From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions (original) (raw)
Denotation Graph
HTML view of the Denotation Graph
Denotation Graph Download
We define ⟦ s ⟧, the visual denotation of a linguistic expression_s_ (e.g. a sentence, verb phrase or noun phrase), to be the set of images that depict what it describes. The denotation graph pairs a large number of linguistic expressions with their visual denotations, and defines a large subsumption hierarchy over these expressions. Consider the following fragment of our denotation graph1:
Each node in the graph corresponds to a string s and its denotation:
If s (e.g. s="two dogs running" ) is the parent of_t_ (e.g. t="two dogs running in the grass" ) in the denotation graph, s is more generic than t, and there is one linguistic operation (here, the addition of the prepositional phrase "in the grass") that turns s into_t_. Hence, any image that depicts t (two dogs running in the grass) must also depict s (two dogs running), and ⟦ t ⟧ ⊆ ⟦ s ⟧. Thus, the visual denotation of a parent s will subsume the visual denotation of any of its children t.
We provide below the data files that make up the denotation graph we have created from the Flickr 30k Dataset. The graph consists of a set of strings that define the nodes of the graph (dog, running,grass, etc...), the edges that connect those nodes (dog running can be created from running by adding the subject_dog_, and can be created from dog by adding the verb_running_), and the images that depict each string in the graph.
Additionally, we have computed two different kinds of denotational similarity metrics computed on the nodes in the graph: (normalized) pointwise mutual information, PMI(s, t), and conditional probabilities, P(s | t ). Our paper shows that these similarity metrics are at least as beneficial as distributional similarities for two tasks that require semantic inference. For example:
| s | PMI(s, play baseball) | P(play baseball | s) |
|---|---|---|
| tag him | 0.673 | 0.600 |
| hold bat | 0.627 | 0.368 |
| try to tag | 0.616 | 0.517 |
| slide into base | 0.569 | 0.278 |
| hold bat | 0.627 | 0.368 |
| pitch | 0.561 | 0.200 |
Approximate Textual Entailment
The approximate textual entailment task generates textual entailment items using the Flickr 30k Dataset and our denotation graph. We use captions from the Flickr 30k Dataset as premises, and try to determine if they entail strings from the denotation graph.
| Premises: | A woman with dark hair in bending, open mouthed, towards the back of a dark headed toddler's head. |
|---|---|
| A dark-haired woman has her mouth open and is hugging a little girl while sitting on a red blanket. | |
| A grown lady is snuggling on the couch with a young girl and the lady has a frightened look. | |
| A mom holding her child on a red sofa while they are both having fun. | |
| Hypothesis: | make face |
Downloads
Please fill in the following form to request access to the Flickr 30k Dataset and the Denotation Graph. Note that the Flickr 30k Dataset includes images obtained from Flickr. Use of the images must abide by the Flickr Terms of Use. We do not own the copyright of the images. They are solely provided at the link below for researchers and educators who wish to use the dataset for non-commercial research and/or educational purposes.
1. In our actual denotation graph, words are lemmatized, so two dogs running becomes two dog run.