natural language processing - cse
TRANSCRIPT
![Page 2: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/2.jpg)
The question "How can you construct a grammar with no appeal to meaning" is wrongly put, since the implication that obviously one can construct a grammar with appeal to meaning is totally unsupported.
- Chomsky, Syntactic Structures 1957, p.93
[Cognitive grammar] takes the radical position that grammar reduces to the structuring and symbolization of conceptual content and thus has no autonomous existence at all.
- Langacker, Grammar and Conceptualization, 2000 ,p.3
Two views of Grammar
![Page 3: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/3.jpg)
1. Colorless green ideas sleep furiously.2. Furiously sleep ideas green colorless.
Both are meaningless yet we can judge 1 as grammatical and 2 as ungrammatical.
Hence syntax is independent of meaning.
Autonomy of Syntax
![Page 4: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/4.jpg)
Probabilistic Grammar
![Page 5: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/5.jpg)
Semantics
![Page 6: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/6.jpg)
Montagovian Semantics [1973]
From [Kohlhase]
![Page 7: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/7.jpg)
![Page 8: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/8.jpg)
Semantics First: A pathway to Cognition
Conc
eptu
al
com
plex
ity
Atomic object
Relation
Event -> Argument Structuret
Analogy / Metaphor
Perceptual complexity
Chase, Come closer
In, Out, Tight, Loose
“Turn left”
![Page 9: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/9.jpg)
Instead of trying to produce a programme to simulate the adult mind, why not rather try to produce one which simulates the child's?
If this were then subjected to an appropriate course of education one would obtain the adult brain.
- Alan Turing
![Page 10: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/10.jpg)
Framenet: Semantic Roles
Familiar notion in NLP Restaurant Frame:
“John ate chicken tandoori with his fingers.”
Framenet = Comprehensive Lexicon of Frames
Roger C. Schank. 1972. Conceptual dependency: A theory of natural language processing. Cognitive Psychology,
Robert F. Simmons. 1973. Semantic networks: Their computation and use for understanding English sentences.
![Page 11: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/11.jpg)
Semantic Roles The underlying relationship that a constituent has with
the target word in a clause. Eg : John hit Bill.
Agent : John Victim : Bill
Apt for capturing semantic information -: systematic method for capturing the event structure the value that a role takes is independent of the syntactic
structure of the sentence
![Page 12: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/12.jpg)
Framenet
The Frame is the basic lexical structure that links: individual word senses, relationships between the senses of
polysemous words, relationships among semantically related
words
![Page 13: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/13.jpg)
Example Frame : IngestionFrame Elements:
Core: Eater Eaten Peripheral: Place Implement Manner Time
John [EATER]ate [lexical unit]chicken tandoori [EATEN]at the Indian Restaurant [PLACE]with his fingers [IMPLEMENT]
![Page 14: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/14.jpg)
Participant semantics
The locals (Ingestor) EAT mainly fish and fruits (Ingestibles).
As the house dosen`t have a dining room the family(Ingestor) eats in the large kitchen(Place).
She(Ingestor) took the ice-cream(ingestible) out of the fridge (source) and ate it.
Degree Ingestibles Ingestor Instrument Manner Means Place Source Time
![Page 15: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/15.jpg)
Frame : Ingestion
LexicalUnits forIngestion
![Page 16: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/16.jpg)
Parallel Sentence Analysis
As the house doesn’t have a dining room, the family [EATER] eat [Lexical Unit] in the large kitchen [PLACE].
[PLACE] [LU][EATER]
bARite bhojan kakSha nei tAi paribArer sabAi [EATER] baRa rAnnAghare [PLACE] khAy [LU].
![Page 17: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/17.jpg)
Other Semantic Categorization Schemes :
![Page 18: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/18.jpg)
Communication Verbs
![Page 19: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/19.jpg)
PropBank / VerbNeteat-39.1
Members
[drink(1 2), eat(1 2 3)]
Thematic Roles Agent[+animate] Patient[+comestible] Instrument[+concrete]
Frames
Basic Transitive () "Cynthia ate the peach" Agent V Patient
Unspecified Object Alternation () "Cynthia ate" Agent V
Conative () "Cynthia ate at the peach" Agent V Prep(at) Patient
Resultative () "Cynthia ate herself sick" Agent V Oblique Adj
![Page 20: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/20.jpg)
Semantic Tagging
Probabilistic Role Assignment based on FrameNet Corpus [Gildea, 2002]
Linking Theory : “There is a unique relationship between the syntactic and semantic structure of a sentence”
Based on features extracted from parse tree, and probability (A statistical approach)
![Page 21: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/21.jpg)
Grounded Language Learning
![Page 22: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/22.jpg)
Heider/Simmel video
[Singh et al CRV 2006]
Match object under gaze focus with words in narrative
Narrative: the little square
hit the big square[Heider and Simmel 1944]
video recreated by Bridgette Hardat Barbara Tversky lab, Stanford U
![Page 23: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/23.jpg)
Visual attention model
[Singh et al CRV 2006]
Match object under gaze focus with words in narrative
Narrative: the little square
hit the big squareMaji, Singh and Mukerjee 2005
![Page 24: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/24.jpg)
Narratives: “Chase” Video
Video and commentaries from Tversky Group, Stanford University
Wide variation in Narratives :
1. Large square corners the little circle
2. Big square approaches little circle
3. Little square is moving away from the big square; and objects inside are moving closer together
4. Big block tries to go after little circle
![Page 25: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/25.jpg)
Noun Learning
![Page 26: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/26.jpg)
Trajectories ending inside (“in”)
Based on intervals where the attended agent is ending “in” the box.
![Page 27: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/27.jpg)
Trajectories ending Outside
Learning Containment Spatial Descriptors
![Page 28: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/28.jpg)
Recognition from real video
![Page 29: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/29.jpg)
Learning Agent Appearances
![Page 30: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/30.jpg)
Shape + Haar clusters
Guha and Nandi 09 model
![Page 31: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/31.jpg)
PHOW clusters
![Page 32: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/32.jpg)
Shape + Haar clusters
Guha and Nandi 09 model
![Page 33: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/33.jpg)
Unsupervised clustering results
Guha and Nandi 09 model
![Page 34: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/34.jpg)
Sample Commentaries
![Page 35: Natural Language Processing - CSE](https://reader036.vdocuments.us/reader036/viewer/2022062609/62b61e094cc5f402cb0aa9ce/html5/thumbnails/35.jpg)
Word-ObjectAssociations
[Singh et al CRV 2006]
Match object under gaze focus with words in narrative
Narrative: the little square
hit the big square