Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/104640
Title: | Grounded textual entailment |
Authors: | Trong Vu, Hoa Greco, Claudio Erofeeva, Aliia Jafaritazehjan, Somayeh Linders, Guido Tanti, Marc Testoni, Alberto Bernardi, Raffaella Gatt, Albert |
Keywords: | Semantic computing Error-correcting codes (Information theory) Data sets |
Issue Date: | 2018 |
Publisher: | Association for Computational Linguistics |
Citation: | Trong Vu, H., Greco, C., Erofeeva, A., Jafaritazehjan, S., Linders, G., Tanti, M. . . Gatt, A. (2018). Grounded textual entailment. Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe. 2354-2368. |
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. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/104640 |
Appears in Collections: | Scholarly Works - InsLin |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Grounded_textual_entailment_2018.pdf Restricted Access | 1.36 MB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.