Centering theory and its direct applications

Slides:



Advertisements
Similar presentations
Referring Expressions: Definition Referring expressions are words or phrases, the semantic interpretation of which is a discourse entity (also called referent)
Advertisements

Academic Writing Writing an Abstract.
Albert Gatt LIN3022 Natural Language Processing Lecture 11.
Curs 7: Teorii ale discursului Centering Dan Cristea Selecţie de slide-uri prezentate în tutoriale (RANLP-03, Borovits, Sept. 2003; ICON-04, Hyderabad,
Week 8: Ms. Lowery.  Large-scale revision and examining higher- order concerns  Revision techniques for content, structure, and adherence to the assignment.
Automatic Essay Scoring Evaluation of text coherence for electronic essay scoring systems (E. Miltsakaki and K. Kukich, 2004) Universität des Saarlandes.
Introduction to phrases & clauses
Released CELDT Questions
Processing of large document collections Part 6 (Text summarization: discourse- based approaches) Helena Ahonen-Myka Spring 2006.
1 Discourse, coherence and anaphora resolution Lecture 16.
Anaphora Resolution Spring 2010, UCSC – Adrian Brasoveanu [Slides based on various sources, collected over a couple of years and repeatedly modified –
Chapter 18: Discourse Tianjun Fu Ling538 Presentation Nov 30th, 2006.
Chapter 20: Natural Language Generation Presented by: Anastasia Gorbunova LING538: Computational Linguistics, Fall 2006 Speech and Language Processing.
Predicting Text Quality for Scientific Articles Annie Louis University of Pennsylvania Advisor: Ani Nenkova.
Predicting Text Quality for Scientific Articles AAAI/SIGART-11 Doctoral Consortium Annie Louis : Louis A. and Nenkova A Automatically.
Information Ordering for Text Generation Computational Models of Discourse Presented by : Henock Tilahun.
EE 399 Lecture 2 (a) Guidelines To Good Writing. Contents Basic Steps Toward Good Writing. Developing an Outline: Outline Benefits. Initial Development.
CS 4705 Lecture 21 Algorithms for Reference Resolution.
1 Special Electives of Comp.Linguistics: Processing Anaphoric Expressions Eleni Miltsakaki AUTH Fall 2005-Lecture 4.
© 2005 John Wiley & Sons PPT1 Midterm Essay – Sharing my comments Negative: 1.The position could be made clearer and more obvious. 2.There are too many.
1 Pragmatics: Discourse Analysis J&M’s Chapter 21.
Discourse and intertextual issues in translation.
Chapter Section A: Verb Basics Section B: Pronoun Basics Section C: Parallel Structure Section D: Using Modifiers Effectively The Writer’s Handbook: Grammar.
Introduction.  Classification based on function role in classroom instruction  Placement assessment: administered at the beginning of instruction 
Testing Writing Miss. Mona AL-Kahtani.
THE ESSAY WRITING PROCESS A. Introduction B. Body C. Conclusion.
Automated Essay Evaluation Martin Angert Rachel Drossman.
McEnery, T., Xiao, R. and Y.Tono Corpus-based language studies. Routledge. Unit A 2. Representativeness, balance and sampling (pp13-21)
Signposting L 5 Ing. Jiří Šnajdar
MECHANICS OF WRITING C.RAGHAVA RAO.
What is Readability?  A characteristic of text documents..  “the sum total of all those elements within a given piece of printed material that affect.
Readers and Writers.  Short essays are written under the pressure of a time limit and average words.  Make a Jot List ▪ A list of points to.
Study Skills For Students of English. English as Your Language of Instruction p.1 Motivation Concentration Distraction Place of Study Time of Study.
1 Special Electives of Comp.Linguistics: Processing Anaphoric Expressions Eleni Miltsakaki AUTH Fall 2005-Lecture 3.
Scientific Prose Style (SPS) Literary and Linguostylistic Characteristics.
Informative/Explanatory Writing
Tutoring IELP Writing An overview In the beginning … What kinds of writing do the students bring in to the Learning Center? What is the best way to tutor.
Pronouns Cano. A pronoun replaces a noun. We call the word being replaced by the pronoun the antecedent. In the following sentence, keys is the antecedent.
Useful tips © Gerlinde Darlington MEd.Mag.phil..  Introduction  Main part – consisting of a few paragraphs  Conclusion  Remember: poorly structured.
This work is supported by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior National Business Center contract number.
Sequencing and Feedback in Teaching Grammar. Problems in Sequencing ► How do we sequence the grammar in a teaching programme? ► From easy to difficult?
1 Special Electives of Comp.Linguistics: Processing Anaphoric Expressions Eleni Miltsakaki AUTH Fall 2005-Lecture 2.
Writing the Analytical Paper Intercultural Literature C. Valverde.
Error Correction: For Dummies? Ellen Pratt, PhD. UPR Mayaguez.
1 Cohesion + Coherence Lecture 9 MODULE 2 Meaning and discourse in English.
The Thesis Statement. What is a thesis statement? A thesis statement is the most important sentence in your paper. A thesis statement tells your readers.
The Grammar Business © 2001 Glenrothes College The Grammar Business Part Two 4. Logic rules: paragraphs, links and headings.
1 KINDS OF PARAGRAPH. There are at least seven types of paragraphs. Knowledge of the differences between them can facilitate composing well-structured.
How to Write an Excellent AP English Language and Composition Essay
Language Issues Constructs, Theories, and Scales.
Automatic recognition of discourse relations Lecture 3.
L ITERATURE REVIEW RESEARCH METHOD FOR ACADEMIC PROJECT I.
Getting from Point A to Point B: Creating Good Transitions Ms. Garcia 6th Grade Language Arts.
Writing Exercise Try to write a short humor piece. It can be fictional or non-fictional. Essay by David Sedaris.
An evolutionary approach for improving the quality of automatic summaries Constantin Orasan Research Group in Computational Linguistics School of Humanities,
GRAMMAR AND PUNCTUATION REVISE AND REVIEW WORD CLASSES.
The Thesis Statement. What is a thesis statement? A thesis statement is the most important sentence in your paper. A thesis statement tells your readers.
25 January 2016 SUMMARY WRITING Sokolova Elvira Yakovlevna.
2. The standards of textuality: cohesion Traditional approach to the study of lannguage: sentence as conventional object of study Structuralism (Bloofield,
5 Passages 75 Questions 45 Minutes
ACT English Test Preparation
Assessing Writing Ningtyas Orilina A, M.Pd.
Smart points and Kaplan online resources
Written Task 1.
Improving a Pipeline Architecture for Shallow Discourse Parsing
Referring Expressions: Definition
9th Grade Literature & Composition
Anaphora Resolution Spring 2010, UCSC – Adrian Brasoveanu
Algorithms for Reference Resolution
Managing People: Essay Guidance 2018/19
Presentation transcript:

