Search Results for author:
Found 18 papers, 3 papers with code
Morfessor-enriched features and multilingual training for canonical morphological segmentation
Our approach is to pre-segment the input data for a neural sequence-to-sequence model with the unsupervised method.
Ranked #1 on
Morpheme Segmentaiton
on UniMorph 4.0
(f1 macro avg (subtask 2) metric)
Helsinki-NLP at SemEval-2022 Task 2: A Feature-Based Approach to Multilingual Idiomaticity Detection
This paper describes the University of Helsinki submission to the SemEval 2022 task on multilingual idiomaticity detection.
Modeling Noise in Paraphrase Detection
Noisy labels in training data present a challenging issue in classification tasks, misleading a model towards incorrect decisions during training.
An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation
In this paper, we investigate the benefits of an explicit alignment to language labels in Transformer-based MNMT models in the zero-shot context, by jointly training one cross attention head with word alignment supervision to stress the focus on the target language label.
Coping with Noisy Training Data Labels in Paraphrase Detection
We present new state-of-the-art benchmarks for paraphrase detection on all six languages in the Opusparcus sentential paraphrase corpus: English, Finnish, French, German, Russian, and Swedish.
A Closer Look at Parameter Contributions When Training Neural Language and Translation Models
We analyze the learning dynamics of neural language and translation models using Loss Change Allocation (LCA), an indicator that enables a fine-grained analysis of parameter updates when optimizing for the loss function.
On Using Distribution-Based Compositionality Assessment to Evaluate Compositional Generalisation in Machine Translation
This is a fully-automated procedure to create natural language compositionality benchmarks, making it simple and inexpensive to apply it further to other datasets and languages.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
Semantic Search as Extractive Paraphrase Span Detection
In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i. e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given document, the same modelling setup as typically used in extractive question answering.
On the differences between BERT and MT encoder spaces and how to address them in translation tasks
Various studies show that pretrained language models such as BERT cannot straightforwardly replace encoders in neural machine translation despite their enormous success in other tasks.
Grammatical Error Generation Based on Translated Fragments
We perform neural machine translation of sentence fragments in order to create large amounts of training data for English grammatical error correction.
A Systematic Study of Inner-Attention-Based Sentence Representations in Multilingual Neural Machine Translation
In particular, we show that larger intermediate layers not only improve translation quality, especially for long sentences, but also push the accuracy of trainable classification tasks.
Paraphrase Generation and Evaluation on Colloquial-Style Sentences
We also conduct human evaluation on five of the six languages and compare the results to the automatic evaluation metrics BLEU and the recently proposed BERTScore.
An Evaluation of Language-Agnostic Inner-Attention-Based Representations in Machine Translation
In this paper, we explore a multilingual translation model with a cross-lingually shared layer that can be used as fixed-size sentence representation in different downstream tasks.
Multilingual NMT with a language-independent attention bridge
In this paper, we propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em attention bridge} that is shared across all languages.
Paraphrase Detection on Noisy Subtitles in Six Languages
We perform automatic paraphrase detection on subtitle data from the Opusparcus corpus comprising six European languages: German, English, Finnish, French, Russian, and Swedish.
Open Subtitles Paraphrase Corpus for Six Languages
The development and test sets consist of sentence pairs that have been checked manually; each set contains approximately 1000 sentence pairs that have been verified to be acceptable paraphrases by two annotators.
