activity
20202022
most citedShow Us the Way: Learning to Manage Dialog from Demonstrations

11 citations · 12 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2022

Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU

Fenia Christopoulou, Gerasimos Lampouras, Ignacio Iacobacci

Curriculum Learning (CL) is a technique of training models via ranking examples in a typically increasing difficulty trend with the aim of accelerating convergence and improving ge…

cs.CL2022

Relational Graph Convolutional Neural Networks for Multihop Reasoning: A Comparative Study

Ieva Staliūnaitė, Philip John Gorinski, Ignacio Iacobacci

Multihop Question Answering is a complex Natural Language Processing task that requires multiple steps of reasoning to find the correct answer to a given question. Previous researc…

cs.CL2022

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…

cs.CL2021

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…

cs.CL20211 cited

Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation

Ieva Staliūnaitė, Philip John Gorinski, Ignacio Iacobacci

Determining the plausibility of causal relations between clauses is a commonsense reasoning task that requires complex inference ability. The general approach to this task is to tr…

cs.CL2020

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…