Extracting argument and domain words for identifying - Description
argument components in texts Huy Nguyen 1 Diane Litman 12 1 Computer Science Department 2 Learning Research amp Development Center University of Pittsburgh The 2nd Workshop on Argumentation Mining ID: 561196 Download Presentation
Ethos, Logos, and Pathos. Ethos (Ethical). This appeal involves convincing your audience that you are intelligent and . can be trusted. . Writers cannot simply say to their audience "I can be trusted because I'm smart and a good person." This appeal is perhaps the most difficult to establish; you have to prove yourself by demonstrating that you understand what you are arguing -.
Criteria Assessed This question is intended to assess the ability of students to critically read and understand a targeted section in the passage and to distil what they have read into their own words with precision and clarity Description of Passag
words. in . gaining text coverage?. Tatsuhiko Matsushita. (University of Tokyo). Vocab@Vic. 2013. Victoria . University of Wellington. 1. Text Covering Efficiency . of the Grouped Words by Genre (Not Graded by Level) *Domain-unspecified.
A well known phrase.. It sent shivers up my spine. .. To be honest……. At the last minute.. Call it a day.. Emotive Language. Words chosen because of the feelings and emotions (connotations) associated with them..
Essential Terms Projects. AP Language and Composition Essential Terms. I. Mode of Rhetoric:. Expository-. writing with the purpose to inform, explain, describe or define the authors subject to the reader..
aka. “persuasive texts”. Exposition texts . are written to show a point of view in favour (to support) or against (to challenge) a specific topic / idea / assumption. . The ultimate aim:. is to try to convince the reader to agree with your opinion, or take a certain course of action, by giving reasons which are proven with evidence.
find an argument and ‘mark it up’. (bracket the reason) . and . underline the conclusion. Recap-. . the difference between an argument, rant and explanation. Cats are easier to look after than dog, cheaper than dogs, don’t need taking for long walks and are good company. Therefore I should get a cat and not a dog..
Used in advertising, speeches, presentations, essays etc…. Claim. States the main point or stance. Big Names. Mentions experts and important people to support the argument or add credibility. .. Hope that the .
. Learning how to put arguments in standard form.. . Understanding the different patterns in argument form.. . Dealing with implied premises and conclusions.. Thinking about visual arguments.. Identifying the Issue: Consider the Verdict.
47K - views
Extracting argument and domain words for identifying
argument components . in texts. Huy Nguyen. 1. . . Diane Litman. 1,2. . 1. Computer Science Department. 2. Learning Research & Development Center. University of Pittsburgh. The 2nd Workshop on Argumentation Mining.
Download Presentation - The PPT/PDF document "Extracting argument and domain words for..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Extracting argument and domain words for identifying
Presentation on theme: "Extracting argument and domain words for identifying"— Presentation transcript:
Extracting argument and domain words for identifying argument components in texts
Huy Nguyen1 Diane Litman1,2 1Computer Science Department2Learning Research & Development CenterUniversity of Pittsburgh
The 2nd Workshop on Argumentation Mining
NAACL 2015 WorkshopsJune 4th 2015, Denver, CO
This research is supported
Argument mining in textsMotivation of our approachOur approachEvaluationDataBaseline vs. proposed modelsExperiment resultsConclusions and future workOutline2Slide3
Argument mining in texts
Automatically identify argument elements and argumentative relations between themArgument mining as classification tasksArgument detection, i.e., argumentative sentence vs. none (Moens et al. 2007)Sentence’s rhetorical status, e.g., aim, background, contrast (Teufel & Moens 2002)Argumentative discourse structures, i.e., major claim, claim, premise
(Stab & Gurevych 2014ab)
Argument mining in texts3Slide4
Student essaysE.g., persuasive essays, academic writingsOptional title/topic but no section headingLack of evidence, substantiated by personal experience rather than cited resourcesSpecialized (useful) features, e.g., section heading, citation (Teufel & Moens 2002), are not availableNgrams and syntactic rules (e.g., VP → VBG NP) are commonly used (Burstein et al. 2003, Moens
et al. 2007, Stab & Gurevych 2014b, Park &
Cardie 2014)But have limitationsLarge and sparse feature spaceFeature selection helps with over-fitting but not efficiently
Argument mining in texts4Slide5
Argument mining in texts5
A novel feature design
Separate argument words from domain wordsArgument words: argument indicators and commonly used in different argument topics, e.g., reason, opinion, believeDomain words: specific terminologies commonly used within the topic’s domain, e.g., art, education, childrenPost-process topic model output using seedingSeeding requires human knowledge but minimal
Unannotated dataDerive novel features to replace
ngrams and syntactic rulesFeature reductionTopic-independenceArgument mining in
et al. 2003)Extraction of argument and domain
LDA topics vs. essay topics
LDA topics approximate writing topics
but not completely
How can we
its difference from
the others (LDA topics) ?
Extraction of argument and domain words
Argument and domain word extraction
Identification stepPre-defined argument keywords: most frequentargument words in essay titles, e.g., opinion, agreeDomain seed words: title words but not argumentkeywords or stop words3 weights of a LDA topic (LDA word lists)(1) Argument weightCount of argument keywords in the list(2) Domain weightSum
domainCan they be used?Alternative argument word list254 academic essays from college Psychology classes5 argument keywords taken from the writing assignmenthypothesis, support, opposition, finding, study
Extract 429 argument words
Replace the 263 argument words of the persuasive setEvaluation15
10-fold cross validation
140 words ≡ Academic ∩ Persuasive
… and qualitatively differentEvaluation16Alternative model’s top 100 feature
(argument words of academic set)
Proposed model’s top 100 feature(argument words of persuasive set)
Most of popular terms in academic writings were not selected:
Conclusions and future work
Novel algorithm to post-process LDA output to extract argument and domain wordsMinimal seeding, unannotated dataFeatures derived from extracted argument wordsEfficiently replace ngrams and syntactic rulesArgument words extracted from different data domainNon-transferable part are genre-dependent and needed for the best performanceOur next study is argumentative relation classification, i.e. support vs. attack
Conclusions and future work
In comparison with prior studies
Our argument words are subsets of generic unigramsWe emphasize the topic-independence of featuresArgument and domain word notion is similar to argument shell and content in (Madnani et al. 2012)We have no requirement of physical boundaries between the two aspectsOur idea of using seed words to guide the word separation is similar to (Louis and Nenkova, 2013)We need much less prior knowledgeWe identify the best number of topics that maximize topic discriminationArgument mining in texts
Evaluation20Baseline (top 130 features)Proposed model (top 70 features)
and train in 75-essay set, test in 15-essay setSlide25
Alternative argument word list
Can argument words be learned from different genre?College students’ essays in introductory Psychology classes254 essays, 5 argument keywords taken from the writing assignmenthypothesis, support, opposition, finding, studyReturn 14 LDA topics, 429 argument words, 1497 domain wordsReplace the 285 argument words of the persuasive setEvaluation
10-fold cross validationSlide26
Argument and domain words
The argument states that based on the result of the recent research, there probably were grizzly bears in Labrador (cf. Madnani et al. 2012)probablyresult
My view is that
the government should give priorities to invest more money on the basic social welfares such as education and housing instead of subsidizing arts relative programs (cf. persuasive essay corpus, Stab & Gurevych 2014a)
Lexical signals of argumentative content and argument topic
Argument shell and contentExtraction of argument and domain