Grounded Textual Entailment

Hoa Trong Vu, Claudio Greco, Aliia Erofeeva, Somayeh Jafaritazehjan, Guido Linders, Marc Tanti, Alberto Testoni, Raffaella Bernardi, Albert Gatt

[How to correct problems with metadata yourself]

Abstract
Capturing semantic relations between sentences, such as entailment, is a long-standing challenge for computational semantics. Logic-based models analyse entailment in terms of possible worlds (interpretations, or situations) where a premise P entails a hypothesis H iff in all worlds where P is true, H is also true. Statistical models view this relationship probabilistically, addressing it in terms of whether a human would likely infer H from P. In this paper, we wish to bridge these two perspectives, by arguing for a visually-grounded version of the Textual Entailment task. Specifically, we ask whether models can perform better if, in addition to P and H, there is also an image (corresponding to the relevant “world” or “situation”). We use a multimodal version of the SNLI dataset (Bowman et al., 2015) and we compare “blind” and visually-augmented models of textual entailment. We show that visual information is beneficial, but we also conduct an in-depth error analysis that reveals that current multimodal models are not performing “grounding” in an optimal fashion.
Anthology ID:
C18-1199
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2354–2368
Language:
URL:
https://aclanthology.org/C18-1199
DOI:
Bibkey:
Cite (ACL):
Hoa Trong Vu, Claudio Greco, Aliia Erofeeva, Somayeh Jafaritazehjan, Guido Linders, Marc Tanti, Alberto Testoni, Raffaella Bernardi, and Albert Gatt. 2018. Grounded Textual Entailment. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2354–2368, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Grounded Textual Entailment (Vu et al., COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/C18-1199.pdf
Code
 claudiogreco/coling18-gte
Data
Flickr30k, Penn Treebank, SICK, SNLI, Visual Genome, Visual Question Answering
PDF Search Code