Search Results for author:
Found 29 papers, 7 papers with code
Deciphering and Characterizing Out-of-Vocabulary Words for Morphologically Rich Languages
This paper presents a detailed foundational empirical case study of the nature of out-of-vocabulary words encountered in modern text in a moderate-resource language such as Bulgarian, and a multi-faceted distributional analysis of the underlying word-formation processes that can aid in their compositional translation, tagging, parsing, language modeling, and other NLP tasks.
On Pronunciations in Wiktionary: Extraction and Experiments on Multilingual Syllabification and Stress Prediction
We constructed parsers for five non-English editions of Wiktionary, which combined with pronunciations from the English edition, comprises over 5. 3 million IPA pronunciations, the largest pronunciation lexicon of its kind.
On the Robustness of Cognate Generation Models
We evaluate two popular neural cognate generation models’ robustness to several types of human-plausible noise (deletion, duplication, swapping, and keyboard errors, as well as a new type of error, phonological errors).
Known Words Will Do: Unknown Concept Translation via Lexical Relations
Translating into low-resource languages is challenging due to the scarcity of training data.
MOKA: Moral Knowledge Augmentation for Moral Event Extraction
News media employ moral language to create memorable stories, and readers often engage with the content that align with their values.
Crossing the Aisle: Unveiling Partisan and Counter-Partisan Events in News Reporting
We benchmark PAC to highlight the challenges of this task.
You Are What You Annotate: Towards Better Models through Annotator Representations
Annotator disagreement is ubiquitous in natural language processing (NLP) tasks.
EASE: An Easily-Customized Annotation System Powered by Efficiency Enhancement Mechanisms
Our results show that our system can meet the diverse needs of NLP researchers and significantly accelerate the annotation process.
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models
Not surprisingly, this has, in turn, made many NLP researchers -- especially those at the beginning of their careers -- worry about what NLP research area they should focus on.
Institutional ownership and liquidity commonality: evidence from Australia
We find that commonality in liquidity is higher for large stocks compared to small stocks in the cross-section of stocks, and the spread between the two has increased over the past two decades.
Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysis
In this work, we introduce the task of multimodal ideology prediction, where a model predicts binary or five-point scale ideological leanings, given a text-image pair with political content.
Evaluating Neural Model Robustness for Machine Comprehension
We evaluate neural model robustness to adversarial attacks using different types of linguistic unit perturbations {--} character and word, and propose a new method for strategic sentence-level perturbations.
Neural Transduction for Multilingual Lexical Translation
We present a method for completing multilingual translation dictionaries.
Wiktionary Normalization of Translations and Morphological Information
We extend the Yawipa Wiktionary Parser (Wu and Yarowsky, 2020) to extract and normalize translations from etymology glosses, and morphological form-of relations, resulting in 300K unique translations and over 4 million instances of 168 annotated morphological relations.
The JHU Submission to the 2020 Duolingo Shared Task on Simultaneous Translation and Paraphrase for Language Education
This paper presents the Johns Hopkins University submission to the 2020 Duolingo Shared Task on Simultaneous Translation and Paraphrase for Language Education (STAPLE).
Computational Etymology and Word Emergence
We developed an extensible, comprehensive Wiktionary parser that improves over several existing parsers.
Evaluating Neural Machine Comprehension Model Robustness to Noisy Inputs and Adversarial Attacks
We evaluate machine comprehension models' robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level.
JHUBC's Submission to LT4HALA EvaLatin 2020
We describe the JHUBC submission to the EvaLatin Shared task on lemmatization and part-of-speech tagging for Latin.
The Johns Hopkins University Bible Corpus: 1600+ Tongues for Typological Exploration
The corpus consists of over 4000 unique translations of the Christian Bible and counting.
Multilingual Dictionary Based Construction of Core Vocabulary
We propose a new functional definition and construction method for core vocabulary sets for multiple applications based on the relative coverage of a target concept in thousands of bilingual dictionaries.
Fine-grained Morphosyntactic Analysis and Generation Tools for More Than One Thousand Languages
Exploiting the broad translation of the Bible into the world{'}s languages, we train and distribute morphosyntactic tools for approximately one thousand languages, vastly outstripping previous distributions of tools devoted to the processing of inflectional morphology.
An Analysis of Massively Multilingual Neural Machine Translation for Low-Resource Languages
We find that best practices in this domain are highly language-specific: adding more languages to a training set is often better, but too many harms performance{---}the best number depends on the source language.
Modeling Color Terminology Across Thousands of Languages
There is an extensive history of scholarship into what constitutes a "basic" color term, as well as a broadly attested acquisition sequence of basic color terms across many languages, as articulated in the seminal work of Berlin and Kay (1969).
