Search Results for author:
Found 19 papers, 5 papers with code
Towards Realistic Few-Shot Relation Extraction
In recent years, few-shot models have been applied successfully to a variety of NLP tasks.
Updated Headline Generation: Creating Updated Summaries for Evolving News Stories
We propose the task of updated headline generation, in which a system generates a headline for an updated article, considering both the previous article and headline.
Towards Fast Inference: Exploring and Improving Blockwise Parallel Drafts
Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation.
Weakly Supervised Headline Dependency Parsing
English news headlines form a register with unique syntactic properties that have been documented in linguistics literature since the 1930s.
What Makes Data-to-Text Generation Hard for Pretrained Language Models?
Previous work shows that pre-trained language models(PLMs) perform remarkably well on this task after fine-tuning on a significant amount of task-specific training data.
Cross-Register Projection for Headline Part of Speech Tagging
However, the register of English news headlines, "headlinese", is very different from the register of long-form text, causing POS tagging models to underperform on headlines.
Comparing Euclidean and Hyperbolic Embeddings on the WordNet Nouns Hypernymy Graph
Nickel and Kiela (2017) present a new method for embedding tree nodes in the Poincare ball, and suggest that these hyperbolic embeddings are far more effective than Euclidean embeddings at embedding nodes in large, hierarchically structured graphs like the WordNet nouns hypernymy tree.
Diversity-Aware Batch Active Learning for Dependency Parsing
While the predictive performance of modern statistical dependency parsers relies heavily on the availability of expensive expert-annotated treebank data, not all annotations contribute equally to the training of the parsers.
Corrected CBOW Performs as well as Skip-gram
Mikolov et al. (2013a) observed that continuous bag-of-words (CBOW) word embeddings tend to underperform Skip-gram (SG) embeddings, and this finding has been reported in subsequent works.
Roll Call Vote Prediction with Knowledge Augmented Models
The sources of knowledge we use are news text and Freebase, a manually curated knowledge base.
Learning Representations of Social Media Users
In this thesis, we begin by showing how user representations can be learned from multiple types of user behavior on social media.
Using Author Embeddings to Improve Tweet Stance Classification
Many social media classification tasks analyze the content of a message, but do not consider the context of the message.
Deep Dirichlet Multinomial Regression
We present deep Dirichlet Multinomial Regression (dDMR), a generative topic model that simultaneously learns document feature representations and topics.
Multi-Task Learning for Mental Health using Social Media Text
We introduce initial groundwork for estimating suicide risk and mental health in a deep learning framework.
Ethical Research Protocols for Social Media Health Research
Social media have transformed data-driven research in political science, the social sciences, health, and medicine.
Deep Generalized Canonical Correlation Analysis
We present Deep Generalized Canonical Correlation Analysis (DGCCA) -- a method for learning nonlinear transformations of arbitrarily many views of data, such that the resulting transformations are maximally informative of each other.
