Bridging Anaphora Resolution as Question Answering [PDF]
Most previous studies on bridging anaphora resolution (Poesio et al., 2004; Hou et al., 2013b; Hou, 2018a) use the pairwise model to tackle the problem and assume that the gold mention information is given.
Yufang Hou
semanticscholar +4 more sources
Cortical γ-oscillations implement basic language operations: Evidence from electroencephalography in anaphora during english filler-gap dependency processing. [PDF]
Hypotheses about top-down structure building propose that gamma (>30Hz) oscillations support the creation of syntax-semantics objects, contrasting with slow-rhythm entrainment of gamma oscillations tracking semantic fitness in bottom-up chunking.
Laurent Dekydtspotter +6 more
doaj +2 more sources
Zero‐anaphora resolution in Korean based on deep language representation model: BERT
It is necessary to achieve high performance in the task of zero anaphora resolution (ZAR) for completely understanding the texts in Korean, Japanese, Chinese, and various other languages.
Youngtae Kim, Dongyul Ra, Soojong Lim
doaj +2 more sources
Coreference annotation and resolution in the Colorado Richly Annotated Full Text (CRAFT) corpus of biomedical journal articles [PDF]
Background Coreference resolution is the task of finding strings in text that have the same referent as other strings. Failures of coreference resolution are a common cause of false negatives in information extraction from the scientific literature.
K. Bretonnel Cohen +8 more
doaj +2 more sources
Few-Shot Anaphora Resolution in Scientific Protocols via Mixtures of In-Context Experts [PDF]
Anaphora resolution is an important task for information extraction across a range of languages, text genres, and domains, motivating the need for methods that do not require large annotated datasets.
N. Le, Fan Bai, Alan Ritter
semanticscholar +1 more source
Analyzing Depression in College Students Using NLP and Transformer Models: Implications for Career and Educational Counseling. [PDF]
A multimodal NLP pipeline uses RoBERTa embeddings with a GRU classifier to detect depression in college students from short posts and interaction signals. The system integrates textual and emoji features and outputs risk levels for early screening and support.
Wan Q, Pan Y, Zakeri S.
europepmc +2 more sources
Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution [PDF]
Masked language models (MLMs) have contributed to drastic performance improvements with regard to zero anaphora resolution (ZAR). To further improve this approach, in this study, we made two proposals. The first is a new pretraining task that trains MLMs
Ryuto Konno +4 more
semanticscholar +1 more source
Stay Together: A System for Single and Split-antecedent Anaphora Resolution [PDF]
The state-of-the-art on basic, single-antecedent anaphora has greatly improved in recent years. Researchers have therefore started to pay more attention to more complex cases of anaphora such as split-antecedent anaphora, as in “Time-Warner is ...
Juntao Yu +3 more
semanticscholar +1 more source
An architecture for anaphora resolution [PDF]
In this paper, we describe the pronominal anaphora resolution module of Lucy, a portable English understanding system. The design of this module was motivated by the observation that, although there exist many theories of anaphora resolution, no one of these theories is complete.
Elaine Rich, Susann LuperFoy
openaire +1 more source
Anaphora resolution without world knowledge [PDF]
A typical problem in the resolution of pronominal anaphora is the presence of more than one candidate for the antecedent of the pronoun. Considering two English sentences like (1) "People buy expensive cars because they offer more status" and (2) "People
Vilson J. Leffa
doaj +1 more source

