268 citations · 662 across the 69 of their papers we have counts for
92 papers · 1 filter
Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems
Songbo Hu, Han Zhou, Mete Hergul +5
Creating high-quality annotated data for task-oriented dialog (ToD) is known to be notoriously difficult, and the challenges are amplified when the goal is to create equitable, cul…
Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data
Guangzhi Sun, Chao Zhang, Ivan Vulić +2
Manually annotating fine-grained slot-value labels for task-oriented dialogue (ToD) systems is an expensive and time-consuming endeavour. This motivates research into slot-filling…
Cross-Lingual Transfer with Target Language-Ready Task Adapters
Marinela Parović, Alan Ansell, Ivan Vulić +1
Adapters have emerged as a modular and parameter-efficient approach to (zero-shot) cross-lingual transfer. The established MAD-X framework employs separate language and task adapte…
Distilling Efficient Language-Specific Models for Cross-Lingual Transfer
Alan Ansell, Edoardo Maria Ponti, Anna Korhonen +1
Massively multilingual Transformers (MMTs), such as mBERT and XLM-R, are widely used for cross-lingual transfer learning. While these are pretrained to represent hundreds of langua…
Translation-Enhanced Multilingual Text-to-Image Generation
Yaoyiran Li, Ching-Yun Chang, Stephen Rawls +2
Research on text-to-image generation (TTI) still predominantly focuses on the English language due to the lack of annotated image-caption data in other languages; in the long run,…
Where's the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence Segmentation
Benjamin Minixhofer, Jonas Pfeiffer, Ivan Vulić
Many NLP pipelines split text into sentences as one of the crucial preprocessing steps. Prior sentence segmentation tools either rely on punctuation or require a considerable amoun…
Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging
Fabian David Schmidt, Ivan Vulić, Goran Glavaš
Massively multilingual language models have displayed strong performance in zero-shot (ZS-XLT) and few-shot (FS-XLT) cross-lingual transfer setups, where models fine-tuned on task…
CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models
Benjamin Minixhofer, Jonas Pfeiffer, Ivan Vulić
While many languages possess processes of joining two or more words to create compound words, previous studies have been typically limited only to languages with excessively produc…
Transfer-Free Data-Efficient Multilingual Slot Labeling
Evgeniia Razumovskaia, Ivan Vulić, Anna Korhonen
Slot labeling (SL) is a core component of task-oriented dialogue (ToD) systems, where slots and corresponding values are usually language-, task- and domain-specific. Therefore, ex…
Romanization-based Large-scale Adaptation of Multilingual Language Models
Sukannya Purkayastha, Sebastian Ruder, Jonas Pfeiffer +2
Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for cross-lingual transfer in NLP. However, their large-scale deployment to many lan…
Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese
Vésteinn Snæbjarnarson, Annika Simonsen, Goran Glavaš +1
Multilingual language models have pushed state-of-the-art in cross-lingual NLP transfer. The majority of zero-shot cross-lingual transfer, however, use one and the same massively m…
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
Han Zhou, Xingchen Wan, Ivan Vulić +1
Large pretrained language models are widely used in downstream NLP tasks via task-specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine-Tuning…
FUN with Fisher: Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezing
Chen Cecilia Liu, Jonas Pfeiffer, Ivan Vulić +1
Standard fine-tuning of language models typically performs well on in-distribution data, but suffers with generalization to distribution shifts. In this work, we aim to improve the…
Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems
Songbo Hu, Ivan Vulić, Fangyu Liu +1
End-to-end (E2E) task-oriented dialogue (ToD) systems are prone to fall into the so-called "likelihood trap", resulting in generated responses which are dull, repetitive, and often…
MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue
Nikita Moghe, Evgeniia Razumovskaia, Liane Guillou +3
Task-oriented dialogue (TOD) systems have been widely deployed in many industries as they deliver more efficient customer support. These systems are typically constructed for a sin…
Improving Bilingual Lexicon Induction with Cross-Encoder Reranking
Yaoyiran Li, Fangyu Liu, Ivan Vulić +1
Bilingual lexicon induction (BLI) with limited bilingual supervision is a crucial yet challenging task in multilingual NLP. Current state-of-the-art BLI methods rely on the inducti…
Can Pretrained Language Models (Yet) Reason Deductively?
Zhangdie Yuan, Songbo Hu, Ivan Vulić +2
Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted increasing attention, showing promising performance in many knowledge-intensive tasks. Their good p…
Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold
Sebastian Ruder, Ivan Vulić, Anders Søgaard
The prototypical NLP experiment trains a standard architecture on labeled English data and optimizes for accuracy, without accounting for other dimensions such as fairness, interpr…
Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog
Chia-Chien Hung, Anne Lauscher, Ivan Vulić +2
Research on (multi-domain) task-oriented dialog (TOD) has predominantly focused on the English language, primarily due to the shortage of robust TOD datasets in other languages, pr…
NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue
Iñigo Casanueva, Ivan Vulić, Georgios P. Spithourakis +1
We present NLU++, a novel dataset for natural language understanding (NLU) in task-oriented dialogue (ToD) systems, with the aim to provide a much more challenging evaluation envir…
Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders
Ivan Vulić, Goran Glavaš, Fangyu Liu +3
Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model dis…
EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification
Georgios P. Spithourakis, Ivan Vulić, Michał Lis +2
Knowledge-based authentication is crucial for task-oriented spoken dialogue systems that offer personalised and privacy-focused services. Such systems should be able to enrol (E),…
Improved and Efficient Conversational Slot Labeling through Question Answering
Gabor Fuisz, Ivan Vulić, Samuel Gibbons +2
Transformer-based pretrained language models (PLMs) offer unmatched performance across the majority of natural language understanding (NLU) tasks, including a body of question answ…
Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval
Robert Litschko, Ivan Vulić, Goran Glavaš
State-of-the-art neural (re)rankers are notoriously data-hungry which -- given the lack of large-scale training data in languages other than English -- makes them rarely used in mu…