Interpreting noun compounds using paraphrases

1. Interpreting noun compounds using paraphrases András Dobó University of Oxford Stephen G. Pulman University of Oxford

2. Interpreting noun compounds using paraphrases • Motivation • Related work • Method • Results • Summary • Future work

3. Motivation • English is full of noun compounds, which are sequences of nouns acting as a single noun • Their interpretation is crucial for many NLP tasks • Using dictionaries is unfeasible • Automated methods

4. Related work • Statistical approaches • Web queries or large corpora • Two main categories of methods • Inventory based approaches • Small number of abstract relational categories • Criticized for numerous reasons • Paraphrasing approaches • Verbs and prepositions as paraphrases • Water bottle = bottle that is for water be for

5. Method • Paraphrasing method • Ranked list of paraphrases for each NC • Uses large corpora to search for paraphrases • Second noun is the head subject = second noun, object = first noun • Validates paraphrases using web queries • Two main approaches in the search of paraphrases

6. Subject-paraphrase-object-triples • Counts the frequency of all (subject, paraphrase, object) triples in the corpus • Then for each NC it searches for those triples, where subject=second noun, object=first noun • List of suitable paraphrases for each NC • Ranks paraphrases for each NC using a scoring method based on their frequency

7. Subject-paraphrase-and-paraphrase-object-pairs • Counts the frequency of all (subject, paraphrase) and (paraphrase, object) pairs in the corpus • Then for each NC it searches for those pairs, where subject=second noun, object=first noun • Two lists of paraphrases for each NC • Rank paraphrases for each NC using a scoring method based on their frequency

8. Scoring methods • Subject-paraphrase-object-triples version: • Simply the frequency of the relevant (subject, paraphrase, object) triple • Subject-paraphrase-and-paraphrase-object-pairs version: • Using frequencies is not suitable • The product of pointwise the mutual information of the relevant (subject, paraphrase) and (paraphrase, object) pairs

9. Used corpora and their preprocessing • Search for paraphrases: • British National Corpus • 100 million words • Grammatical relations from parser • Web 1T 5-gram Corpus • Generated from 1 trillion words of web page text • Grammatical relations from POS patterns • Noun verb determiner noun • Validation of paraphrases: • The Web through Google and Yahoo!

10. Passive paraphrases • Their surface subject is actually their object • (subject, paraphrase)=(paraphrase2, object) • paraphrase: passive, without preposition • paraphrase2: active version of paraphrase • subject = object • Their frequencies are counted together

11. Passive paraphrases • (subject, paraphrase, object)=(subject2, paraphrase2, object2) • paraphrase: passive, with by preposition • paraphrase2: active version of paraphrase, without preposition • object2 = subject • subject2 = object • Their frequencies are counted together • Such (paraphrase, object) and (subject2, paraphrase2) pairs are treated the same way

12. Patientive ambitransitive verbs • Three main groups of verbs: strictly transitive, strictly intransitive, ambitransitive • Strictly intransitive verbs have two subclasses: unergative and unaccusative • Ambitransitive verbs have two subclasses too: agentive and patientive • Patientive ambitransitive verbs in intransitive use behave in the same way as passive verbs they are treated the same way

13. Using synonyms, hypernyms, sister words etc. • No paraphrases are found for several NCs • Hypothesis: NCs comprising semantically similar words are interpreted the same way • Using semantically similar words in the search for paraphrases • Synonyms, hypernyms, sister words from WordNet • Semantically similar words that are automatically found with a method proposed by Dekang Lin

14. Validation of paraphrases • Some paraphrases are incorrectValidation is needed • Hypothesis: If a paraphrase is suitable for a NC, then there should exist at least some web pages containing the NC paraphrased by that paraphrase

15. Validation of paraphrases • Google and Yahoo! queries • Simple queries: “n2Infl THAT p n1Infl” • Extended queries: • Multiple verb tenses • Wildcard characters (up to 9) • Score for each paraphrase is recalculated

16. Testing and evaluation • Tested on the first 50 NCs of the SemEval-2 Task #9 • 3 best paraphrases for each NC • 5 native speakers recruited for evaluation • They score each paraphrase from 1 to 5 • Their agreement was checked using Krippendorff’s alpha, and it was too low The (noun compound, paraphrase) pairs with highest disagreement were omitted

17. Best version • Subject-paraphrase-object-triples version • Web 1T 5-gram Corpus • Combination of two basic versions: • No substitute words • Sister words • Scores are recalculated in a way that favors paraphrases returned by the first version • Validation: Google, present simple, up to 1 wildcard

18. Results • Mixed performance • Average scores • Promising results given the difficulty of task

19. Results Best scoring NCs Worst scoring NCs

20. Future work • Parsing the Web 1T 5-gram Corpus Much lower error rate in obtaining the grammatical relations • Extended validation part • Employing synonyms, hypernyms, sister words or semantically similar words • Combining the different extensions

21. Summary • Interpreting noun compounds is crucial for many NLP tasks • We presented a method for noun compound interpretation that searches for paraphrases in large corpora and issues web queries to validate the results • The results are promising, and could be further improved

22. Acknowledgements • The attendance of this workshop was partly supported by the Hungarian National Office for Research and Technology within the framework of the R&D project MASZEKER (Modell-Alapú Szemantikus Kereső Rendszer – Model Based Semantic Search System).

23. Thank you!