A Psycholinguistic Analysis of BERT's Representations of Compounds

Autor: Buijtelaar, L., Pezzelle, S., Vlachos, A., Augenstein, I.

Publikováno v: The 17th Conference of the European Chapter of the Association for Computational Linguistics: EACL 2023 : proceedings of the conference : May 2-6, 2023
The 17th Conference of the European Chapter of the Association for Computational Linguistics

This work studies the semantic representations learned by BERT for compounds, that is, expressions such as sunlight or bodyguard. We build on recent studies that explore semantic information in Transformers at the word level and test whether BERT ali

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c07ec994174592788b3b3df67d24f401
https://doi.org/10.48550/arxiv.2302.07232

Less Descriptive yet Discriminative: Quantifying the Properties of Multimodal Referring Utterances via CLIP

Autor: Takmaz, E., Pezzelle, S., Fernández, R., Chersoni, E., Hollenstein, N., Jacobs, C., Oseki, Y., Prévot, L., Santus, E.

Publikováno v: Workshop on Cognitive Modeling and Computational Linguistics: CMCL 2022 : proceedings of the workshop : May 26, 2022, 36-42
STARTPAGE=36;ENDPAGE=42;TITLE=Workshop on Cognitive Modeling and Computational Linguistics

In this work, we use a transformer-based pre-trained multimodal model, CLIP, to shed light on the mechanisms employed by human speakers when referring to visual entities. In particular, we use CLIP to quantify the degree of descriptiveness (how well

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::085dd3645b64e910ffec6169d15f51cd
https://dare.uva.nl/personal/pure/en/publications/less-descriptive-yet-discriminative-quantifying-the-properties-of-multimodal-referring-utterances-via-clip(60c3bc42-b3b0-4dcf-af49-5fb65967bdb9).html

EaSe: A Diagnostic Tool for VQA Based on Answer Diversity

Autor: Jolly, S., Pezzelle, S., Nabi, M., Toutanova, K., Rumshisky, A., Zettlemoyer, L., Hakkani-Tur, D., Beltagy, I., Bethard, S., Cotterell, R., Chakraborty, T., Zhou, Y.

Publikováno v: The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: NAACL-HLT 2021 : proceedings of the conference : June 6-11, 2021, 2407-2414
STARTPAGE=2407;ENDPAGE=2414;TITLE=The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
NAACL-HLT

We propose EASE, a simple diagnostic tool for Visual Question Answering (VQA) which quantifies the difficulty of an image, question sample. EASE is based on the pattern of answers provided by multiple annotators to a given question. In particular, it

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74ee792406ed3d7c28443ddd95adc13a
https://doi.org/10.18653/v1/2021.naacl-main.192

Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze

Autor: Takmaz, E., Pezzelle, S., Beinborn, L., Fernández, R., Webber, B., Cohn, T., He, Y., Liu, Y.

Publikováno v: Takmaz, E, Pezzelle, S, Beinborn, L & Fernández, R 2020, Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze . in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) . Association for Computational Linguistics, pp. 4664-4677 . https://doi.org/10.18653/v1/2020.emnlp-main.377
EMNLP (1)
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
2020 Conference on Empirical Methods in Natural Language Processing: EMNLP 2020 : proceedings of the conference : November 16-20, 2020
2020 Conference on Empirical Methods in Natural Language Processing
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 4664-4677
STARTPAGE=4664;ENDPAGE=4677;TITLE=Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

When speakers describe an image, they tend to look at objects before mentioning them. In this paper, we investigate such sequential cross-modal alignment by modelling the image description generation process computationally. We take as our starting p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0de5296d4ab58b0425a667f2c4e05b8f
https://doi.org/10.18653/v1/2020.emnlp-main.377

Be Different to Be Better!

Autor: Pezzelle, S., Greco, C., Gandolfi, G., Gualdoni, E., Bernardi, R., Cohn, T., He, Y., Liu, Y.

Publikováno v: Findings of the Association for Computational Linguistics : Findings of ACL: EMNLP 2020: 16-20 November, 2020, 2751-2767
STARTPAGE=2751;ENDPAGE=2767;TITLE=Findings of the Association for Computational Linguistics : Findings of ACL: EMNLP 2020
Findings of the Association for Computational Linguistics: EMNLP 2020
EMNLP (Findings)

This paper introduces BD2BB, a novel language and vision benchmark that requires multimodal models combine complementary information from the two modalities. Recently, impressive progress has been made to develop universal multimodal encoders suitabl

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::849395fbcc81a7abaaa24425f2265fea
https://doi.org/10.18653/v1/2020.findings-emnlp.248