Presented by: Zdeněk Žabokrtský
Report by: Eduard Bejček

• The paper describes two methods for unsupervised head assignment and tests them on two corpora byt two means (against gold standard and using it in constituency parser).
• It is the first successful unsupervised head assignment.
• There is a problem when converting dependency structures into head annotations: their algorithm doesn't guarantee exactly one head assigned among siblings.

• There is a wrong definition of entropy in Section 5.
• We found three possible interpretations of “any” in Section 3.3, second paragraph; their approach is therefore a bit unclear.
• It is also unclear, what “transformed to their respective spines” means exactly; Section 3.4, first item in the itemize.
• The greediness of the entropy model could be its main weakness resulting in not so good numbers.

• Things mentioned in the Introduction.
• The correspondence between rule based head-assignment (by Magerman-Collins) and depencencies (in PARC 700 Depencency Bank) is surprisingly low: 85%.