lecture 3: semantic role labelling

Seman&c Analysis in Language Technology http://stp.lingfil.uu.se/~santinim/sais/2014/sais_2014.htm

Seman&c Role Labelling

/ Predicate-‐Argument Structure

Marina San&ni

[email protected]

Department of Linguis&cs and Philology Uppsala University, Uppsala, Sweden

Autumn 2014

Lecture 3: SRL/PAS 1

Outline

•  Seman&c (thema&c) Roles •  Seman&c Role Labelling/Predicate-‐Argument Structure


The seman&cs of events •  Predicates in FOL have fixed arity: they take a fixed number of arguments – predicates have a fixed arity


event variables à (neo) Davidsonian event representa&on

•  No need to specify a fixed number of arguments •  The event itself is a single argument. •  Everything else is captured by addi&onal predica&on

!Ǝe eating(e) ∧ eater(e, speaker)∧ eaten(e,turkey sandwich) ∧ meal(e,lunch) ∧ location(e,desk)∧time(e,tuesday)!


What is the seman&c similarity here?

•  John broke the window Ǝe x,y, breaking(e) ∧ breaker(e, x) ∧ john(e,x)brokenThing(e,y) ∧ window(e,y)!

•  Mary opend the door Ǝe x,y, opening(e) ∧ opener(e, x) ∧ mary(e,x) ∧ openThing(e,y) ∧ door(e,y)#


Deep roles = agents

Examples: Thema&c Roles

•  Thema&c roles refer to a par&cular model of seman&c roles

•  Them roles try to capture the seman&c commonality betw breaker and eater à agents à voli&onal causa&on

•  brokenThing and openedThing are inanimate objects that are affected by te ac&on à themes


2 seman&c constraints on the arguments of event predicate

1.  Seman&c Roles 2.  Selec&onal Constraints


I. Seman&c Roles

•  Express the seman&c of the arguments and its rela&on to predicate


Examples

•  Some common roles


Why are they useful?

•  Help generalize over different surface realiza&ons of predicate arguments.

•  Ex: Diathesis


Problems •  No standard set of roles •  Some&mes, many fine-‐grained roles •  Difficult to formalize

•  Solu&on? – Generalized seman&c roles

•  PROTO-‐AGENT, PROTO-‐PATIENT, etc. … the more an argument displays agent-‐like proper&es (voli&on, inten&onality etc), the greater the possibility that the argument can be labelled a proto-‐agent…


Predicate-‐Argument Structure

The argument structure of a verb is the lexical informa&on about the arguments of a predicate and their seman&c and syntac&c proper&es. Argument structure is generally seen as intermediate between seman&c-‐role structure and syntac&c-‐func&on structure. See: h^p://www.glo^opedia.org/index.php/Argument_structure


Ex Argument structure is what makes a lexical head induce argument posi&ons in syntac&c structure is called its argument structure. Example: the head open has an argument structure which induces obligatorily one argument posi&on (Theme), and op&onally two more (Agent and Instrument).


PropBank •  Resource of sentences annotated with seman&c roles. –  The English PropBank: sentences from the PennTreeBank.

•  Each sense of each verb has a specific set of roles: – Arg0 = proto-‐agent – Arg1 = proto-‐pa&ent –  The seman&c of the other roles is specific to each verb sense…


Ex •  Same role, despite the differing surface forms: increase and Arg1


FrameNet

•  Project that a^empts to generalize seman&c roles on different verbs and also betw verbs and nouns


Frame •  A structure with seman&c roles includes frame elements: – Core roles – Non-‐core roles


Each word evoke a frame

•  Ex: change_posi&on_on_a_scale


II. Selec&onal Restric&ons •  Seman&c constraints on arguments

•  Constraints that the verb imposes on the concepts that are allowed to fill its arguments roles.

–  I want to eat home –  I want to eat French food

How do we know that ”home” is not a argument of eat? Seman&cally, we can say that the theme of ”eat” is edible. edible becomes a selec&onal restric&on of the theme of eat.


Selec&onal Restric&ons and FOL

•  neo-‐Davidsonian representa&on of events:


•  Drawbacks (p. 662) –  Using FOL for a simple task like this is overkill. Far too computa&onally expensive

–  We would need a KB of facts and concepts that is very large…

A more prac&cal approach •  State selec&onal restric&ons in terms f WordNet synsets rather than as logical concepts.

•  Each predicate simply specifies a WordNet synset as the selec&onal restrictons on each of its arguments.

ex: eat (food, nutrient) Selec&onal restric&on o the theme role of eat to the sysets àfood, nutrient


Seman&c Role Labelling

•  Synonyms: – Thema&c role labelling – Case role assignment – Shallow seman&c parsing

•  What is it? – The task of automa&cally finding the appropriate role for each predicate in a sentence


Current Approaches

•  Based on supervised machine learning – Adequate amounts of training and testng sets. – FrameNet and PropBank have been used for this purpose.


Features suggested by Gildea and Jurafsky (2000, 2002)


Vectors of Features

•  SVM, Maximum Entropy and other classifiers


The End


lecture 3: semantic role labelling

Education