Search Results for author:
Found 16 papers, 12 papers with code
Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization
Parameter-efficient fine-tuning (PEFT) using labeled task data can significantly improve the performance of large language models (LLMs) on the downstream task.
On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss
By conducting extensive experiments on different language pairs, including similar and distant, high and low-resource languages, we find that our method alleviates the copying problem, thus improving the translation performance on low-resource languages.
Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters
To translate speech for automatic dubbing, machine translation needs to be isochronous, i. e. translated speech needs to be aligned with the source in terms of speech durations.
Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation
Despite advances in multilingual neural machine translation (MNMT), we argue that there are still two major challenges in this area: data imbalance and representation degeneration.
Jointly Optimizing Translations and Speech Timing to Improve Isochrony in Automatic Dubbing
Automatic dubbing (AD) is the task of translating the original speech in a video into target language speech.
AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models
We also explore weight averaging of adapters trained on the same domain with different hyper-parameters, and show that it preserves the performance of a PLM on new domains while obtaining strong in-domain results.
$m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter
We consider a very challenging scenario: adapting the MNMT model both to a new domain and to a new language pair at the same time.
Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation
Training a new adapter on each language pair or training a single adapter on all language pairs without updating the pretrained model has been proposed as a parameter-efficient alternative.
Efficient Hierarchical Domain Adaptation for Pretrained Language Models
The remarkable success of large language models has been driven by dense models trained on massive unlabeled, unstructured corpora.
Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation
Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the lexical- and high-level representations of the two languages.
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.
Domain Adversarial Fine-Tuning as an Effective Regularizer
To address this issue, we introduce a new regularization technique, AFTER; domain Adversarial Fine-Tuning as an Effective Regularizer.
Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT
Using a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results.
An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models
A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora.
NTUA-SLP at IEST 2018: Ensemble of Neural Transfer Methods for Implicit Emotion Classification
In this paper we present our approach to tackle the Implicit Emotion Shared Task (IEST) organized as part of WASSA 2018 at EMNLP 2018.
NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning
In this paper we present deep-learning models that submitted to the SemEval-2018 Task~1 competition: "Affect in Tweets".