Centering theory and its direct applications Lecture 2

Some definitions Discourse = coherent sequence of utterances Several sentences following one another do not make a readable text Defining specific computable measures of coherence is the goal of this seminar

Centering theory ingredients Deals with local coherence What happens to the flow from sentence to sentence Does not deal with global structuring of the text (paragraphs/segments) Defines coherence as an estimate of the processing load required to “understand” the text

Processing load Upon hearing a sentence a person Cognitive effort to interpret the expressions in the utterance Integrates the meaning of the utterance with that of the previous sentence Creates some expectations on what might come next

Example John met his friend Mary today. He was surprised to see her. He thought she is still in Italy. Form of referring expressions Anaphora needs to be resolved “Create” a discourse entity at first mention with full noun phrase Creating expectations

Creating and meeting expectations (1) a. John went to his favorite music store to buy a piano. b. He had frequented the store for many years. c. He was excited that he could finally buy a piano. d. He arrived just as the store was closing for the day. (2) a. John went to his favorite music store to buy a piano. b. It was a store John had frequented for many years. d. It was closing just as John arrived.

Interpreting pronouns Terry really goofs sometimes. Yesterday was a beautiful day and he was excited about trying out his new sailboat. He wanted Tony to join him on a sailing expedition. He called him at 6am. He was sick and furious at being woken up so early.

Basic center definitions Centers of an utterance Set of entities serving to link that utterance to the other utterances in the discourse segment that contains it Not words or phrases themselves Semantic interpretations of noun phraes

Types of centers Forward looking centers An ordered set of entities What could we expect to hear about next Ordered by salience as determined by grammatical function Subject > Indirect object > Object > Others John gave the textbook to Mary. Cf = {John, Mary, textbook} Preferred center Cp The highest ranked forward looking center High expectation that the next utterance in the segment will be about Cp

Backward looking center Single backward looking center, Cb (U) For each utterance other than the segment-initial one The backward looking center of utterance Un+1 connects with one of the forward looking centers of Un Cb (U+1) is the most highly ranked element from Cf (Un) that is also realized in U+1

Centering transitions ordering Cb(Un+1)=Cb(Un) OR Cb(Un)=[?] Cb(Un+1) != Cb(Un) Cb(Un+1) = Cp (Un+1) continue smooth-shift Cb(Un+1) != Cp (Un+1) retain rough-shift

Centering constraints There is precisely one backward-looking center Cb(Un) Cb(Un+1) is the highest-ranked element of Cf(Un) that is realized in Un+1

Centering rules If some element of Cf(Un) is realized as a pronoun in Un+1 then so is Cb(Un+1) Transitions not equal continue > retain > smooth-shift > rough-shift

