors, etc. • Elimination of wordiness
- 5. HOW TO ACHIEVE WRITING OPTIMIZATION Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 Synonymy Stylistics PARAPHRASING • effective in helping writers with writing difficulties or learners of a non- native language (pedagogical exercise) • essential component in the translation process and of an extreme value to machine translation pre-editing • can be employed in linguistic quality assurance for both source and target texts For the past few years, researchers have been trying to achieve automated paraphrasing to respond to the commercial enterprises’ wish to include paraphrases in their text processing tools, authoring aids, learning tools, etc.
- 6. REWRITER – PARAPHRASING TOOL authoring aid (word processing applications) Language composition tool Text production and style editor Empirical testbed for linguistic quality assurance (source and target texts) text (pre-)editing (machine translation) “Revision memory” tool (≈ “translation memory”) Applicable to general and technical language (e.g. student texts or legal texts) Portuguese version “ReEscreve” - publicly available service at: http://www.linguateca.pt/ReEscreve/ Soon to be integrated in a cyber school project – “Ciberescola” Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 7. PARAPHRASES COVERED BY REWRITER Synonyms in context (ex: phrasal verbs into equivalent expressions) to clear up (weather) = (weather) to become better/brighter Support verb constructions into single verbs to make a decision = to decide make a presentation of = present to give support to N(AN) = to support N(AN) to go V-ing = to continue V-ing to get into contact with = to contact to turn on N(light) = to extinguish N(light) to become acid = to acidify Support verb constructions into their stylistic variants to make an audit = to perform an audit to make an impression = to create an impression Aspectual constructions into single verbs to launch an attack = to attack Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 8. Adverbials (compounds into single adverbs) in a constructive way = constructively on purpose > purposely = deliberately Relatives into participial adjectives the president that was elected = the president elect Relatives into possessives the role that Europe plays/has = the role of Europe the position that the Church defends = the position of the Church Relatives into compound nouns (and vice-versa) a container for the milk = a milk container a bottle made of plastic = a plastic bottle Agentive passives into actives the young man is released by the police officer = the police officer releases the young man Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 PARAPHRASES COVERED BY REWRITER
- 9. REWRITER (V0.1) INTERFACE FOR THE PUBLIC SERVICE Interactive ReWriter for word processing applications, such as text editing Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 10. REWRITER (V0.1) SUGGESTIONS FOR EXAMPLE SENTENCES Suggestions for general language linguistic phenomena Compound adverbs > single adverbs Support verb constructions > single verbs Relatives > participial adjectives Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 11. REWRITER (V0.1) USER’S CAPABILITY TO ADD NEW REWRITING OPTIONS The user can suggest new words or expressions (synonyms or paraphrases) Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 12. REWRITER (V0.2) COMMERCIAL INTERFACE - PROTOTYPE Users can select among general and technical dictionaries (more than one selection allowed), grammars for specific linguistic transformations (one, several or all grammars can be selected). The interface provides sample texts for testing. Sample LEGAL text Informative details about the linguistic resources selected Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 13. REWRITER (V0.2) COMMERCIAL INTERFACE - PROTOTYPE Identification of legal terms in the text Suggestions for the term “breach of law” Users can select one term on the list of suggestions or provide a new suggestion Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 14. REWRITER (V0.2) COMMERCIAL INTERFACE - PROTOTYPE Text rewritten • In red, the expressions in the source text • In green, suggestions provided by ReWriter and selected by the user It is possible to go back and change the user option as many times as necessary Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 15. LINGUISTIC RESOURCES USED BY REWRITER Eng4NooJ – linguistic knowledge database • OpenLogos dictionary (http://logos-os.dfki.de/) – commercial version belongs to GROUP Business Software, Germany • converted into NooJ format, and enhanced with new properties, including derivational and morpho-syntactic and semantic relations Allows linguistic annotation and processing of corpora Instrument for empirical testbed to support theoretical linguistics research Basis for language technology applications, including machine translation between several languages Sample of Dictionary of Legal Terms Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 16. Sample of terms classified as Information + Instructional/legal Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 LINGUISTIC RESOURCES USED BY REWRITER
