Search Results for author: Ignacio Iacobacci

Found 24 papers, 11 papers with code

Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis

1 code implementation20 Oct 2023 Philip John Gorinski, Matthieu Zimmer, Gerasimos Lampouras, Derrick Goh Xin Deik, Ignacio Iacobacci

The advent of large pre-trained language models in the domain of Code Synthesis has shown remarkable performance on various benchmarks, treating the problem of Code Generation in a fashion similar to Natural Language Generation, trained with a Language Modelling (LM) objective.

Code Generation Language Modelling +2

The Regular Expression Inference Challenge

no code implementations15 Aug 2023 Mojtaba Valizadeh, Philip John Gorinski, Ignacio Iacobacci, Martin Berger

We propose \emph{regular expression inference (REI)} as a challenge for code/language modelling, and the wider machine learning community.

Language Modelling Program Synthesis

Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems

1 code implementation26 Jul 2023 Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen

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, culturally adapted, and large-scale ToD datasets for multiple languages.

Translation

Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access

1 code implementation10 Dec 2022 Yue Feng, Gerasimos Lampouras, Ignacio Iacobacci

To alleviate the problem of structured databases' limited coverage, recent task-oriented dialogue systems incorporate external unstructured knowledge to guide the generation of system responses.

Response Generation Sentence +1

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

1 code implementation22 Oct 2022 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 generalisability.

Natural Language Understanding Zero-Shot Cross-Lingual Transfer

EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switching

no code implementations22 Oct 2022 Chenxi Whitehouse, Fenia Christopoulou, Ignacio Iacobacci

We use Wikidata and English Wikipedia to construct an entity-centric CS corpus by switching entities to their counterparts in other languages.

Data Augmentation Retrieval +3

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

no code implementations12 Oct 2022 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.

Question Answering

PanGu-Coder: Program Synthesis with Function-Level Language Modeling

1 code implementation22 Jul 2022 Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta, Guchun Zhang, Yinpeng Guo, Zhongqi Li, Qi Zhang, Meng Xiao, Bo Shen, Lin Li, Hao Yu, Li Yan, Pingyi Zhou, Xin Wang, Yuchi Ma, Ignacio Iacobacci, Yasheng Wang, Guangtai Liang, Jiansheng Wei, Xin Jiang, Qianxiang Wang, Qun Liu

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 solutions given a natural language problem description.

Code Generation Language Modelling +2

XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking

1 code implementation12 Apr 2022 Han Zhou, Ignacio Iacobacci, Pasquale Minervini

Dialogue State Tracking (DST), a crucial component of task-oriented dialogue (ToD) systems, keeps track of all important information pertaining to dialogue history: filling slots with the most probable values throughout the conversation.

Cross-Lingual Transfer Dialogue State Tracking +4

Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning

1 code implementation Findings (ACL) 2021 Benjamin Minixhofer, Milan Gritta, Ignacio Iacobacci

For small Natural Language Inference (NLI) datasets, language modelling is typically followed by pretraining on a large (labelled) NLI dataset before fine-tuning with each NLI subtask.

Language Modelling Natural Language Inference +1

Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation

no code implementations13 Jan 2021 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.

Commonsense Causal Reasoning Data Augmentation +1

Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management

2 code implementations29 Oct 2020 Milan Gritta, Gerasimos Lampouras, Ignacio Iacobacci

We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi-reference training and evaluation of non-deterministic agents.

Data Augmentation Dialogue Management +3

Show Us the Way: Learning to Manage Dialog from Demonstrations

no code implementations17 Apr 2020 Gabriel Gordon-Hall, Philip John Gorinski, Gerasimos Lampouras, Ignacio Iacobacci

We present our submission to the End-to-End Multi-Domain Dialog Challenge Track of the Eighth Dialog System Technology Challenge.

dialog state tracking Management +5

LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories

no code implementations ACL 2019 Ignacio Iacobacci, Roberto Navigli

While word embeddings are now a de facto standard representation of words in most NLP tasks, recently the attention has been shifting towards vector representations which capture the different meanings, i. e., senses, of words.

Word Embeddings

Embedding Words and Senses Together via Joint Knowledge-Enhanced Training

no code implementations CONLL 2017 Massimiliano Mancini, Jose Camacho-Collados, Ignacio Iacobacci, Roberto Navigli

Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora.

Word Embeddings

Semantic Representations of Word Senses and Concepts

no code implementations2 Aug 2016 José Camacho-Collados, Ignacio Iacobacci, Roberto Navigli, Mohammad Taher Pilehvar

Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days.

Cannot find the paper you are looking for? You can Submit a new open access paper.