Search Results for author:
Found 29 papers, 4 papers with code
The LMU Munich System for the WMT20 Very Low Resource Supervised MT Task
We present our systems for the WMT20 Very Low Resource MT Task for translation between German and Upper Sorbian.
Don’t Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings
The two approaches we find most effective are: 1) using identical words as seed lexicons (which unsupervised approaches incorrectly assume are not available for orthographically distinct language pairs) and 2) combining such lexicons with pairs extracted by matching romanized versions of words with an edit distance threshold.
Cross-Lingual Transfer Learning for Hate Speech Detection
Rather than collecting and annotating new hate speech data, we show how to use cross-lingual transfer learning to leverage already existing data from higher-resource languages.
Adapting Entities across Languages and Cultures
He is associated with founding a company in the United States, so perhaps the German founder Carl Benz could stand in for Gates in those contexts.
Improving Machine Translation of Rare and Unseen Word Senses
The performance of NMT systems has improved drastically in the past few years but the translation of multi-sense words still poses a challenge.
Unsupervised Parallel Sentence Extraction from Comparable Corpora
We show that our approach is effective, on three language-pairs, without the use of any bilingual signal which is important because parallel sentence mining is most useful in low resource scenarios.
Do not neglect related languages: The case of low-resource Occitan cross-lingual word embeddings
In contrast to previous approaches which leverage independently pre-trained embeddings of languages, we (i) train CLWEs for the low-resource and a related language jointly and (ii) map them to the target language to build the final multilingual space.
Bilingual Lexicon Induction
Cross-Lingual Word Embeddings
+1
Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages
In this paper, we propose to build multilingual word embeddings (MWEs) via a novel language chain-based approach, that incorporates intermediate related languages to bridge the gap between the distant source and target.
Extending Multilingual Machine Translation through Imitation Learning
Despite the growing variety of languages supported by existing multilingual neural machine translation (MNMT) models, most of the world's languages are still being left behind.
How to Solve Few-Shot Abusive Content Detection Using the Data We Actually Have
Our analysis also shows that our models acquire a general understanding of abusive language, since they improve the prediction of labels which are present only in the target dataset.
Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings
The two approaches we find most effective are: 1) using identical words as seed lexicons (which unsupervised approaches incorrectly assume are not available for orthographically distinct language pairs) and 2) combining such lexicons with pairs extracted by matching romanized versions of words with an edit distance threshold.
Addressing the Challenges of Cross-Lingual Hate Speech Detection
The goal of hate speech detection is to filter negative online content aiming at certain groups of people.
Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction
In this paper, we enrich BWE-based BDI with transliteration information by using Bilingual Orthography Embeddings (BOEs).
The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task
Our core unsupervised neural machine translation (UNMT) system follows the strategy of Chronopoulou et al. (2020), using a monolingual pretrained language generation model (on German) and fine-tuning it on both German and Upper Sorbian, before initializing a UNMT model, which is trained with online backtranslation.
Anchor-based Bilingual Word Embeddings for Low-Resource Languages
For low resource languages training MWEs monolingually results in MWEs of poor quality, and thus poor bilingual word embeddings (BWEs) as well.
Exploring Bilingual Word Embeddings for Hiligaynon, a Low-Resource Language
We use a publicly available Hiligaynon corpus with only 300K words, and match it with a comparable corpus in English.
LMU Bilingual Dictionary Induction System with Word Surface Similarity Scores for BUCC 2020
We participate in both the open and closed tracks of the shared task and we show improved results of our method compared to simple vector similarity based approaches.
The LMU Munich Unsupervised Machine Translation System for WMT19
We describe LMU Munich{'}s machine translation system for German→Czech translation which was used to participate in the WMT19 shared task on unsupervised news translation.
Better OOV Translation with Bilingual Terminology Mining
In our experiments we use a system trained on Europarl and mine sentences containing medical terms from monolingual data.
Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation
Mining parallel sentences from comparable corpora is important.
The LMU Munich Unsupervised Machine Translation Systems
We describe LMU Munich{'}s unsupervised machine translation systems for English↔German translation.
An Unsupervised System for Parallel Corpus Filtering
In this paper we describe LMU Munich{'}s submission for the \textit{WMT 2018 Parallel Corpus Filtering} shared task which addresses the problem of cleaning noisy parallel corpora.
LMU Munich's Neural Machine Translation Systems at WMT 2018
The systems were used for our participation in the WMT18 biomedical translation task and in the shared task on machine translation of news.
Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable
Bilingual tasks, such as bilingual lexicon induction and cross-lingual classification, are crucial for overcoming data sparsity in the target language.
Evaluating bilingual word embeddings on the long tail
Bilingual word embeddings are useful for bilingual lexicon induction, the task of mining translations of given words.
A Hungarian Sentiment Corpus Manually Annotated at Aspect Level
In this paper, on the one hand, we present the method of annotation, and we discuss the difficulties concerning text annotation process.
