In computational linguistics, FrameNet is a project housed at the International Computer Science Institute in Berkeley, California which produces an electronic resource based on a theory of meaning called frame semantics. FrameNet reveals for example that the sentence "John sold a car to Mary" essentially describes the same basic situation (semantic frame) as "Mary bought a car from John", just from a different perspective. A semantic frame can be thought of as a conceptual structure describing an event, relation, or object and the participants in it. The FrameNet lexical database contains over 1,200 semantic frames, 13,000 lexical units (a pairing of a word with a meaning; polysemous words are represented by several lexical units) and 202,000 example sentences. FrameNet is largely the creation of Charles J. Fillmore, who developed the theory of frame semantics that the project is based on, and was initially the project leader when the project began in 1997. Collin Baker became the project manager in 2000. The FrameNet project has been influential in both linguistics and natural language processing, where it led to the task of automatic Semantic Role Labeling.
A frame is a schematic representation of a situation involving various participants, props, and other conceptual roles. Examples of frame names are
Locative_relation. A frame in FrameNet contains a textual description of what it represents (a frame definition), associated frame elements, lexical units, example sentences, and frame-to-frame relations.
Frame elements (FE) provide additional information to the semantic structure of a sentence. Each frame has a number of core and non-core FEs which can be thought of as semantic roles. Core FEs are essential to the meaning of the frame while non-core FEs are generally descriptive (such as time, place, manner, etc.).
Some examples include:
- The only core FE of the
Being_bornframe is called
Child; non-core FEs being
- Core FEs of the
Goods, among other things, while non-core FEs include a
FrameNet includes shallow data on syntactic roles that frame elements play in the example sentences. For an example sentence like "She was born about AD 460", FrameNet would mark "She" as a noun phrase referring to the
Child FE, and "about AD 460" as a noun phrase corresponding to the
Time frame element. Details of how frame elements can be realized in a sentence are important because this reveals important information about the subcategorization frames as well as possible diathesis alternations (e.g. "John broke the window" vs. "The window broke")
of a verb.
Lexical units (LU) are lemmas, with their part of speech, that evoke a specific frame. In other words, when a LU is identified in a sentence, that specific LU can be associated with its specific frame(s). For each frame, there are many LUs associated to one frame and many frames that share multiple LUs, this is typically the case with LUs that have multiple word senses. Alongside the frame, each lexical unit is associated with specific frame elements by means of the annotated example sentences.
Frames are associated with example sentences and frame elements are marked within the sentences. Thus the sentence
- She was born about AD 460
is associated with the frame
Being_born, while "She" is marked as the frame element
Child and "about AD 460" is marked as
(See the FrameNet Annotation Report for
From the start, the FrameNet project has been committed to looking at evidence from actual language use as found in text collections like the British National Corpus.
Based on such example sentences, automatic semantic role labeling tools are able to determine frames and mark frame elements in new sentences.
FrameNet also exposes the statistics on the valences of the frames, that is the number and the position of the frame elements within example sentences. The sentence
- She was born about AD 460
falls in the valence pattern
- NP Ext, INI --, NP Dep
which occurs two times in the example sentences in FrameNet, namely in:
- She was born about AD 460, daughter and granddaughter of Roman and Byzantine emperors, whose family had been prominent in Roman politics for over 700 years.
- He was soon posted to north Africa, and never met their only child, a daughter born 8 June 1941.
FrameNet additionally captures relationships between different frames using relations. These include the following.
- Inheritance: When one frame is a more specific version of another, more abstract parent frame. Anything that is true about the parent frame must also be true about the child frame, and a mapping is specified between the frame elements of the parent and the frame elements of the child.
- Perspectivized_in: A neutral frame (like
Commerce_transfer-goods) is connected to a frame with a specific perspective of the same scenario (e.g. the
Commerce_sellframe, which assumes the perspective of the seller or the
Commerce_buyframe, which assumes the perspective of the buyer)
- Subframe: Some frames like the
Criminal_processframe refer to complex scenarios that consist of several individual states or events that can be described by separate frames like
Trial, and so on.
- Precedes: The Precedes relation captures a temporal order that holds between subframes of a complex scenario.
- Causative_of and Inchoative_of: There is a fairly systematic relationship between stative descriptions (e.g. the
Position_on_a_scaleframe, "She had a high salary") and causative descriptions (
Cause_change_of_scalar_position, "She raised his salary") or inchoative descriptions (
Change_position_on_a_scale, e.g. "Her salary increased").
- Using: A relationship that holds between a frame that in some way involves another frame. For instance, the
Judgment_communicationframe uses both the
Judgmentframe and the
Statementframe, but does not inherit from either of them because there is no clear correspondence of the frame elements.
- See_also: Connects frames that bear some resemblance but need to be distinguished carefully.
FrameNet has proven useful in a number of computational applications, because computers need additional knowledge in order to recognize that "John sold a car to Mary" and "Mary bought a car from John" describe essentially the same situation, despite using two quite different verbs, different prepositions and a different word order. FrameNet has been used in applications like question answering, paraphrasing, recognizing textual entailment, and information extraction, either directly or by means of Semantic Role Labeling tools. The first automatic system for Semantic Role Labeling (SRL, sometimes also referred to as "shallow semantic parsing") was developed by Daniel Gildea and Daniel Jurafsky based on FrameNet in 2002. Semantic Role Labeling has since become one of the standard tasks in natural language processing, with the latest version (1.7) of FrameNet now fully supported in the Natural Language Toolkit.
Since frames are essentially semantic descriptions, they are similar across languages, and several projects have arisen over the years that have relied on the original FrameNet as the basis for additional non-English FrameNets, for Spanish, Japanese, German, and Polish, among others.
- Cliff Goddard (25 September 2011). Semantic Analysis: A Practical Introduction. Oxford University Press. pp. 78–81. ISBN 978-0-19-956028-8. Retrieved 21 March 2012.
- Heine, Bernd; Narrog, Heiko (eds.). The Oxford Handbook of Linguistic Analysis. Oxford University Press. p. 20. ISBN 978-0-19-160925-1. Retrieved 21 March 2012.
- Gildea, Daniel; Jurafsky, Daniel (2002). "Automatic Labeling of Semantic Roles" (PDF). Computational Linguistics. 28 (3): 245–288. doi:10.1162/089120102760275983.
- Schneider, Nathan; Wooters, Chuck (2017). "The NLTK FrameNet API: Designing for Discoverability with a Rich Linguistic Resource". EMNLP 2017: Conference on Empirical Methods in Natural Language Processing. arXiv:1703.07438.
- Ruppenhofer, Josef; Ellsworth, Michael; Petruck, Miriam R. L.; Johnson, Christopher R.; Baker, Collin F.; Scheffczyk, Jan (November 1, 2016). FrameNet II: Extended Theory and Practice (revised ed.). Berkeley, CA: International Computer Science Institute.