24 citations · 32 across the 14 of their papers we have counts for
16 papers
TranslatePsy-AfriSLM: High-Quality Data Scaling For Low-Resource Machine Translation
Milan Gritta, Patrik Lambert, Jihye Back +1
The rapid progress in Artificial Intelligence has largely bypassed African languages, creating a digital divide that limits AI adoption on the continent. Recent open-source LLMs sy…
A Benchmark for Deep Information Synthesis
Debjit Paul, Daniel Murphy, Milan Gritta +14
Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current e…
DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems
Meiru Zhang, Philipp Borchert, Milan Gritta +1
Automating the formalization of mathematical statements for theorem proving remains a major challenge for Large Language Models (LLMs). LLMs struggle to identify and utilize the pr…
DReSD: Dense Retrieval for Speculative Decoding
Milan Gritta, Huiyin Xue, Gerasimos Lampouras
Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a sin…
Mixture of Attentions For Speculative Decoding
Matthieu Zimmer, Milan Gritta, Gerasimos Lampouras +2
The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. S…
Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency
Leonidas Gee, Milan Gritta, Gerasimos Lampouras +1
Code Language Models have been trained to generate accurate solutions, typically with no regard for runtime. On the other hand, previous works that explored execution optimisation…
HumanRankEval: Automatic Evaluation of LMs as Conversational Assistants
Milan Gritta, Gerasimos Lampouras, Ignacio Iacobacci
Language models (LMs) as conversational assistants recently became popular tools that help people accomplish a variety of tasks. These typically result from adapting LMs pretrained…
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems
Songbo Hu, Han Zhou, Moy Yuan +5
Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP. In this work, we take stock of and empirically…
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…
PanGu-Coder: Program Synthesis with Function-Level Language Modeling
Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta +19
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of programming language solut…
CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding
Milan Gritta, Ruoyu Hu, Ignacio Iacobacci
Task-oriented personal assistants enable people to interact with a host of devices and services using natural language. One of the challenges of making neural dialogue systems avai…
Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning
Benjamin Minixhofer, Milan Gritta, Ignacio Iacobacci
Transfer learning has become the dominant paradigm for many natural language processing tasks. In addition to models being pretrained on large datasets, they can be further trained…
XeroAlign: Zero-Shot Cross-lingual Transformer Alignment
Milan Gritta, Ignacio Iacobacci
The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks. However, the lack of labelled task data necessitates a variety…
Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management
Milan Gritta, Gerasimos Lampouras, Ignacio Iacobacci
Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in s…
A Comparison of Techniques for Sentiment Classification of Film Reviews
Milan Gritta
We undertake the task of comparing lexicon-based sentiment classification of film reviews with machine learning approaches. We look at existing methodologies and attempt to emulate…
A Pragmatic Guide to Geoparsing Evaluation
Milan Gritta, Mohammad Taher Pilehvar, Nigel Collier
Empirical methods in geoparsing have thus far lacked a standard evaluation framework describing the task, metrics and data used to compare state-of-the-art systems. Evaluation is f…