- 17. Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 NDRV04 = <B>ion/Npred+Nom ADRV02 = <B>icable AVDRV01 = <E>ly/ADV AVDRV04 = <B>tically/ADV impress,V+FLX=POLISH+SAL=PVPCpleasetype+PT=impressionar+DRV=NDRV01:BOOK+ VSUP=make+VSUP=cause+NPREP=on aesthetic,AFLX=NATURAL+SAL=AVstate+PT=aesthetically+DRV=AVDRV03 skepticism,N+FLX=BOOK+SAL=ABcause+PT=cepticismo+DRV=NAVDRV02 Grammar to recognize adverbial compounds and transform them into equivalent single adverbs Rules to transform morpho-syntactically and semantically related words of different parts of speech General language dictionary entries LINGUISTIC RESOURCES USED BY REWRITER Morpho-syntactic and semantic relations
- 18. EVALUATION RESULTS: PARAPHRASING PRECISION Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 SVC Recognition Precision SVC Recognition Recall SVC Paraphrasing Precision Pôr 73/73 - 100% 73/100 – 73% 72/73 - 98.6% Tomar 75/75 - 100% 75/100 – 75% 68/73 - 93.1% Ter 65/65 - 100% 65/100 – 65% 59/65 - 90.7% Dar 57/60 - 95% 57/100 – 57% 46/51 - 90.1% Fazer 43/45 – 95.5% 43/100 – 43% 40/45 - 88.8% Average 62.6/63.6 - 98.4% 62.6/100 - 62.6% 57/61 - 93.4% Evaluation of recognition and paraphrasing of support verb constructions Corpus of fiction: 500 sentences 100 for each of 5 elementary support verbs
- 19. EVALUATION RESULTS: IMPACT ON TRANSLATABILITY (MT) Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 Same corpus, 50 sentences selected randomly (i) automated pre-processing of support verb constructions with ReWriter and conversion into equivalent single verbs (ii) pre-processed sentences (automatically generated paraphrases) and original text are submitted to MT and the output translations for both original and pre-processed sentences were compared • 29 (58%) of the best translations were of automatically generated paraphrases • 9 (18%) were of support verb constructions • 12 (24%) were equally bad or equally good CONCLUSION The experiment indicates that paraphrases such as those generated by ReWriter help improve translation scores • The automated paraphrasing of support verb constructions through ReWriter allowed a significant improvement of the quality of the MT results in that context
- 20. TRANSFORMATIONS FOR THE NEAR FUTURE [Popular versus technical terms] around the orbit of the eye ≡ periorbital [If clauses] if it is necessary ≡ if necessary [Passives into actives - whenever suitable] That book was written by Saramago in 2008 > Saramago wrote that book in 2008 Florida was hit by a tornado > A tornado hit Florida [Coordinated noun phrases - conjoining or disjoining] linguistic resources for teaching and for research > linguistic resources for teaching and research [Subjunctive clauses - into infinitives] we ask the favor that you confirm your attendance > we ask the favor to confirm your attendance [Marked-up constructions] if the end-user need is to create controlled language text > if the end-user needs to create controlled language text [Vague and undefined or null subject sentences] (whenever the real subject/actor is known) [-] there was shouting in the street > [N-PRON]/someone shouted in the street Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 21. WHO COULD BENEFIT FROM REWRITER? Writers in general (searching for synonyms and paraphrases) Technical writers (searching for the “exact” term) Editors MT pre-editors Translators Learners of a second language Students learning language and writing skills Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 22. $EN FROM REWRITER TO MACHINE TRANSLATION Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 a fazer um estágio para dar aulas de / tutor Religião a fazer um estágio para dar aulas de / lecture Religião a fazer um estágio para dar aulas de / teach Religião começa a dar exemplos / exemplify : sentia-se capaz de dar um murro em / punch quem quisesse detê-lo gostávamos de lhe dar uma palavrinha / speak .
- 23. IMPROVEMENT OF REWRITER Writing (pedagogical) exercises – students learning how to improve their writing skills in a native or foreign language Professional writers and translators using (and testing) the tool, marking [informal], [idiomatic], [slang] and other uses of the terminology Detection of errors (words that are not synonyms, or not in a particular context) Define linguistic rules to improve precision in specific contexts (e.g.: [bring(vt)) N(charge; action) > present(vt) N(idem)] Include “revision memories” (recycling validated reviewed sentences, structures or phrases) Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010
- 24. Translating and the Computer Conference 2010 Anabela Barreiro London, 18-19 November 2010 To learn more on paraphrases… Soon to be released!Anabela Barreiro ab@metatrad.com