Centering analysis Terry really goofs sometimes. Cf={Terry}, Cb=?, undef Yesterday was a beautiful day and he was excited about trying out his new sailboat. Cf={Terry,sailboat}, Cb=Terry, continue He wanted Tony to join him in a sailing expedition. Cf={Terry, Tony, expedition}, Cb=Terry, continue He called him at 6am. Cf={Terry,Tony}, Cb=Terry, continue

Tony was sick and furious at being woken up so early. He called him at 6am. Cf={Terry,Tony}, Cb=Terry, continue Tony was sick and furious at being woken up so early. Cf={Tony}, Cb=Tony, smooth shift He told Terry to get lost and hung up. Cf={Tony,Terry}, Cb=Tony, continue Of course, Terry hadn’t intended to upset Tony. Cf={Terry,Tony}, Cb = Tony, retain

Rough shifts in evaluation of writing skills One of the graders of student essays in standardized tests is an automatic program ETS researchers have developed a number of applications that use natural language processing technologies to evaluate and score the writing abilities of test takers: The CriterionSM Online Essay Evaluation Service automatically evaluates essay responses using e-rater and the Critique writing analysis tools. E-rater® gives holistic scores for essays. CritiqueTM provides real-time feedback about grammar, usage, mechanics and style, and organization and development. C-raterTM offers automated analysis of conceptual information in short-answer, free responses.

E-rater features Syntactic variety Clear transitions Represented by features that quantify the occurrence of clause types Clear transitions Cue phrases in certain syntactic constructions Existence of main and supporting points Appropriateness of the vocabulary content of the essay What about local coherence?

Ranking forward looking centers Subject > Indirect object > Object > Others > Quantified indefinite subjects (people, everyone) > Arbitrary plural pronominals

Essay score model Human score available E-rater prediction available Percentage of rough-shifts in each essay: analysis done manually Negative correlation between the human score and the percentage of rough-shifts

Karamanis’07 Why are we reading this paper? Gives quite complete list of references on later work on centering Centering variants Reminds that entity coherence is not the only factor in text flow We’ll be discussing rhetorical structure theory during the next class Applications---can some aspects of the work be done differently/improved upon?

Information ordering task Given a set of sentences/clauses, what is the best presentation? Take a newspaper article and jumble the sentences---the result will be much more difficult to read than the original Criteria for deciding which of two orderings is better Centering would definitely be applicable Summarization, question answering, generation

Linear multi-factor regression Approximate the human score as a linear function of the e-rater prediction and the percentage of rough-shifts Adding rough shifts significantly improves the model of the score 0.5 improvement on 1—6 scale How easy/difficult would it be to fully automate the rough-shift variable

Centering variations Continuity (NOCB=lack of continuity) Coherence Cf(Un) and Cf(Un+1) share at least one element Coherence Cb(Un) = Cb(Un+1) Salience The Cb(U) = Cp(U) Coherence is more important than salience Cheapness (fulfilled expectations) Cb (Un+1) = Cp(Un)

GNOME corpus 20 descriptions of museum artifacts Split into finite unites (clauses) Semi-automatic centering annotation Item 144 is a torc. Its present arrangement, twisted into three rings, may be a modern alteration; it should probably be a single ring, worn around the neck. The terminals are in the form of goats’ heads.

Rhetorical coherence Each text can be seen as a hierarchical tree structure Different spans are related by some rhetorical relation Elaboration (adding more information) Contrast Sequence Purpose Summary etc

Local rhetorical coherence Applies only locally rather than on the text as a whole Signaled by cue phrases Contrast: but, however, on the other hand Continuation: and, then, later Consequence: because, in order to, so These local rhetorical relations structure the text When missing, entity coherence determines the flow 8 out of the 20 texts do not have any explicitly marked rhetorical relations

Joint centering and local rhetorical coherence In clauses directly marked for a rhetorical relation Merge the Cf lists of the two clauses Apply centering transitions on the resulting Cf list rather than the original GNOME-RR contains 1.58 fewer CF lists compared to the original average number (8.35)

Metrics of coherence M.NOCB (no continuity) M.CHEAP (expectations not met) M.KP sum of the violations of continuity, cheapness, coherence and salience M. BFP seeks to maximize transitions according to Rule 2

Experimental methodology Gold-standard ordering The original order of the text (object description, news article) Assume that other orderings are inferior Classification error rate Percentage orderings that score better than the gold-standard + 0.5*percentage of the orderings that score the same

Results NOCB gives best results M.BFP is the second best metric Significantly better than the other metrics M.BFP is the second best metric Adding the local rhetorical relations hurts performance---is this surprising?

Reminders Select topics you would like to present Should schedule next week now The second time you present one of the goals will be to relate the papers with previous topics we have covered Start thinking about the topic of your literature overview About 15 papers 5/6 pages Due Nov 12