Search Results for author:
Found 27 papers, 1 papers with code
Distributional properties of political dogwhistle representations in Swedish BERT
“Dogwhistles” are expressions intended by the speaker have two messages: a socially-unacceptable “in-group” message understood by a subset of listeners, and a benign message intended for the out-group.
Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences
The image sequences are aligned with a total of 12K stories which were collected via crowdsourcing given the image sequences and a set of grounded characters from the corresponding image sequence.
Multi-Task Learning for Joint Semantic Role and Proto-Role Labeling
Unlike previous work, our model does not require pre-training or fine-tuning on additional tasks, beyond using off-the-shelf (static or contextual) embeddings and supervision.
Where's the Learning in Representation Learning for Compositional Semantics and the Case of Thematic Fit
Observing that for certain NLP tasks, such as semantic role prediction or thematic fit estimation, random embeddings perform as well as pretrained embeddings, we explore what settings allow for this and examine where most of the learning is encoded: the word embeddings, the semantic role embeddings, or ``the network''.
Semantic shift in social networks
Just as the meaning of words is tied to the communities in which they are used, so too is semantic change.
Thematic Fit Bits: Annotation Quality and Quantity Interplay for Event Participant Representation
We compare the old and new corpus versions' impact on a verb--argument fit modeling task, using a high-performing neural approach.
Diverse and Relevant Visual Storytelling with Scene Graph Embeddings
A problem in automatically generated stories for image sequences is that they use overly generic vocabulary and phrase structure and fail to match the distributional characteristics of human-generated text.
Ranked #5 on
Visual Storytelling
on VIST
Exploiting Cross-Lingual Hints to Discover Event Pronouns
Non-nominal co-reference is much less studied than nominal coreference, partly because of the lack of annotated corpora.
Building Sense Representations in Danish by Combining Word Embeddings with Lexical Resources
Our aim is to identify suitable sense representations for NLP in Danish.
An Annotation Approach for Social and Referential Gaze in Dialogue
This paper introduces an approach for annotating eye gaze considering both its social and the referential functions in multi-modal human-human dialogue.
A Hybrid Model for Globally Coherent Story Generation
The model exploits a symbolic text planning module to produce text plans, thus reducing the demand of data; a neural surface realization module then generates fluent text conditioned on the text plan.
Verb-Second Effect on Quantifier Scope Interpretation
Sentences like {``}Every child climbed a tree{''} have at least two interpretations depending on the precedence order of the universal quantifier and the indefinite.
Learning distributed event representations with a multi-task approach
Human world knowledge contains information about prototypical events and their participants and locations.
Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction
Recent research in psycholinguistics has provided increasing evidence that humans predict upcoming content.
