We release ManyNames v2 (MN v2), a verified version of an object naming dataset that contains dozens of valid names per object for 25K images. We analyze issues in the data collection method originally employed, standard in Language & Vision (L&V), and find that the main source of noise in the data comes from simulating a naming context solely from an image with a target object marked with a bounding box, which causes subjects to sometimes disagree regarding which object is the target. We also find that both the degree of this uncertainty in the original data and the amount of true naming variation in MN v2 differs substantially across object domains. We use MN v2 to analyze a popular L&V model and demonstrate its effectiveness on the task of object naming. However, our fine-grained analysis reveals that what appears to be human-like model behavior is not stable across domains, e.g., the model confuses people and clothing objects much more frequently than humans do. We also find that standard evaluations underestimate the actual effectiveness of the naming model: on the single-label names of the original dataset (Visual Genome), it obtains −27% accuracy points than on MN v2, that includes all valid object names.
People choose particular names for objects, such as dog or puppy for a given dog. Object naming has been studied in Psycholinguistics, but has received relatively little attention in Computational Linguistics. We review resources from Language and Vision that could be used to study object naming on a large scale, discuss their shortcomings, and create a new dataset that affords more opportunities for analysis and modeling. Our dataset, ManyNames, provides 36 name annotations for each of 25K objects in images selected from VisualGenome. We highlight the challenges involved and provide a preliminary analysis of the ManyNames data, showing that there is a high level of agreement in naming, on average. At the same time, the average number of name types associated with an object is much higher in our dataset than in existing corpora for Language and Vision, such that ManyNames provides a rich resource for studying phenomena like hierarchical variation (chihuahua vs. dog), which has been discussed at length in the theoretical literature, and other less well studied phenomena like cross-classification (cake vs. dessert).
Humans use language to refer to entities in the external world. Motivated by this, in recent years several models that incorporate a bias towards learning entity representations have been proposed. Such entity-centric models have shown empirical success, but we still know little about why. In this paper we analyze the behavior of two recently proposed entity-centric models in a referential task, Entity Linking in Multi-party Dialogue (SemEval 2018 Task 4). We show that these models outperform the state of the art on this task, and that they do better on lower frequency entities than a counterpart model that is not entity-centric, with the same model size. We argue that making models entity-centric naturally fosters good architectural decisions. However, we also show that these models do not really build entity representations and that they make poor use of linguistic context. These negative results underscore the need for model analysis, to test whether the motivations for particular architectures are borne out in how models behave when deployed.
We address the task of visual semantic role labeling (vSRL), the identification of the participants of a situation or event in a visual scene, and their labeling with their semantic relations to the event or situation. We render candidate participants as image regions of objects, and train a model which learns to ground roles in the regions which depict the corresponding participant. Experimental results demonstrate that we can train a vSRL model without reliance on prohibitive image-based role annotations, by utilizing noisy data which we extract automatically from image captions using a linguistic SRL system. Furthermore, our model induces frame—semantic visual representations, and their comparison to previous work on supervised visual verb sense disambiguation yields overall better results.
This paper describes our winning contribution to SemEval 2018 Task 4: Character Identification on Multiparty Dialogues. It is a simple, standard model with one key innovation, an entity library. Our results show that this innovation greatly facilitates the identification of infrequent characters. Because of the generic nature of our model, this finding is potentially relevant to any task that requires the effective learning from sparse or imbalanced data.
In this paper, we present HeiNER, the multilingual Heidelberg Named Entity Resource. HeiNER contains 1,547,586 disambiguated English Named Entities together with translations and transliterations to 15 languages. Our work builds on the approach described in (Bunescu and Pasca, 2006), yet extends it to a multilingual dimension. Translating Named Entities into the various target languages is carried out by exploiting crosslingual information contained in the online encyclopedia Wikipedia. In addition, HeiNER provides linguistic contexts for every NE in all target languages which makes it a valuable resource for multilingual Named Entity Recognition, Disambiguation and Classification. The results of our evaluation against the assessments of human annotators yield a high precision of 0.95 for the NEs we extract from the English Wikipedia. These source language NEs are thus very reliable seeds for our multilingual NE translation method.