Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 Combining Contexts in Lexicon Learning for Semantic Parsing May 25, 2007 NODALIDA 2007, Tartu, Estonia Chris Biemann University of Leipzig Germany Rainer.

Similar presentations


Presentation on theme: "1 Combining Contexts in Lexicon Learning for Semantic Parsing May 25, 2007 NODALIDA 2007, Tartu, Estonia Chris Biemann University of Leipzig Germany Rainer."— Presentation transcript:

1 1 Combining Contexts in Lexicon Learning for Semantic Parsing May 25, 2007 NODALIDA 2007, Tartu, Estonia Chris Biemann University of Leipzig Germany Rainer Osswald FernUniversität Hagen Germany Richard Socher Saarland University Germany

2 2 Outline Motivation: lexicon extension for semantic parsing The semantic lexicon HaGenLex Binary features and complex sorts Method: bootstrapping via syntactic contexts Results Discussion

3 3 Motivation Semantic parsing aims at finding a semantic representation for a sentence Semantic parsing needs as a prerequisite semantic features of words. Semantic features are obtained by manually creating lexicon entries (expensive in terms of time and money) Given a certain amount of manually created lexicon entries, it might be possible to train a classifier in order to find more entries Objective is Precision, Recall is secondary

4 4 HaGenLex: Semantic Lexicon for German complex sort size: 22,700 entries of these: 13,000 nouns, 6,700 verbs WORDSEMANTIC CLASS Aggressivitätnonment-dyn-abs-situation Agonienonment-stat-abs-situation Agrarproduktnat-discrete Ägypterhuman-object Ahnhuman-object Ahndungnonment-dyn-abs-situation Ähnlichkeitrelation Airbagnonax-mov-art-discrete Airbusmov-nonanimate-con-potag Airportart-con-geogr Ajatollahhuman-object Akademikerhuman-object Akademisierungnonment-dyn-abs-situation Akkordeonnonax-mov-art-discrete Akkreditierungnonment-dyn-abs-situation Akkuax-mov-art-discrete Akquisitionnonment-dyn-abs-situation Akrobathuman-object...

5 5 Characteristics of complex sorts in HaGenLex In total, 50 complex sorts for nouns are constructed from allowed combinations of: 16 semantic features (binary), e.g. HUMAN+, ARTIFICIAL- 17 sorts (binary), e.g. concrete, abstract-situation... sort (hierarchy) semantic features complex sorts

6 6 Application: WOCADI-Parser Welche Bücher von Peter Jackson über Expertensysteme wurden bei Addison-Wesley seit 1985 veröffentlicht?

7 7 General Methodology Distributional Hypothesis projected on syntactic- semantic contexts for nouns: nouns of similar complex sort are found in similar contexts We use three kinds of context elements Adjective Modifier Verb-Subject (deep) Verb-Object (deep) as assigned by the WOCADI parser for training 33 binary classifiers.

8 8 Data Corpus: 3,068,945 sentences obtained from the Leipzig Corpora Collection parser coverage: 42% verb-deep-subject relations: 430,916 verb-deep-object relations: 408,699 adjective-noun relations: 450,184 Lexicon 11,100 noun entries lexicon extension: 10-fold cross validation on known nouns Also unknown nouns will be classified

9 9 Algorithm: Initialize the training set; As long as new nouns get classified { calculate class probabilities for each context element; for all yet unclassified nouns n { Multiply class probs of context elements class-wise; Assign the class with highest probabilities to noun n; } Class probabilities per context element: a) count number of per class b) normalize on total number of class wrt. noun classes c) normalize to row sum=1 A threshold regulates the minimum number of different context elements a noun co-occurs with in order to be classified Bootstrapping Mechanism

10 10 From binary classes to complex sorts Binary classifiers for single features for all three context element types are combined into one feature assignment: –Lenient: voting –Strict: all classifiers for different context types agree Combining the outcome: safe choices ANIMAL +/- ANIMATE +/- ARTIF +/- AXIAL +/-... (16 features)... (17 sorts) ab +/- abs +/- ad +/- as +/- Selection: compatible complex sorts that are minimal w.r.t hierarchy and unambiguous. result class or reject

11 11 Results: binary classes for different context types =5 =1 most of the binary features are highly biased

12 12 Combination of context types =1

13 13 Results for complex sorts =5 =1 Complex sorts with highest training frequency

14 14 Typical mistakes Pflanze (plant) animal-object instead of plant-object zart, fleischfressend, fressend, verändert, genmanipuliert, transgen, exotisch, selten, giftig, stinkend, wachsend... Nachwuchs (offspring) human-object instead of animal-object wissenschaftlich, qualifiziert, akademisch, eigen, talentiert, weiblich, hoffnungsvoll, geeignet, begabt, journalistisch... Café (café) art-con-geogr instead of nonmov-art-discrete (cf. Restaurant) Wiener, klein, türkisch, kurdisch, romanisch, cyber, philosophisch, besucht, traditionsreich, schnieke, gutbesucht,... Neger (negro) animal-object instead of human-object weiß, dreckig, gefangen, faul, alt, schwarz, nackt, lieb, gut, brav but: Skinhead (skinhead) human-object (ok) {16,17,18,19,20,21,22,23,30}ährig, gleichaltrig, zusammengeprügelt, rechtsradikal, brutal In most cases the wrong class is semantically close. Evaluation metrics did not account for that.

15 15 Discussion of Results Binary features: Precision >98% for most binary features Assigning the smaller class is hard for bias>0.9 Context types verb-subject and verb-object are better than adjective verb-subject is best single context for complex sorts combination always helps for binary features Complex sorts Todo: more lenient combination procedure to increase recall

16 16 Conclusion Method for semantic lexicon extension High precision for binary semantic features Unknown nouns: –For 3,755 nouns not in the lexicon, a total of 125,491 binary features was assigned. –For 1,041 unknown nouns, a complex sort was assigned Combination to complex sorts yet to be improved Combination of different context types improves results

17 17 Any Questions? Thank you very much!


Download ppt "1 Combining Contexts in Lexicon Learning for Semantic Parsing May 25, 2007 NODALIDA 2007, Tartu, Estonia Chris Biemann University of Leipzig Germany Rainer."

Similar presentations


Ads by Google