Transductive Visual Verb Sense Disambiguation
This work provides a more data-efficient solution for Visual Verb Sense Disambiguation, which is a challenging task due to the complexity of annotating multimodal datasets requiring both linguistic and visual expertise.
This paper addresses Visual Verb Sense Disambiguation (VVSD), where the goal is to assign the correct sense to a verb based on an accompanying image. The authors propose a transductive semi-supervised learning approach that significantly outperforms the state-of-the-art on the VerSe dataset while using only a small fraction of labeled samples.
Verb Sense Disambiguation is a well-known task in NLP, the aim is to find the correct sense of a verb in a sentence. Recently, this problem has been extended in a multimodal scenario, by exploiting both textual and visual features of ambiguous verbs leading to a new problem, the Visual Verb Sense Disambiguation (VVSD). Here, the sense of a verb is assigned considering the content of an image paired with it rather than a sentence in which the verb appears. Annotating a dataset for this task is more complex than textual disambiguation, because assigning the correct sense to a pair of $<$image, verb$>$ requires both non-trivial linguistic and visual skills. In this work, differently from the literature, the VVSD task will be performed in a transductive semi-supervised learning (SSL) setting, in which only a small amount of labeled information is required, reducing tremendously the need for annotated data. The disambiguation process is based on a graph-based label propagation method which takes into account mono or multimodal representations for $<$image, verb$>$ pairs. Experiments have been carried out on the recently published dataset VerSe, the only available dataset for this task. The achieved results outperform the current state-of-the-art by a large margin while using only a small fraction of labeled samples per sense. Code available: https://github.com/GiBg1aN/TVVSD.