=Paper=
{{Paper
|id=None
|storemode=property
|title=Linguistic Affordances: Making Sense of Word Senses
|pdfUrl=https://ceur-ws.org/Vol-1100/paper15.pdf
|volume=Vol-1100
|dblpUrl=https://dblp.org/rec/conf/aiia/RuggeriC13a
}}
==Linguistic Affordances: Making Sense of Word Senses==
https://ceur-ws.org/Vol-1100/paper15.pdf
Linguistic Affordances:
Making sense of Word Senses
Alice Ruggeri and Luigi Di Caro
Department of Computer Science, University of Turin
Corso Svizzera 185, Torino, Italy
{ruggeri,dicaro}@di.unito.it
Abstract. In this position paper we want to focus the attention on the
roles of word senses in standard Natural Language Understanding tasks.
We first identify the main problems of having such a rigourous and in-
flexible way of discriminating among different meanings at word-level. In
fact, in human cognition, we know the process of language understand-
ing refers to a more shaded procedure. For this reason, we propose the
concept of linguistic affordances, i.e., combinations of objects properties
that are involved in specific actions and that help the comprehension of
the whole scene being described. The idea is that similar verbs involv-
ing similar properties of the arguments may refer to comparable mental
scenes. This architecture produces a converging framework where mean-
ing becomes a distributed property between actions and objects, without
having to differentiate among terms and relative word senses. We hope
that this contribution will stimulate the debate about the actual effective-
ness of current Word Sense Disambiguation systems towards more cog-
nitive approaches able to go beyond word-level automatic understanding
of natural language.
1 Background
In linguistics, a word sense is the meaning ascribed to a word in a given context.
A single word can have multiple senses. For instance, within the well-known
lexical database WordNet [1], the word “play” has 35 verb senses and 17 senses
as noun. This phenomenon is called polysemy. However, this must be distincted
from the concept of homonymy, where words share the same spelling and the
same pronunciation, having different and unrelated meanings. According to the
human process of disambiguating meanings, the man reads a word at a time
through a process called “word sense disambiguation”. In the Natural Language
Processing field, there exist numerous systems to automate this task, relying on
existing ontologies [2, 3] rather than through statistical approaches [4, 5].
From another perspective, an affordance is linked to the meaning of an action
that is dynamically created by the interaction of the involved agents [6–8].
Dropping this principle in natural language, an action (for example indicated
by the use of a verbal phrase) will have a certain meaning that is given by the
interaction between the agent and the receiver, and more particularly by the
their properties. The idea is that different combinations of subjects and objects
with their properties are likely to lead to different actions in terms of execution,
or final outcome.
2 Linguistic Affordances
In this work, we want to focus on the application of the concept of affordance
to the natural language understanding made by machines. If a computer could
comprehend language meanings at a more cognitive level, it would allow more
complex and fine-grained automatic operations, leading to highly-powerful sys-
tems for Information Extraction [9] and Question Answering [10].
The meaning of a word is a concept that is very easy to understand by
humans. A word sense is directly tied to a single entry in a dictionary. It applies
to nouns and verbs in the same way. Given a word with more than one meaning,
humans must proceed with the process of disambiguation using all the available
information coming from the context of use.
The affordance of a word is a more complex thing. First of all, the word
in question must refer to an action. For this reason, it is particularly oriented
towards verbs (although other language constructions can refer to actions or
events). In addition, the affordances related to an action (we will now use the
more precise term “action” instead of “word”) is suggested by the properties
(also called qualities, attributes, or characteristics) of those who act and those
who receive the action, together. The affordance is more tied with the cognitive
aspect of an action rather than its encyclopedic meaning. More precisely, it refers
to how the action can be mentally imagined. This is also in line with [11, 12], i.e.,
meanings are relativized to scenes.
For these reasons, the affordance is not directly linked to an entry in a dic-
tionary. It has no direct link with a descriptive meaning. Nevertheless, it can
coincide with it. In general, affordances and meanings are two distinct concepts
that travel on separate tracks, but which can also converge on identical units.
On the contrary, it may be the case that two distinct senses for a verb accu-
rately reflect two different subject-object contexts. In this case, word senses and
affordances coincide.
Still, a single sense can include multiple affordances. It is the case where a
word with a single meaning can be applied to multiple subject-object combina-
tions, creating different mental images of the same action.
Finally, two distinct word senses could not theoretically lead to a single lin-
guistic mental image of an action, since two different meanings are likely to
identify two different mental images. We think that it would be interesting to
see how much of such theoretical concept can be considered valid. Potentially,
two word senses can be very close semantically, inducing to a single mental im-
age (and therefore a single combination of properties). This, undoubtedly, also
depends on the level of granularity that has been chosen during the creation of
the possible senses related to a word. In any case, we want to stress the actual
independence between the two perspectives.
Word senses are completely separated. This means that they refer to mean-
ings that have the same degree of semantic distance between them. However, this
results to be quite approximate, since human cognition does not work this way.
