Foundations of Natural Language Processing Semantic Role Labelling and Argument Structure
Foundations of Natural Language Processing Semantic Role Labelling and Argument Structure
Lecture 16
Semantic Role Labelling and Argument Structure
Alex Lascarides
(Slides based on those of Schneider, Koehn, Lascarides)
13 March 2020
• Often we want to know who did what to whom (when, where, how and why)
• But the same event and its participants can have different syntactic realizations.
Sandy broke the glass. vs. The glass was broken by Sandy.
She gave the boy a book. vs. She gave a book to the boy.
• syntax 6= semantics
• The semantic roles played by different participants in the sentence are not
trivially inferable from syntactical relations
• The idea of semantic roles can be combined with other aspects of meaning
(beyond this course).
Role Example
Agent The boy kicked his toy
Theme The boy kicked his toy
Experiencer The boy felt sad
Result The girl built a shelf with power tools
Instrument The girl built a shelf with power tools
Source She came from home
... ...
• Items with the “same” role (e.g., Instrument) may not behave quite the same
Sandy opened the door with a key The key opened the door
Sandy ate the salad with a fork *The fork ate the salad
• The two main NLP resources for thematic roles avoid these problems by
defining very fine-grained roles:
– Specific to individual verbs only (PropBank)
– Specific to small groups of verbs (FrameNet)
• The NLP task of identifying which words/phrases play which roles in an event.
• Supervised classification:
– Resource data is PropBank: Repository of frame files for each verb
(more shortly) plus annotations on constituents in Penn treebank with their
semantic roles (wrt the relevant frame file).
– Features are mostly related to syntactic structure and the particular words
involved
(i.e., assumes pipeline architecture)
• Current research focuses on reducing the need for training data (e.g., to work
on non-English languages)
3. Argument classification: select a role for each argument (wrt to the frame
role for the predicate’s sense).
• Useful feature: predicate-to-argument path in the tree (e.g., NP-S-VP-V).
Frame Elements:
• Grammatical relations on their own don’t determine who did what to whom
• You need to (also) know about word and phrase meanings and how they relate
to grammatical roles