Search Results - "Gritta, Milan"

A pragmatic guide to geoparsing evaluation: Toponyms, Named Entity Recognition and pragmatics by Gritta, Milan, Pilehvar, Mohammad Taher, Collier, Nigel

“…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…”
Get full text

What's missing in geographical parsing? by Gritta, Milan, Pilehvar, Mohammad Taher, Limsopatham, Nut, Collier, Nigel

“…Geographical data can be obtained by converting place names from free-format text into geographical coordinates. The ability to geo-locate events in textual…”
Get full text

Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management by Gritta, Milan, Lampouras, Gerasimos, Iacobacci, Ignacio

“…Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets…”
Get full text

A pragmatic guide to geoparsing evaluation by Gritta Milan, Pilehvar Mohammad Taher, Collier, Nigel

“…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…”
Get full text

Multi 3 WOZ : A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems by Hu, Songbo, Zhou, Han, Hergul, Mete, Gritta, Milan, Zhang, Guchun, Iacobacci, Ignacio, Vulić, Ivan, Korhonen, Anna

“…Abstract Creating high-quality annotated data for task-oriented dialog (ToD) is known to be notoriously difficult, and the challenges are amplified when the…”
Get full text

Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems by Hu, Songbo, Zhou, Han, Hergul, Mete, Gritta, Milan, Zhang, Guchun, Iacobacci, Ignacio, Vulić, Ivan, Korhonen, Anna

“…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…”
Get full text

A Comparison of Techniques for Sentiment Classification of Film Reviews by Gritta, Milan

“…We undertake the task of comparing lexicon-based sentiment classification of film reviews with machine learning approaches. We look at existing methodologies…”
Get full text

XeroAlign: Zero-Shot Cross-lingual Transformer Alignment by Gritta, Milan, Iacobacci, Ignacio

“…The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks. However, the lack of labelled task data…”
Get full text

HumanRankEval: Automatic Evaluation of LMs as Conversational Assistants by Gritta, Milan, Lampouras, Gerasimos, Iacobacci, Ignacio

“…Language models (LMs) as conversational assistants recently became popular tools that help people accomplish a variety of tasks. These typically result from…”
Get full text

Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency by Gee, Leonidas, Gritta, Milan, Lampouras, Gerasimos, Iacobacci, Ignacio

“…Code Language Models have been trained to generate accurate solutions, typically with no regard for runtime. On the other hand, previous works that explored…”
Get full text

CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding by Gritta, Milan, Hu, Ruoyu, Iacobacci, Ignacio

“…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…”
Get full text

Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning by Minixhofer, Benjamin, Gritta, Milan, Iacobacci, Ignacio

“…Transfer learning has become the dominant paradigm for many natural language processing tasks. In addition to models being pretrained on large datasets, they…”
Get full text

Mixture of Attentions For Speculative Decoding by Zimmer, Matthieu, Gritta, Milan, Lampouras, Gerasimos, Ammar, Haitham Bou, Wang, Jun

“…The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging…”
Get full text

Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management by Gritta, Milan, Lampouras, Gerasimos, Iacobacci, Ignacio

“…Task-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets…”
Get full text

A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems by Hu, Songbo, Zhou, Han, Yuan, Moy, Gritta, Milan, Zhang, Guchun, Iacobacci, Ignacio, Korhonen, Anna, Vulić, Ivan

“…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…”
Get full text

Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems by Hu, Songbo, Zhou, Han, Hergul, Mete, Gritta, Milan, Zhang, Guchun, Iacobacci, Ignacio, Vulić, Ivan, Korhonen, Anna

“…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…”
Get full text

A Pragmatic Guide to Geoparsing Evaluation by Gritta, Milan, Pilehvar, Mohammad Taher, Collier, Nigel

“…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…”
Get full text

PanGu-Coder: Program Synthesis with Function-Level Language Modeling by Christopoulou, Fenia, Lampouras, Gerasimos, Gritta, Milan, Zhang, Guchun, Guo, Yinpeng, Li, Zhongqi, Zhang, Qi, Xiao, Meng, Shen, Bo, Li, Lin, Yu, Hao, Yan, Li, Zhou, Pingyi, Wang, Xin, Ma, Yuchi, Iacobacci, Ignacio, Wang, Yasheng, Liang, Guangtai, Wei, Jiansheng, Jiang, Xin, Wang, Qianxiang, Liu, Qun

“…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…”
Get full text