Representing Context in FrameNet: A Multidimensional, Multimodal Approach
Frame Semantics includes context as a central aspect of the theory. Frames themselves can be regarded as a representation of the immediate context against which meaning is to be construed. Moreover, the notion of frame invocation includes context as one possible source of information comprehenders u...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2022.838441/full |
| _version_ | 1811311489042087936 |
|---|---|
| author | Tiago Timponi Torrent Ely Edison da Silva Matos Frederico Belcavello Marcelo Viridiano Maucha Andrade Gamonal Maucha Andrade Gamonal Alexandre Diniz da Costa Mateus Coutinho Marim |
| author_facet | Tiago Timponi Torrent Ely Edison da Silva Matos Frederico Belcavello Marcelo Viridiano Maucha Andrade Gamonal Maucha Andrade Gamonal Alexandre Diniz da Costa Mateus Coutinho Marim |
| author_sort | Tiago Timponi Torrent |
| collection | DOAJ |
| description | Frame Semantics includes context as a central aspect of the theory. Frames themselves can be regarded as a representation of the immediate context against which meaning is to be construed. Moreover, the notion of frame invocation includes context as one possible source of information comprehenders use to construe meaning. As the original implementation of Frame Semantics, Berkeley FrameNet is capable of providing computational representations of some aspects of context, but not all of them. In this article, we present FrameNet Brasil: a framenet enriched with qualia relations and capable of taking other semiotic modes as input data, namely pictures and videos. We claim that such an enriched model is capable of addressing other types of contextual information in a framenet, namely sentence-level cotext and commonsense knowledge. We demonstrate how the FrameNet Brasil software infrastructure addresses contextual information in both database construction and corpora annotation. We present the guidelines for the construction of two multimodal datasets whose annotations represent contextual information and also report on two experiments: (i) the identification of frame-evoking lexical units in sentences and (ii) a methodology for domain adaptation in Neural Machine Translation that leverages frames and qualia for representing sentence-level context. Experimental results emphasize the importance of computationally representing contextual information in a principled structured fashion as opposed to trying to derive it from the manipulation of linguistic form alone. |
| first_indexed | 2024-04-13T10:18:37Z |
| format | Article |
| id | doaj.art-8e37812e0f624218a2a9c409f89fe7de |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-04-13T10:18:37Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-8e37812e0f624218a2a9c409f89fe7de2022-12-22T02:50:34ZengFrontiers Media S.A.Frontiers in Psychology1664-10782022-04-011310.3389/fpsyg.2022.838441838441Representing Context in FrameNet: A Multidimensional, Multimodal ApproachTiago Timponi Torrent0Ely Edison da Silva Matos1Frederico Belcavello2Marcelo Viridiano3Maucha Andrade Gamonal4Maucha Andrade Gamonal5Alexandre Diniz da Costa6Mateus Coutinho Marim7FrameNet Brasil, Graduate Program in Linguistics, Faculty of Letters, Federal University of Juiz de Fora, Juiz de Fora, BrazilFrameNet Brasil, Graduate Program in Linguistics, Faculty of Letters, Federal University of Juiz de Fora, Juiz de Fora, BrazilFrameNet Brasil, Graduate Program in Linguistics, Faculty of Letters, Federal University of Juiz de Fora, Juiz de Fora, BrazilFrameNet Brasil, Graduate Program in Linguistics, Faculty of Letters, Federal University of Juiz de Fora, Juiz de Fora, BrazilFrameNet Brasil, Graduate Program in Linguistics, Faculty of Letters, Federal University of Juiz de Fora, Juiz de Fora, BrazilLaboratório Experimental de Tradução, Graduate Program in Linguistics, Faculty of Letters, Federal University of Minas Gerais, Belo Horizonte, BrazilFrameNet Brasil, Graduate Program in Linguistics, Faculty of Letters, Federal University of Juiz de Fora, Juiz de Fora, BrazilFrameNet Brasil, Graduate Program in Linguistics, Faculty of Letters, Federal University of Juiz de Fora, Juiz de Fora, BrazilFrame Semantics includes context as a central aspect of the theory. Frames themselves can be regarded as a representation of the immediate context against which meaning is to be construed. Moreover, the notion of frame invocation includes context as one possible source of information comprehenders use to construe meaning. As the original implementation of Frame Semantics, Berkeley FrameNet is capable of providing computational representations of some aspects of context, but not all of them. In this article, we present FrameNet Brasil: a framenet enriched with qualia relations and capable of taking other semiotic modes as input data, namely pictures and videos. We claim that such an enriched model is capable of addressing other types of contextual information in a framenet, namely sentence-level cotext and commonsense knowledge. We demonstrate how the FrameNet Brasil software infrastructure addresses contextual information in both database construction and corpora annotation. We present the guidelines for the construction of two multimodal datasets whose annotations represent contextual information and also report on two experiments: (i) the identification of frame-evoking lexical units in sentences and (ii) a methodology for domain adaptation in Neural Machine Translation that leverages frames and qualia for representing sentence-level context. Experimental results emphasize the importance of computationally representing contextual information in a principled structured fashion as opposed to trying to derive it from the manipulation of linguistic form alone.https://www.frontiersin.org/articles/10.3389/fpsyg.2022.838441/fullFrameNetqualia structuremultimodal semantic representationdomain adaptation in neural machine translationcontext |
| spellingShingle | Tiago Timponi Torrent Ely Edison da Silva Matos Frederico Belcavello Marcelo Viridiano Maucha Andrade Gamonal Maucha Andrade Gamonal Alexandre Diniz da Costa Mateus Coutinho Marim Representing Context in FrameNet: A Multidimensional, Multimodal Approach Frontiers in Psychology FrameNet qualia structure multimodal semantic representation domain adaptation in neural machine translation context |
| title | Representing Context in FrameNet: A Multidimensional, Multimodal Approach |
| title_full | Representing Context in FrameNet: A Multidimensional, Multimodal Approach |
| title_fullStr | Representing Context in FrameNet: A Multidimensional, Multimodal Approach |
| title_full_unstemmed | Representing Context in FrameNet: A Multidimensional, Multimodal Approach |
| title_short | Representing Context in FrameNet: A Multidimensional, Multimodal Approach |
| title_sort | representing context in framenet a multidimensional multimodal approach |
| topic | FrameNet qualia structure multimodal semantic representation domain adaptation in neural machine translation context |
| url | https://www.frontiersin.org/articles/10.3389/fpsyg.2022.838441/full |
| work_keys_str_mv | AT tiagotimponitorrent representingcontextinframenetamultidimensionalmultimodalapproach AT elyedisondasilvamatos representingcontextinframenetamultidimensionalmultimodalapproach AT fredericobelcavello representingcontextinframenetamultidimensionalmultimodalapproach AT marceloviridiano representingcontextinframenetamultidimensionalmultimodalapproach AT mauchaandradegamonal representingcontextinframenetamultidimensionalmultimodalapproach AT mauchaandradegamonal representingcontextinframenetamultidimensionalmultimodalapproach AT alexandredinizdacosta representingcontextinframenetamultidimensionalmultimodalapproach AT mateuscoutinhomarim representingcontextinframenetamultidimensionalmultimodalapproach |