19.4.5 FrameNet

While making inferences about the semantic commonalities across different sentences with increase is useful, it would be even more useful if we could make such inferences in many more situations, across different verbs, and also between verbs and nouns.

For example, we'd like to extract the similarity between these three sentences:

[Arg1 The price of bananas] increased [Arg2 5%].

(19.40) [Arg1 The price of bananas] rose [Arg2 5%].

(19.41) There has been a $ [\text{Arg}_2\ 5\%] $ rise $ [\text{Arg}_1 $ in the price of bananas].

Note that the second example uses the different verb rise, and the third example uses the noun rather than the verb rise. We'd like a system to recognize that the price of bananas is what went up, and that 5% is the amount it went up, no matter whether the 5% appears as the object of the verb increased or as a nominal modifier of the noun rise.

The FrameNet project is another semantic role labeling project that attempts to address just these kinds of problems (Baker et al., 1998; Lowe et al., 1997; Ruppenhofer et al., 2006). Where roles in the PropBank project are specific to an individual verb, roles in the FrameNet project are specific to a frame. A frame is a script-like structure, which instantiated a set of frame-specific semantic roles called frame elements. Each word evokes a frame and profiles some aspect of the frame and its elements. For example, the change_position_on_a_scale frame is defined as follows:

This frame consists of words that indicate the change of an Item's position on a scale (the Attribute) from a starting point (Initial_value) to an end point (Final_value).

Some of the semantic roles (frame elements) in the frame, separated into core roles and non-core roles, are defined as follows (definitions are taken from the FrameNet labelers guide (Ruppenhofer et al., 2006)).

Core Roles

ATTRIBUTE The ATTRIBUTE is a scalar property that the ITEM possesses.

ATTRIBUTE THE ATTRIBUTE is a scalar property that the ITEM possesses. DIFFERENCE The distance by which an ITEM changes its position on the scale.

FINAL_STATE A description that presents the ITEM's state after the change in the ATTRIBUTE's value as an independent predication.

FINAL_VALUE The position on the scale where the Item ends up.

INITIAL_STATE A description that presents the ITEM's state before the change in the ATTRIBUTE's value as an independent predication.

INITIAL_VALUE The initial position on the scale from which the ITEM moves away.

ITEM The entity that has a position on the scale.

VALUE_RANGE A portion of the scale, typically identified by its end points, along which the values of the ATTRIBUTE fluctuate.

Some Non-Core Roles

DURATION The length of time over which the change takes place.

SPEED The rate of change of the VALUE.

GROUP The GROUP in which an ITEM changes the value of an ATTRIBUTE in a specified way.

Here are some example sentences:

(19.42) [ITEM Oil] rose [ATTRIBUTE in price] in price [DIFFERENCE by 2%].

(19.43) [ITEM It] has increased [FINAL STATE to having them 1 day a month].

(19.44) [ITEM Microsoft shares] fell [FINAL VALUE to 7 5/8].

(19.45) [ITEM Colon cancer incidence] fell [DIFFERENCE by 50%] [GROUP among men].

(19.46) a steady increase [INITIAL_VALUE from 9.5] [FINAL_VALUE to 14.3] [ITEM in dividends]

(19.47) a [DIFFERENCE 5%] [ITEM dividend] increase...

Note from these example sentences that the frame includes target words like rise, fall, and increase. In fact, the complete frame consists of the following words:

VERBS: dwindle move soar escalation shift

advance edge mushroom swell explosion tumble

climb explode plummet swing fall

decline fall reach triple fluctuation ADVERBS:

decrease fluctuate rise tumble gain increasingly

diminish gain rocket growth

dip grow shift NOUNS: hike

double increase skyrocket decline increase

drop jump slide decrease rise

FrameNet also codes relationships between frames and frame elements. Frames can inherit from each other, and generalizations among frame elements in different frames can be captured by inheritance as well. Other relations between frames like causation are also represented. Thus there is a Cause_change_of_position_on_a_scale frame which is linked to the Change_of_position_on_a_scale frame by the cause relation, but adds an AGENT role and is used for causative examples such as the following:

[AGENT They] raised [ITEM the price of their soda] [DIFFERENCE by 2%].

Together, these two frames would allow an understanding system to extract the common event semantics of all the verbal and nominal causative and non-causative usages.

Ch. 20 will discuss automatic methods for extracting various kinds of semantic roles; indeed one main goal of PropBank and FrameNet is to provide training data for such semantic role labeling algorithms.