Reference Scope Identification in Citing Sentences
Download as ODP, PDF1 like1,330 views
This document describes an approach to identify the scope of references in sentences containing multiple citations. The approach uses a conditional random field (CRF) sequence model with features including distance, position, part-of-speech tags, and syntactic dependencies. It first segments sentences using punctuation and conjunctions, then applies the CRF and a majority voting scheme to label each word as inside or outside the scope. The method achieved over 90% accuracy on a dataset of citations from ACL papers.
![Approach 3-S1-* (CRF/segment)
● segmentation (1)
● punctuation marks
● coordination conjunctions
– and, but, for, nor, or, so, yet
● a set of special expressions
– "for example", "for instance", "including", "includes",
"such as", "like", etc.
● [Rerankers have been successfully applied to numerous
NLP tasks such as] [parse selection (GTREF)], [parse
reranking (GREF)], [question-answering (REF)].](https://image.slidesharecdn.com/kameda-citation-121011035139-phpapp01/85/Reference-Scope-Identification-in-Citing-Sentences-7-320.jpg)
![Approach 3-S2-* (CRF/segment)
● segmentation (2)
● chunking tool
– noun groups
– verb groups
– preposition groups
– adjective groups
– adverb groups
– other parts form segment by themselves
● [To] [score] [the output] [of] [the coreference models], [we]
[employ] [the commonly-used MUC scoring program (REF)]
[and] [the recently-developed CEAF scoring program (TREF)].](https://image.slidesharecdn.com/kameda-citation-121011035139-phpapp01/85/Reference-Scope-Identification-in-Citing-Sentences-8-320.jpg)
![Approach 3-*-R1,2,3
(CRF/segment)
● R1: majority label of the words it contains
● R2: inside if any word is inside
● R3: outside if any word is outside
● [I O O O O] [I I I] [O O]](https://image.slidesharecdn.com/kameda-citation-121011035139-phpapp01/85/Reference-Scope-Identification-in-Citing-Sentences-9-320.jpg)
Reference Scope Identification in Citing Sentences
- 1. Reference Scope Identification in Citing Sentences Authors: Amjad Abu-Jbara, Dragomir Radev (University of Michigan) Conference: NAACL 2012 Expositor: Akihiro Kameda (Aizawa Lab. The University of Tokyo)
- 2. Abstract ● Problem: ● Multiple citation in one sentence ● There are many POS taggers developed using different techniques for many major languages such as transformation-based error-driven learning (Brill, 1995), decision trees (Black et al., 1992), Markov model (Cutting et al., 1992), maximum entropy methods (Ratnaparkhi, 1996) etc for English. ● Approach:Prepossessing and 2+1+2*3+1=10 methods
- 4. Reference Preprocessing (tagging, grouping, non-syntactical element removal) ● These constraints can be lexicalized (REF.1; REF.2), unlexicalized (REF.3; TREF.4) or automatically learned (REF.5; REF.6). ● These constraints can be lexicalized (GREF.1), unlexicalized (GTREF.2) or automatically learned (GREF.3). ● (GTREF.1) apply fuzzy techniques for integrating source syntax into hierarchical phrase-based systems (REF.2).
- 5. Approach 1(SVM,LR) ● Word classification ● with SVM, a logistic regression classifier ● Feature: Distance, Position(Before/After), in Segment(,.; and, but, for, nor, or, so, yet), POS tag, Dependency Distance, Dependency Relations, Common Ancestor Node, Syntactic Distance ● Problem Example: ● There are many POS taggers developed using different techniques for many major languages such as transformation- based error-driven learning (Brill, 1995), decision trees (Black et al., 1992), Markov model (Cutting et al., 1992), maximum entropy methods (Ratnaparkhi, 1996) etc for English.
- 6. Approach 2(CRF) ● Sequence Labeling with CRF ● feature is same as Approach 1
- 7. Approach 3-S1-* (CRF/segment) ● segmentation (1) ● punctuation marks ● coordination conjunctions – and, but, for, nor, or, so, yet ● a set of special expressions – "for example", "for instance", "including", "includes", "such as", "like", etc. ● [Rerankers have been successfully applied to numerous NLP tasks such as] [parse selection (GTREF)], [parse reranking (GREF)], [question-answering (REF)].
- 8. Approach 3-S2-* (CRF/segment) ● segmentation (2) ● chunking tool – noun groups – verb groups – preposition groups – adjective groups – adverb groups – other parts form segment by themselves ● [To] [score] [the output] [of] [the coreference models], [we] [employ] [the commonly-used MUC scoring program (REF)] [and] [the recently-developed CEAF scoring program (TREF)].
- 9. Approach 3-*-R1,2,3 (CRF/segment) ● R1: majority label of the words it contains ● R2: inside if any word is inside ● R3: outside if any word is outside ● [I O O O O] [I I I] [O O]
- 10. AR2011 the link grammar parser (Sleator and Temperley,1991)
- 11. Experiment
- 12. Data ● ACL Anthology Network Corpus ● 3300 sentences, citations in each ≧ 2 Annotation agreement ● 500 of 3300, ● Preprocessing is perfect ● Kappa coefficient of scope is P ( A)−P ( E ) K= =2P ( A)−1=0.61 1−P ( E )
- 13. Tools ● Edinburgh Language Technology Text Tokenization Toolkit (LT-TTT) ● text tokenization, part-of-speech tagging, chunking, and noun phrase head identification. ● Stanford parser ● syntactic and dependency parsing ● LibSVM with linear kernel ● Weka ● logistic regression classification
- 14. Tools ● Machine Learning for Language Toolkit (MALLET) ● CRF Validation ● 10-fold cross validation
- 15. Experiment (Preprocessing) These constraints can be lexicalized (REF.1; REF.2), ll r ec a ● unlexicalized (REF.3; TREF.4) or and 93 .1%learned (REF.5; REF.6). 3% preci s ion automatically ng: 9 8 . Taggi ● These constraints can be lexicalized (GREF.1), unlexicalized (GTREF.2) or Perfect! automatically learned (GREF.3). Grouping: (GTREF.1) apply fuzzy techniques for integrating source a l: ● syntax into hierarchicalence removsystems (REF.2). Non-syn tactic refer phrase-based ecall 9 0. 1% r cision and 9 0.08% pre
- 16. Experiment (Main) ● CRF ● Chunking ● Majority
- 17. Feature Analysis ● Feature: Distance, Position(Before/After), Same segment(,.; and, but, for, nor, or, so, yet), POS tag, Dependency Distance, Dependency Relations, Common Ancestor Node, Syntactic Distance
- 18. Summary ● Identified reference scope in a sentence which has multiple citation ● CRF ● Chunking ● Majority