Eduard Hovy

Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models

2017

Variations in writing styles are commonly used to adapt the content to a specific context, audience, or purpose. However, applying stylistic variations is still largely a manual process, and there have been little efforts towards …

An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation

2019 · arXiv (Cornell University)

In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via …

Visualizing and Understanding Neural Models in NLP

2016

While neural networks have been successfully applied to many NLP tasks the resulting vectorbased models are very difficult to interpret. For example it's not clear how they achieve compositionality, building sentence meaning from the meanings …

(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas

2019 · arXiv (Cornell University)

Stylistic variation in text needs to be studied with different aspects including the writer's personal traits, interpersonal relations, rhetoric, and more. Despite recent attempts on computational modeling of the variation, the lack of parallel corpora …

EIGEN: Event Influence GENeration using Pre-trained Language Models

2020 · arXiv (Cornell University)

Reasoning about events and tracking their influences is fundamental to understanding processes. In this paper, we present EIGEN - a method to leverage pre-trained language models to generate event influences conditioned on a context, nature …

NL-Augmenter 🦎 → 🐍 A Framework for Task-Sensitive Natural Language Augmentation

2023 · Northern European Journal of Language Technology

Data augmentation is an important method for evaluating the robustness of and enhancing the diversity of training data for natural language processing (NLP) models. In this paper, we present NL-Augmenter, a new participatory Python-based natural …

Retrofitting Word Vectors to Semantic Lexicons

2015

Manaal Faruqui, Jesse Dodge, Sujay Kumar Jauhar, Chris Dyer, Eduard Hovy, Noah A. Smith. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

Visualizing and Understanding Neural Models in NLP

2015 · arXiv (Cornell University)

While neural networks have been successfully applied to many NLP tasks the resulting vector-based models are very difficult to interpret. For example it's not clear how they achieve {\em compositionality}, building sentence meaning from the …

Harnessing Deep Neural Networks with Logic Rules

2016 · arXiv (Cornell University)

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs …

RACE: Large-scale ReAding Comprehension Dataset From Examinations

2017 · arXiv (Cornell University)

We present RACE, a new dataset for benchmark evaluation of methods in the reading comprehension task. Collected from the English exams for middle and high school Chinese students in the age range between 12 to …

An Interpretable Knowledge Transfer Model for Knowledge Base Completion

2017 · arXiv (Cornell University)

Knowledge bases are important resources for a variety of natural language processing tasks but suffer from incompleteness. We propose a novel embedding model, \emph{ITransF}, to perform knowledge base completion. Equipped with a sparse attention mechanism, …

Exploring Numeracy in Word Embeddings

2019

Word embeddings are now pervasive across NLP subfields as the de-facto method of forming text representataions. In this work, we show that existing embedding models are inadequate at constructing representations that capture salient aspects of …

On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing

2019

Wasi Ahmad, Zhisong Zhang, Xuezhe Ma, Eduard Hovy, Kai-Wei Chang, Nanyun Peng. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and …

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

2016

State-of-the-art sequence labeling systems traditionally require large amounts of taskspecific knowledge in the form of handcrafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word-and …

AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples

2018

We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large lexical resources in …

A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications

2018

Dongyeop Kang, Waleed Ammar, Bhavana Dalvi, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard Hovy, Roy Schwartz. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume …

Learning The Difference That Makes A Difference With Counterfactually-Augmented Data

2020 · International Conference on Learning Representations

Despite alarm over the reliance of machine learning systems on so-called spurious patterns in training data, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are …

Measuring and Improving Consistency in Pretrained Language Models

2021 · Transactions of the Association for Computational Linguistics

Abstract Consistency of a model—that is, the invariance of its behavior under meaning-preserving alternations in its input—is a highly desirable property in natural language processing. In this paper we study the question: Are Pretrained Language …