A sense “x ” can be very similar to another sense “y”, while very distant from
a third one “z ”. More in detail, there exist the concept of “similarity between
senses” thought as the similarity of the mental models that they generate [13].
These abstractions are plausibly created by combining the properties of the
agents that are involved in the action, thus through the affordances that they
exhibit.
Let us think at the WordNet entry for the verb “to play”. Among all 35
word senses, there exist groups that share some semantics. For instance, the
word sense #3 and the word senses #6 and #7 are defined by the following
descriptions:
– To play #3: play on an instrument (“the band played all night long”)
– To play #6: replay as a melody (“play it again, Sam”, “she played the third
movement very beautifully”)
– To play #7: perform music on a musical instrument (“he plays the flute”,
“can you play on this old recorder?”)
It is noticeable that the three word senses refer to similar meanings. Within
the WordNet knowledge base, the lexicographers have manually grouped word
senses according to this idea. However, coverage of verb groups is incomplete.
Moreover, having groups of senses only solves the semantic similarity problem
to a limited extent, since the concept of similarity usually deals with more fine-
grained analyses. In literature, there are several computational models to classify
words of a text into relative word senses. On the contrary, there are no compu-
tational models to identify “scenes” or “mental images” in texts.
The Word Sense Disambiguation task is one of the most studied in compu-
tational linguistics for several reasons:
– there are a lot of available resources (often manually produced) presenting
dictionaries and corpus annotated with word senses (such as WordNet and
the SemEval competition series [1, 14]).
– it has a significant impact in the understanding of language from the compu-
tational point of view. Through the disambiguation of terms in texts it is
possible to increase the level of accuracy of different systems for Information
Retrieval, Information Extraction, Text Classification, Question Answering,
and so on.
The extraction of linguistic affordances in texts is an issue rather untouched, for
different (but correlated) reasons:
– there are no resources and manual annotation of this type of information
– affordances have a more cognitive aspect than word senses, thus they seem
less applicable
Nevertheless, we think that this type of analysis can represent a significant step
forward on the current state of the art.
3 Conclusions
In this paper we presented the limits of having fixed and word-level semantic
representations, i.e., word senses, for automatic tasks like Information Extrac-
tion and Semantic Search. Instead, we proposed an orthogonal approach where
meaning becomes a distributed property between verbs and arguments. In fu-
ture work we aim at studying how arguments properties distribute over actions
indicated by specific verbs in order to test the idea, making first comparisons
with standard word sense-based approaches for automatic natural language un-
derstanding.
References
1. Miller, G.A.: Wordnet: a lexical database for english. Communications of the ACM
38(11) (1995) 39–41
2. Agirre, E., Martinez, D.: Knowledge sources for word sense disambiguation. In:
Text, Speech and Dialogue, Springer (2001) 1–10
3. Curtis, J., Cabral, J., Baxter, D.: On the application of the cyc ontology to word
sense disambiguation. In: FLAIRS Conference. (2006) 652–657
4. Agirre, E., Soroa, A.: Personalizing pagerank for word sense disambiguation. In:
Proceedings of the 12th Conference of the European Chapter of the Association
for Computational Linguistics, Association for Computational Linguistics (2009)
33–41
5. Navigli, R., Lapata, M.: An experimental study of graph connectivity for unsu-
pervised word sense disambiguation. Pattern Analysis and Machine Intelligence,
IEEE Transactions on 32(4) (2010) 678–692
6. Gibson, J.: The concept of affordances. Perceiving, acting, and knowing (1977)
67–82
7. Ortmann, J., Kuhn, W.: Affordances as qualities. In: Formal Ontology in Infor-
mation Systems Proceedings of the Sixth International Conference (FOIS 2010).
Volume 209. (2010) 117–130
8. Osborne, F., Ruggeri, A.: A prismatic cognitive layout for adapting ontologies. In:
User Modeling, Adaptation, and Personalization. Springer (2013) 359–362
9. Sarawagi, S.: Information extraction. Foundations and trends in databases 1(3)
(2008) 261–377
10. Mendes, A.C., Coheur, L.: When the answer comes into question in question-
answering: survey and open issues. Natural Language Engineering 19(1) (2013)
1–32
11. Fillmore, C.J.: Frame semantics and the nature of language*. Annals of the New
York Academy of Sciences 280(1) (1976) 20–32
12. Fillmore, C.: Frame semantics. Linguistics in the morning calm (1982) 111–137
13. Johnson-Laird, P.: Mental models: Towards a cognitive science of language, infer-
ence, and consciousness. Number 6. Harvard University Press (1983)
14. Agirre, E., Diab, M., Cer, D., Gonzalez-Agirre, A.: Semeval-2012 task 6: A pilot on
semantic textual similarity. In: Proceedings of the First Joint Conference on Lexical
and Computational Semantics-Volume 1: Proceedings of the main conference and
the shared task, and Volume 2: Proceedings of the Sixth International Workshop
on Semantic Evaluation, Association for Computational Linguistics (2012) 385–393