Unsupervised Acquisition of Axioms to Paraphrase Noun Compounds
- Slides: 21
Unsupervised Acquisition of Axioms to Paraphrase Noun Compounds and Genitives CICLING 2012, New Delhi Anselmo Peñas NLP & IR Group, UNED, Spain Ekaterina Ovchinnikova USC – Information Science Institute, USA
UNED Texts omit information ¢ Humans optimize language generation effort ¢ We omit information that we know the receptor is able to predict and recover ¢ Our research goal is to make explicit the omitted information in texts nlp. uned. es
UNED Implicit predicates ¢ In particular, some noun compounds and genitives are used in such way ¢ In these cases, we want to recover the implicit predicates l For example: • Morning coffee -> coffee drunk in the morning • Malaria mosquito -> mosquito that carries malaria nlp. uned. es
UNED How to find the candidates? ¢ Nakov & Hearst 2006 l ¢ Search the web • N 1 N 2 -> N 2 THAT * N 1 • Malaria mosquito -> mosquito THAT * malaria Here we use Proposition Stores l l Harvest a text collection that will serve as context Parse documents Count N-V-N, N-V-P-N, N-P-N, … structures Build Proposition Stores (Peñas & Hovy, 2010) nlp. uned. es
UNED Proposition Stores Example: propositions that relate Bomb, attack • npn: [bomb: n, in: in, attack: n]: 13. • nvpn: [bomb: n, explode: v, in: in, attack: n]: 11. • nvnpn: [bomb: n, kill: v, people: n, in: in, attack: n]: 8. • npn: [attack: n, with: in, bomb: n]: 8. • … All of them could be paraphrases for the noun compound “bomb attack” nlp. uned. es
UNED NE Semantic Classes Now, What happens if we have a Named Entity? l l Shakespeare’s tragedy -> write Why? Consider • John’s tragedy • Airbus’ tragedy nlp. uned. es
UNED NE Semantic Classes We are considering the “semantic classes” of the NE Shakespeare -> writer, tragedy -> write nlp. uned. es
UNED Class-Instance relations ¢ Fortunately, relevant semantic classes are pointed out in texts through well-known structures • appositions, copulative verbs, “such as”, … ¢ Here we take advantage of dependency parsing to get class-instance relations NNP nn NN NNP appos NN be NN nlp. uned. es
UNED Class-Instance relations World News has_instance(leader, 'Yasir': 'Arafat'): 1491. has_instance(spokesman, 'Marlin': 'Fitzwater'): 1001. has_instance(leader, 'Mikhail': 'S. ': 'Gorbachev'): 980. has_instance(chairman, 'Yasir': 'Arafat'): 756. has_instance(agency, 'Tass'): 637. has_instance(leader, 'Radovan': 'Karadzic'): 611. has_instance(adviser, 'Condoleezza': 'Rice'): 590. … nlp. uned. es
UNED So far Propositions: <p, a> | P(p, a) p: predicate a: list of arguments <a 1 …an> P(p, a): joint probability Class-instance relations: <c, i> | P(c, i) c: class i: instance P(c, i): joint probability nlp. uned. es
UNED Probability of a predicate ¢ Let’s consider the following example Favre pass ¢ Assume the text has pointed out he is a quarterback ¢ What is Favre doing with the pass? The same as other quarterbacks • The quarterbacks we observed before in the background collection – Proposition Store nlp. uned. es
UNED Probability of a predicate Favre pass -> p | P(p|i) Favre -> quarterback | P(c|i) quarterback, pass -> throw | P(p|c) We already have: We need to estimate: P(p|c) (What other quarterbacks do with passes) nlp. uned. es
UNED Probability of a predicate quarterback pass -> p | P(p|c) • Steve: Young pass -> throw | P(p|i) • Culpepper pass -> complete | P(p|i) • … We already have and P(p|i) comes from previous observation: Proposition Store nlp. uned. es
UNED Evaluation ¢ We want to address the following questions l Do we find the paraphrases required to enable Textual Entailment? l Do all the noun-noun dependencies need to be paraphrased? l How frequently NEs appear in them? nlp. uned. es
UNED Experimental setting ¢ Proposition Store from 216, 303 World News l 7, 800, 000 sentences parsed l ¢ RTE-2 (Recognizing Textual Entailment) 83 entailment decisions depend on noun -noun paraphrases l 77 different noun-noun paraphrases l nlp. uned. es
UNED Results How frequently NEs appear in these pairs? ¢ ¢ 82% of paraphrases contain at least one NE 62% are paraphrasing NE-N (e. g. Vikings quarterback) nlp. uned. es
UNED Results Do all the noun-noun dependencies need to be paraphrased? ¢ ¢ No, only 54% in our test set Some compounds encode semantic relations such as: ¢ ¢ ¢ 12% are locative relations (e. g. New York club) Temporal relations (e. g. April 23 rd strike , Friday semi-final) Class-instance relations (e. g. quarterback Favre) Measure, … Some are trivial: ¢ 27% are paraphrased with “of” nlp. uned. es
UNED Results ¢ Do we find the paraphrases required to enable Textual Entailment? ¢ Yes in 63% of non-trivial cases Proposition type Paraphrase NPN Jackson trial ↔ trial against Jackson engine problem ↔ problem with engine NVN U. S. Ambassador ↔ Ambassador represents the U. S. ETA bombing ↔ ETA carried_out bombing NVNPN wife of Joseph Wilson ↔ wife is married to Joseph Wilson NVPN Vietnam veteran ↔ veteran comes from Vietnam Shapiro’s office ↔ Shapiro work in office Germany's people ↔ people live in Germany Abu Musab al-Zarqawi's group ↔ group led by Abu Musab al-Zarqawi nlp. uned. es
UNED Results RTE-2 pair 485: Paraphrase not found United Nations vehicle ↔ United Nations produces vehicles United Nations doesn’t share any class with the instances that “produce vehicles” Toyota vehicle -> develop, build, sell, produce, make, export, recall, assemble, … nlp. uned. es
UNED Conclusions ¢ ¢ ¢ A significant proportion of noun-noun dependencies includes Named Entities Some noun-noun dependencies don’t require the retrieval of implicit predicates The method proposed is sensitive to different Nes l ¢ Different NEs retrieve different predicates Current work: to select the most relevant paraphrase according to the text l We are exploring weighted abduction nlp. uned. es
Unsupervised Acquisition of Axioms to Paraphrase Noun Compounds and Genitives CICLING 2012, New Delhi Thanks!
- Compound noun phrases
- Collective noun of cereal
- Monitor model
- Ionic covalent and metallic venn diagram
- Paul watzlawick 5 axioms of communication
- Peano axioms
- Property of equality
- Transactional model of communication
- Object oriented design axioms
- What is an axiomatic system in geometry
- Compliance motivation and health behaviors of the learner
- Ring axioms
- Corpuleu
- Incidence axioms
- Set of complex numbers
- Prices adjust to achieve locational equilibrium
- Is cereal a common noun or proper noun
- Countable and uncountable nouns project
- Proper noun and common noun
- Noun and proper noun
- Proper noun idea
- Shelf is common or proper noun