Search Results for author:
Found 52 papers, 3 papers with code
Extracting Family Relationship Networks from Novels
We present an approach to the extraction of family relations from literary narrative, which incorporates a technique for utterance attribution proposed recently by Elson and McKeown (2010).
Decoding Anagrammed Texts Written in an Unknown Language and Script
Algorithmic decipherment is a prime example of a truly unsupervised problem.
Morphological Analysis without Expert Annotation
The task of morphological analysis is to produce a complete list of lemma+tag analyses for a given word-form.
Bootstrapping Unsupervised Bilingual Lexicon Induction
The task of unsupervised lexicon induction is to find translation pairs across monolingual corpora.
Identifying Cognate Sets Across Dictionaries of Related Languages
We present a system for identifying cognate sets across dictionaries of related languages.
Comparison of Assorted Models for Transliteration
We report the results of our experiments in the context of the NEWS 2018 Shared Task on Transliteration.
You Shall Know the Most Frequent Sense by the Company it Keeps
Identification of the most frequent sense of a polysemous word is an important semantic task.
String Transduction with Target Language Models and Insertion Handling
Many character-level tasks can be framed as sequence-to-sequence transduction, where the target is a word from a natural language.
Efficient Sequence Labeling with Actor-Critic Training
We set out to establish RNNs as an attractive alternative to CRFs for sequence labeling.
One Homonym per Translation
The study of homonymy is vital to resolving fundamental problems in lexical semantics.
Joint Approach to Deromanization of Code-mixed Texts
The conversion of romanized texts back to the native scripts is a challenging task because of the inconsistent romanization conventions and non-standard language use.
Cognate Projection for Low-Resource Inflection Generation
We propose cognate projection as a method of crosslingual transfer for inflection generation in the context of the SIGMORPHON 2019 Shared Task.
Synonymy = Translational Equivalence
Synonymy and translational equivalence are the relations of sameness of meaning within and across languages.
Low-Resource G2P and P2G Conversion with Synthetic Training Data
This paper presents the University of Alberta systems and results in the SIGMORPHON 2020 Task 1: Multilingual Grapheme-to-Phoneme Conversion.
UAlberta at SemEval-2020 Task 2: Using Translations to Predict Cross-Lingual Entailment
We investigate the hypothesis that translations can be used to identify cross-lingual lexical entailment.
One Sense per Translation
Translations have been used in WSD as a source of knowledge, and even as a means of delimiting word senses.
Semi-Supervised and Unsupervised Sense Annotation via Translations
Our two unsupervised methods refine sense annotations produced by a knowledge-based WSD system via lexical translations in a parallel corpus.
WiC = TSV = WSD: On the Equivalence of Three Semantic Tasks
The Word-in-Context (WiC) task has attracted considerable attention in the NLP community, as demonstrated by the popularity of the recent MCL-WiC SemEval shared task.
UAlberta at SemEval-2021 Task 2: Determining Sense Synonymy via Translations
We describe the University of Alberta systems for the SemEval-2021 Word-in-Context (WiC) disambiguation task.
UAlberta at SemEval 2022 Task 2: Leveraging Glosses and Translations for Multilingual Idiomaticity Detection
Further hypothesizing that literal and idiomatic expressions translate differently, our second method translates an expression in context, and uses a lexical knowledge base to determine if the translation is literal.
Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs
In this work, we propose a systematic way of qualifying the performance disparities of LLMs under multilingual settings.
Semantically-Prompted Language Models Improve Visual Descriptions
With both ideas, we demonstrate that V-GLOSS improves visual descriptions and achieves strong results in the zero-shot setting on general and fine-grained image-classification datasets, including ImageNet, STL-10, FGVC Aircraft, and Flowers 102.
UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation
We present a novel algorithm that leverages glosses retrieved from BabelNet, in combination with text and image encoders.
black[LSCDiscovery shared task] UAlberta at LSCDiscovery: Lexical Semantic Change Detection via Word Sense Disambiguation
We describe our two systems for the shared task on Lexical Semantic Change Discovery in Spanish.
Dorabella Cipher as Musical Inspiration
The Dorabella cipher is an encrypted note of English composer Edward Elgar, which has defied decipherment attempts for more than a century.
Lexical Resource Mapping via Translations
Aligning lexical resources that associate words with concepts in multiple languages increases the total amount of semantic information that can be leveraged for various NLP tasks.
On Universal Colexifications
Colexification occurs when two distinct concepts are lexified by the same word.
Improving Word Sense Disambiguation with Translations
It has been conjectured that multilingual information can help monolingual word sense disambiguation (WSD).
Homonymy and Polysemy Detection with Multilingual Information
Deciding whether a semantically ambiguous word is homonymous or polysemous is equivalent to establishing whether it has any pair of senses that are semantically unrelated.
