Search Results for author:
Found 22 papers, 13 papers with code
Learning Universal Authorship Representations
Determining whether two documents were composed by the same author, also known as authorship verification, has traditionally been tackled using statistical methods.
AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies
Our benchmarking approach focuses on aspects of this ability that are common among humans: (i) recalling related experiences from a large amount of information, and (ii) applying analogical reasoning to complex and lengthy scenarios.
Few-Shot Detection of Machine-Generated Text using Style Representations
Furthermore, given a handful of examples composed by each of several specific language models of interest, our approach affords the ability to predict which model generated a given document.
Learning to Generate Text in Arbitrary Writing Styles
However, in applications such as writing assistants, it is desirable for language models to produce text in an author-specific style on the basis of a potentially small writing sample.
Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?
Authorship verification is the task of determining if two distinct writing samples share the same author and is typically concerned with the attribution of written text.
Can Authorship Representation Learning Capture Stylistic Features?
Automatically disentangling an author's style from the content of their writing is a longstanding and possibly insurmountable problem in computational linguistics.
Low-Resource Authorship Style Transfer: Can Non-Famous Authors Be Imitated?
Existing unsupervised approaches like STRAP have largely focused on style transfer to target authors with many examples of their writing style in books, speeches, or other published works.
Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?
Learning these models often requires specialized training algorithms that address task-conflict in the shared parameter updates, which otherwise can lead to negative transfer.
A Deep Metric Learning Approach to Account Linking
We consider the task of linking social media accounts that belong to the same author in an automated fashion on the basis of the content and metadata of their corresponding document streams.
Ensemble Distillation for Structured Prediction: Calibrated, Accurate, Fast-Choose Three
However, extending these methods to structured prediction is not always straightforward or effective; furthermore, a held-out calibration set may not always be available.
Sources of Transfer in Multilingual Named Entity Recognition
However, a straightforward implementation of this simple idea does not always work in practice: naive training of NER models using annotated data drawn from multiple languages consistently underperforms models trained on monolingual data alone, despite having access to more training data.
Multilingual Named Entity Recognition
named-entity-recognition
+2
Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning
Low levels of pruning (30-40%) do not affect pre-training loss or transfer to downstream tasks at all.
Learning Invariant Representations of Social Media Users
The evolution of social media users' behavior over time complicates user-level comparison tasks such as verification, classification, clustering, and ranking.
Convolutions Are All You Need (For Classifying Character Sequences)
While recurrent neural networks (RNNs) are widely used for text classification, they demonstrate poor performance and slow convergence when trained on long sequences.
Predicting Twitter User Demographics from Names Alone
Social media analysis frequently requires tools that can automatically infer demographics to contextualize trends.
Bayesian Modeling of Lexical Resources for Low-Resource Settings
Practically, this means that we may treat the lexical resources as observations under the proposed generative model.
Low Resource Named Entity Recognition
named-entity-recognition
+2
