1 code implementation • 30 Sep 2018 • Saeed Najafi, Colin Cherry, Grzegorz Kondrak
We set out to establish RNNs as an attractive alternative to CRFs for sequence labeling.
1 code implementation • 24 Jun 2023 • Michael Ogezi, Bradley Hauer, Talgat Omarov, Ning Shi, Grzegorz Kondrak
We present a novel algorithm that leverages glosses retrieved from BabelNet, in combination with text and image encoders.
1 code implementation • EMNLP 2017 • Adam St Arnaud, David Beck, Grzegorz Kondrak
We present a system for identifying cognate sets across dictionaries of related languages.
no code implementations • 3 May 2014 • Aibek Makazhanov, Denilson Barbosa, Grzegorz Kondrak
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).
no code implementations • 21 Aug 2018 • Bradley Hauer, Yixing Luan, Grzegorz Kondrak
Identification of the most frequent sense of a polysemous word is an important semantic task.
no code implementations • WS 2018 • Garrett Nicolai, Saeed Najafi, Grzegorz Kondrak
Many character-level tasks can be framed as sequence-to-sequence transduction, where the target is a word from a natural language.
no code implementations • TACL 2016 • Bradley Hauer, Grzegorz Kondrak
Algorithmic decipherment is a prime example of a truly unsupervised problem.
no code implementations • EACL 2017 • Garrett Nicolai, Grzegorz Kondrak
The task of morphological analysis is to produce a complete list of lemma+tag analyses for a given word-form.
no code implementations • EACL 2017 • Bradley Hauer, Garrett Nicolai, Grzegorz Kondrak
The task of unsupervised lexicon induction is to find translation pairs across monolingual corpora.
no code implementations • WS 2018 • Saeed Najafi, Bradley Hauer, Rashed Rubby Riyadh, Leyuan Yu, Grzegorz Kondrak
We report the results of our experiments in the context of the NEWS 2018 Shared Task on Transliteration.
no code implementations • 17 Apr 2019 • Bradley Hauer, Grzegorz Kondrak
The study of homonymy is vital to resolving fundamental problems in lexical semantics.
no code implementations • WS 2019 • Rashed Rubby Riyadh, Grzegorz Kondrak
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.
no code implementations • WS 2019 • Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Rashed Rubby Riyadh, Grzegorz Kondrak
We propose cognate projection as a method of crosslingual transfer for inflection generation in the context of the SIGMORPHON 2019 Shared Task.
no code implementations • 28 Apr 2020 • Bradley Hauer, Grzegorz Kondrak
Synonymy and translational equivalence are the relations of sameness of meaning within and across languages.
no code implementations • WS 2020 • Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Arnob Mallik, Grzegorz Kondrak
This paper presents the University of Alberta systems and results in the SIGMORPHON 2020 Task 1: Multilingual Grapheme-to-Phoneme Conversion.
no code implementations • EMNLP 2020 • Yixing Luan, Bradley Hauer, Lili Mou, Grzegorz Kondrak
It has been conjectured that multilingual information can help monolingual word sense disambiguation (WSD).
no code implementations • RANLP 2021 • Bradley Hauer, Grzegorz Kondrak, Yixing Luan, Arnob Mallik, Lili Mou
Our two unsupervised methods refine sense annotations produced by a knowledge-based WSD system via lexical translations in a parallel corpus.
no code implementations • 10 Jun 2021 • Bradley Hauer, Grzegorz Kondrak
Translations have been used in WSD as a source of knowledge, and even as a means of delimiting word senses.
no code implementations • SEMEVAL 2020 • Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Arnob Mallik, Grzegorz Kondrak
We investigate the hypothesis that translations can be used to identify cross-lingual lexical entailment.
no code implementations • NAACL 2022 • Bradley Hauer, Grzegorz Kondrak
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.
no code implementations • SEMEVAL 2021 • Bradley Hauer, Hongchang Bao, Arnob Mallik, Grzegorz Kondrak
We describe the University of Alberta systems for the SemEval-2021 Word-in-Context (WiC) disambiguation task.
no code implementations • EACL (GWC) 2021 • Hongchang Bao, Bradley Hauer, Grzegorz Kondrak
Colexification occurs when two distinct concepts are lexified by the same word.
no code implementations • EACL (GWC) 2021 • Amir Ahmad Habibi, Bradley Hauer, Grzegorz Kondrak
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.
no code implementations • LChange (ACL) 2022 • Daniela Teodorescu, Spencer von der Ohe, Grzegorz Kondrak
We describe our two systems for the shared task on Lexical Semantic Change Discovery in Spanish.
no code implementations • SemEval (NAACL) 2022 • Bradley Hauer, Seeratpal Jaura, Talgat Omarov, Grzegorz Kondrak
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.
no code implementations • LREC 2022 • Hongchang Bao, Bradley Hauer, Grzegorz Kondrak
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.
no code implementations • SMP (ICON) 2021 • Bradley Hauer, Colin Choi, Abram Hindle, Scott Smallwood, Grzegorz Kondrak
The Dorabella cipher is an encrypted note of English composer Edward Elgar, which has defied decipherment attempts for more than a century.
no code implementations • 24 May 2023 • Xiang Zhang, Senyu Li, Bradley Hauer, Ning Shi, Grzegorz Kondrak
In this work, we propose a systematic way of qualifying the performance disparities of LLMs under multilingual settings.
no code implementations • 5 Jun 2023 • Michael Ogezi, Bradley Hauer, Grzegorz Kondrak
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.