Search Results for author:
Found 27 papers, 3 papers with code
Every time I fire a conversational designer, the performance of the dialogue system goes down
In fact, rules from conversational designers used in CLINN significantly outperform a state-of-the-art neural-based dialogue system when trained with smaller sets of annotated dialogues.
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations
Syntactic parsers have dominated natural language understanding for decades.
Change My Mind: How Syntax-based Hate Speech Recognizer Can Uncover Hidden Motivations Based on Different Viewpoints
Hate speech recognizers may mislabel sentences by not considering the different opinions that society has on selected topics.
Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation
Our results indicate a significant performance drop in GPT-3. 5 on the unfamiliar Termite dataset, even with ATD modifications, highlighting the effect of Data Contamination on LLMs in Text-to-SQL translation tasks.
Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models
This approach maintains model performance while allowing storage of only the optimized subnetwork, leading to significant memory savings.
Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
Reasoning methods, best exemplified by the well-known Chain-of-Thought (CoT), empower the reasoning abilities of Large Language Models (LLMs) by eliciting them to solve complex tasks in a step-by-step manner.
HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
Following a correlation between first positions and model choices due to positional bias, we hypothesized the presence of structural heuristics in the decision-making process of the It-LLMs, strengthened by including significant examples in few-shot scenarios.
A Trip Towards Fairness: Bias and De-Biasing in Large Language Models
In this paper, we performed a large investigation of the bias of three families of CtB-LLMs, and we showed that debiasing techniques are effective and usable.
PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
Pre-trained Language Models such as BERT are impressive machines with the ability to memorize, possibly generalized learning examples.
Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
The impressive achievements of transformers force NLP researchers to delve into how these models represent the underlying structure of natural language.
Active Informed Consent to Boost the Application of Machine Learning in Medicine
In this paper, we present Active Informed Consent (AIC) as a novel hybrid legal-technological tool to foster the gathering of a large amount of data for machine learning.
The Dark Side of the Language: Pre-trained Transformers in the DarkNet
Pre-trained Transformers are challenging human performances in many NLP tasks.
Every time I fire a conversational designer, the performance of the dialog system goes down
Incorporating explicit domain knowledge into neural-based task-oriented dialogue systems is an effective way to reduce the need of large sets of annotated dialogues.
Lacking the embedding of a word? Look it up into a traditional dictionary
In this paper, we propose to use definitions retrieved in traditional dictionaries to produce word embeddings for rare words.
When will the mist clear? On the Interpretability of Machine Learning for Medical Applications: a survey
Among the most challenging targets of interest in medicine are cancer diagnosis and therapies but, to start this revolution, software tools need to be adapted to cover the new requirements.
GASP! Generating Abstracts of Scientific Papers from Abstracts of Cited Papers
In this paper, we dare to introduce the novel, scientifically and philosophically challenging task of Generating Abstracts of Scientific Papers from abstracts of cited papers (GASP) as a text-to-text task to investigate scientific creativity, To foster research in this novel, challenging task, we prepared a dataset by using services where that solve the problem of copyright and, hence, the dataset is public available with its standard split.
SyntNN at SemEval-2018 Task 2: is Syntax Useful for Emoji Prediction? Embedding Syntactic Trees in Multi Layer Perceptrons
In this paper, we present SyntNN as a way to include traditional syntactic models in multilayer neural networks used in the task of Semeval Task 2 of emoji prediction.
Human-in-the-loop Artificial Intelligence
Little by little, newspapers are revealing the bright future that Artificial Intelligence (AI) is building.
Parsing with CYK over Distributed Representations
By showing that CYK can be entirely performed on distributed representations, we open the way to the definition of recurrent layers of CYK-informed neural networks.
Symbolic, Distributed and Distributional Representations for Natural Language Processing in the Era of Deep Learning: a Survey
Natural language is inherently a discrete symbolic representation of human knowledge.
