Papers by Milan Gritta
Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management (2021.tacl-1)
Copied to clipboard
| Challenge: | Existing datasets limited in size con- sidering complexity of dialogues . current trends lean towards end-to-end models while modular systems tend to be preferred in industrial applications. |
| Approach: | They propose a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non-deterministic agents. |
| Outcome: | The proposed graph-based representation of dialogues can be exploited for data augmentation, multi- reference training and evaluation of non-deterministic agents. |
DReSD: Dense Retrieval for Speculative Decoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Speculative decoding (SD) uses an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its outputs. |
| Approach: | They propose a draft model that proposes the next few tokens from a non-parametric datastore and uses a framework that uses approximate nearest neighbour search with contextualised token embeddings to retrieve the most semantically relevant sequences for SD. |
| Outcome: | The proposed framework achieves (on average) 87% higher acceptance rates, 65% longer accepted tokens and 19% faster generation speeds compared to sparse retrieval (REST). |
Process Evaluation for Agentic Systems (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent adoption of LLM-based assistants has led to premature assumptions about their reliability and general capability. |
| Approach: | They propose to assess the feasibility of automatic process evaluation for critical applications such as medicine, finance, law and infrastructure. |
| Outcome: | The proposed evaluations are based on a small-scale study to assess the feasibility of automated process evaluation, present a compliance score, analyse use cases of bad and good behaviours, and offer recommendations for more holistic evaluation. |
Multi 3 WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems (2023.tacl-1)
Copied to clipboard
Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen
| Challenge: | Task-oriented dialog (TOD) is one of the central objectives, hallmarks, and applications of machine intelligence. |
| Approach: | They propose a multilingual, multi-domain, multiparallele ToD dataset that offers culturally adapted dialogs in 4 languages for training and evaluation of multilingual and cross-lingual systems. |
| Outcome: | The proposed dataset is large-scale and culturally adapted to enable training and evaluation of multilingual and cross-lingual ToD systems. |
XeroAlign: Zero-shot cross-lingual transformer alignment (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing zero-shot approaches to improve multilingual NLP tasks require translation of task data to bridge the gap between the source and target language. |
| Approach: | They propose a method for task-specific alignment of cross-lingual pretrained transformers such as XeroAlign that uses translated task data to encourage the model to generate similar sentence embeddings for different languages. |
| Outcome: | The proposed method performs on par with state-of-the-art models on a cross-lingual adversarial paraphrasing task and its text classification accuracy exceeds that of XLM-R trained with labelled data. |
Which Melbourne? Augmenting Geocoding with Maps (P18-1)
Copied to clipboard
| Challenge: | Existing methods to associate geographic information in text with coordinates are limited by lexical features and cartesian coordinates. |
| Approach: | They propose a geocoder that exploits implicit lexical clues to associate coordinates with text . they propose encoding of geographic metadata to generate two distinct views of the same text. |
| Outcome: | The proposed method improves state-of-the-art results on three datasets and an open-source dataset for disease outbreaks and epidemics. |
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems (2023.emnlp-main)
Copied to clipboard
Songbo Hu, Han Zhou, Moy Yuan, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Anna Korhonen, Ivan Vulić
| Challenge: | Existing systems trained for Arabic or Turkish using annotated data fully parallel to English ToD data still exhibit diminished ToD task performance. |
| Approach: | They define new quantitative measures of absolute and relative equivalence in system performance, capturing disparities across languages and within individual languages. |
| Outcome: | The proposed measures capture disparities across languages and within individual languages. |
CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding (2022.findings-acl)
Copied to clipboard
| Challenge: | Task-oriented personal assistants enable people to interact with devices and services using natural language. |
| Approach: | They propose a method to acquire task knowledge in a high-resource language and then transfer it to the low-resourced language(s) they use unlabelled parallel data to perform a quantitative analysis of the methods. |
| Outcome: | The proposed methods exceed state-of-the-art (SOTA) scores across nine languages, fifteen test sets and three benchmark multilingual datasets. |
Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in transfer learning have brought significant improvements to many natural language processing tasks. |
| Approach: | They propose a method of fitting a GBDT head on the features computed during finetuning to increase performance without additional computation by the neural network. |
| Outcome: | The proposed method improves on several NLI datasets using a strong baseline model (RoBERTa-large) with MNLI pretraining. |
Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have shown that CLMs can generate accurate solutions with no regard for runtime, but at a substantial cost to correctness (down by up to 30%) |
| Approach: | They propose a framework that incorporates correctness and runtime as learning signals via self-generated preference data. |
| Outcome: | The proposed framework reduces the baseline runtimes by 6% and the average length of the generated solutions is reduced by up to 48% on MBPP and 23% on HumanEval. |
HumanRankEval: Automatic Evaluation of LMs as Conversational Assistants (2024.naacl-long)
Copied to clipboard
| Challenge: | Language models (LMs) are popular conversational assistants, but evaluation of such models is not scalable. |
| Approach: | They propose a task that performs automatic evaluation using human judgement and a large-scale set of questions with multiple answers authored and scored by humans. |
| Outcome: | The proposed task performs well with human judgements and is particularly responsive to model changes following instruction-tuning. |