38 citations · 238 across the 42 of their papers we have counts for
58 papers
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…
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,…
Detecting and Mitigating Hallucinations in Multilingual Summarisation
Yifu Qiu, Yftah Ziser, Anna Korhonen +2
Hallucinations pose a significant challenge to the reliability of neural models for abstractive summarisation. While automatically generated summaries may be fluent, they often lac…
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…
Language-Agnostic Bias Detection in Language Models with Bias Probing
Abdullatif Köksal, Omer Faruk Yalcin, Ahmet Akbiyik +3
Pretrained language models (PLMs) are key components in NLP, but they contain strong social biases. Quantifying these biases is challenging because current methods focusing on fill…
LongForm: Effective Instruction Tuning with Reverse Instructions
Abdullatif Köksal, Timo Schick, Anna Korhonen +1
Instruction tuning enables language models to more effectively generalize and better follow user intent. However, obtaining instruction data is costly and challenging. Prior work e…
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…
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…
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…
Improving Word Translation via Two-Stage Contrastive Learning
Yaoyiran Li, Fangyu Liu, Nigel Collier +2
Word translation or bilingual lexicon induction (BLI) is a key cross-lingual task, aiming to bridge the lexical gap between different languages. In this work, we propose a robust a…
Delving Deeper into Cross-lingual Visual Question Answering
Chen Liu, Jonas Pfeiffer, Anna Korhonen +2
Visual question answering (VQA) is one of the crucial vision-and-language tasks. Yet, existing VQA research has mostly focused on the English language, due to a lack of suitable ev…
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation
Olga Majewska, Evgeniia Razumovskaia, Edoardo Maria Ponti +2
Multilingual task-oriented dialogue (ToD) facilitates access to services and information for many (communities of) speakers. Nevertheless, the potential of this technology is not f…
Measuring Context-Word Biases in Lexical Semantic Datasets
Qianchu Liu, Diana McCarthy, Anna Korhonen
State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that perfo…
Composable Sparse Fine-Tuning for Cross-Lingual Transfer
Alan Ansell, Edoardo Maria Ponti, Anna Korhonen +1
Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic f…
MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models
Qianchu Liu, Fangyu Liu, Nigel Collier +2
Recent work indicated that pretrained language models (PLMs) such as BERT and RoBERTa can be transformed into effective sentence and word encoders even via simple self-supervised t…
Towards Zero-shot Language Modeling
Edoardo Maria Ponti, Ivan Vulić, Ryan Cotterell +2
Can we construct a neural model that is inductively biased towards learning human languages? Motivated by this question, we aim at constructing an informative prior over neural wei…
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking
Fangyu Liu, Ivan Vulić, Anna Korhonen +1
Injecting external domain-specific knowledge (e.g., UMLS) into pretrained language models (LMs) advances their capability to handle specialised in-domain tasks such as biomedical e…
AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples
Qianchu Liu, Edoardo M. Ponti, Diana McCarthy +2
Capturing word meaning in context and distinguishing between correspondences and variations across languages is key to building successful multilingual and cross-lingual text repre…
Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems
Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska +3
In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent to complete a concrete task. Although this technology represents one of the central objectives…