Anaphora and coreference resolution: A review
Coreference resolution aims at resolving repeated references to an object in a document
and forms a core component of natural language processing (NLP) research. When used as …
and forms a core component of natural language processing (NLP) research. When used as …
A brief survey on recent advances in coreference resolution
The task of resolving repeated objects in natural languages is known as coreference
resolution, and it is an important part of modern natural language processing. It is classified …
resolution, and it is an important part of modern natural language processing. It is classified …
A survey on semantic processing techniques
Semantic processing is a fundamental research domain in computational linguistics. In the
era of powerful pre-trained language models and large language models, the advancement …
era of powerful pre-trained language models and large language models, the advancement …
DeepStruct: Pretraining of language models for structure prediction
We introduce a method for improving the structural understanding abilities of language
models. Unlike previous approaches that finetune the models with task-specific …
models. Unlike previous approaches that finetune the models with task-specific …
Toward gender-inclusive coreference resolution
YT Cao, H Daumé III - arXiv preprint arXiv:1910.13913, 2019 - arxiv.org
Correctly resolving textual mentions of people fundamentally entails making inferences
about those people. Such inferences raise the risk of systemic biases in coreference …
about those people. Such inferences raise the risk of systemic biases in coreference …
Constructing holistic spatio-temporal scene graph for video semantic role labeling
As one of the core video semantic understanding tasks, Video Semantic Role Labeling
(VidSRL) aims to detect the salient events from given videos, by recognizing the predict …
(VidSRL) aims to detect the salient events from given videos, by recognizing the predict …
Visual semantic role labeling for video understanding
We propose a new framework for understanding and representing related salient events in a
video using visual semantic role labeling. We represent videos as a set of related events …
video using visual semantic role labeling. We represent videos as a set of related events …
CDLM: Cross-document language modeling
We introduce a new pretraining approach geared for multi-document language modeling,
incorporating two key ideas into the masked language modeling self-supervised objective …
incorporating two key ideas into the masked language modeling self-supervised objective …
Toward gender-inclusive coreference resolution: An analysis of gender and bias throughout the machine learning lifecycle
YT Cao, H Daumé III - Computational Linguistics, 2021 - aclanthology.org
Correctly resolving textual mentions of people fundamentally entails making inferences
about those people. Such inferences raise the risk of systematic biases in coreference …
about those people. Such inferences raise the risk of systematic biases in coreference …
Hierarchical self-supervised representation learning for movie understanding
Most self-supervised video representation learning approaches focus on action recognition.
In contrast, in this paper we focus on self-supervised video learning for movie understanding …
In contrast, in this paper we focus on self-supervised video learning for movie understanding …