no code implementations • EMNLP (NLLP) 2021 • Mihai Masala, Radu Cristian Alexandru Iacob, Ana Sabina Uban, Marina Cidota, Horia Velicu, Traian Rebedea, Marius Popescu
Transformer-based models have become the de facto standard in the field of Natural Language Processing (NLP).
no code implementations • VarDial (COLING) 2020 • George-Eduard Zaharia, Andrei-Marius Avram, Dumitru-Clementin Cercel, Traian Rebedea
Dialect identification represents a key aspect for improving a series of tasks, for example, opinion mining, considering that the location of the speaker can greatly influence the attitude towards a subject.
no code implementations • EACL (VarDial) 2021 • George-Eduard Zaharia, Andrei-Marius Avram, Dumitru-Clementin Cercel, Traian Rebedea
Dialect identification is a task with applicability in a vast array of domains, ranging from automatic speech recognition to opinion mining.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • COLING 2022 • Iustin Sirbu, Tiberiu Sosea, Cornelia Caragea, Doina Caragea, Traian Rebedea
In this paper, we investigate how to leverage the copious amounts of unlabeled data generated on social media by disaster eyewitnesses and affected individuals during disaster events.
no code implementations • 4 Apr 2024 • Makesh Narsimhan Sreedhar, Traian Rebedea, Shaona Ghosh, Christopher Parisien
Recent advancements in instruction-tuning datasets have predominantly focused on specific tasks like mathematical or logical reasoning.
no code implementations • 29 Feb 2024 • Mihai Masala, Traian Rebedea, Horia Velicu
In recent years, the entire field of Natural Language Processing (NLP) has enjoyed amazing novel results achieving almost human-like performance on a variety of tasks.
1 code implementation • 16 Oct 2023 • Traian Rebedea, Razvan Dinu, Makesh Sreedhar, Christopher Parisien, Jonathan Cohen
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
no code implementations • 29 Aug 2023 • Mihai Masala, Nicolae Cudlenco, Traian Rebedea, Marius Leordeanu
Artificial Intelligence makes great advances today and starts to bridge the gap between vision and language.
no code implementations • 2 Aug 2023 • Andrei-Alexandru Preda, Dumitru-Clementin Cercel, Traian Rebedea, Costin-Gabriel Chiru
This paper describes the solutions submitted by the UPB team to the AuTexTification shared task, featured as part of IberLEF-2023.
no code implementations • 22 May 2023 • Mihai Masala, Nicolae Cudlenco, Traian Rebedea, Marius Leordeanu
GEST alows us to measure the similarity between texts and videos in a semantic and fully explainable way, through graph matching.
1 code implementation • LREC 2022 • Andrei-Marius Avram, Darius Catrina, Dumitru-Clementin Cercel, Mihai Dascălu, Traian Rebedea, Vasile Păiş, Dan Tufiş
In this work, we introduce three light and fast versions of distilled BERT models for the Romanian language: Distil-BERT-base-ro, Distil-RoBERT-base, and DistilMulti-BERT-base-ro.
1 code implementation • 8 Apr 2021 • Nicolae-Teodor Pavel, Traian Rebedea
In this paper we apply neural machine translation (NMT) techniques to convert code diffs into commit messages and we present an improved sketch-based encoder for this task.
no code implementations • EACL 2021 • Cristian Popa, Traian Rebedea
We propose a novel solution for assigning labels to topic models by using multiple weak labelers.
no code implementations • COLING 2020 • Radu Cristian Alexandru Iacob, Florin Brad, Elena-Simona Apostol, Ciprian-Octavian Truic{\u{a}}, Ionel Alexandru Hosu, Traian Rebedea
A natural language interface to databases (NLIDB) enables users without technical expertise to easily access information from relational databases.
no code implementations • SEMEVAL 2020 • George-Eduard Zaharia, George-Alexandru Vlad, Dumitru-Clementin Cercel, Traian Rebedea, Costin-Gabriel Chiru
In this paper, we describe the systems developed by our team for SemEval-2020 Task 9 that aims to cover two well-known code-mixed languages: Hindi-English and Spanish-English.
no code implementations • 23 Jun 2020 • Radu D. Stochiţoiu, Marian Petrica, Traian Rebedea, Ionel Popescu, Marius Leordeanu
More specifically, we want to statistically estimate all the relevant parameters for the new coronavirus COVID-19, such as the reproduction number, fatality rate or length of infectiousness period, based on Romanian patients, as well as be able to predict future outcomes.
no code implementations • IJCNLP 2019 • George Sebastian Pirtoaca, Traian Rebedea, Stefan Ruseti
Answering multiple-choice questions in a setting in which no supporting documents are explicitly provided continues to stand as a core problem in natural language processing.
no code implementations • 2 Sep 2019 • George-Sebastian Pîrtoacă, Traian Rebedea, Stefan Ruseti
Answering multiple-choice questions in a setting in which no supporting documents are explicitly provided continues to stand as a core problem in natural language processing.
no code implementations • RANLP 2019 • Alex Bod{\^\i}rl{\u{a}}u, ra Maria, Stefania Budulan, Traian Rebedea
Goal-Oriented Chatbots in fields such as customer support, providing certain information or general help with bookings or reservations, suffer from low performance partly due to the difficulty of obtaining large domain-specific annotated datasets.
1 code implementation • 7 Dec 2018 • George-Sebastian Pirtoaca, Traian Rebedea, Stefan Ruseti
Question answering is one of the most important and difficult applications at the border of information retrieval and natural language processing, especially when we talk about complex science questions which require some form of inference to determine the correct answer.
no code implementations • COLING 2018 • Ionel Alex Hosu, Radu Cristian Alex Iacob, ru, Florin Brad, Stefan Ruseti, Traian Rebedea
We propose a sketch-based two-step neural model for generating structured queries (SQL) based on a user{'}s request in natural language.
no code implementations • WS 2017 • Florin Brad, Traian Rebedea
Progress in statistical paraphrase generation has been hindered for a long time by the lack of large monolingual parallel corpora.
1 code implementation • IJCNLP 2017 • Florin Brad, Radu Iacob, Ionel Hosu, Traian Rebedea
Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability.
1 code implementation • 18 Jul 2016 • Ionel-Alexandru Hosu, Traian Rebedea
This paper introduces a novel method for learning how to play the most difficult Atari 2600 games from the Arcade Learning Environment using deep reinforcement learning.