Natural Language Processing | Gabriele Sarti

Natural Language Processing

Inseq: An Interpretability Toolkit for Sequence Generation Models

This talk introduces the Inseq toolkit for interpreting sequence generation models. The usage of Inseq is illustrated with examples introducing state-of-the-art approaches for interpreting language models such as contrastive attribution, tuned lenses and causal mediation analysis.

Advanced XAI Techniques and Inseq: An Interpretability Toolkit for Sequence Generation Models

This talk introduces the Inseq toolkit for interpreting sequence generation models. The usage of Inseq is illustrated with examples introducing state-of-the-art approaches for interpreting language models such as contrastive attribution, tuned lenses and causal mediation analysis.

Introducing Inseq: An Interpretability Toolkit for Sequence Generation Models

After motivating the usage of interpretability methods in NLP, this talk introduces the Inseq toolkit for interpreting sequence generation models. The usage of Inseq is illustrated on two case studies related to gender bias in machine translation and locating factual knowledge withing GPT-2 representations.

Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation

We analyze input contributions of char-level MT models and show how they modulate word and character-level information.

Inseq: An Interpretability Toolkit for Sequence Generation Models

We present Inseq, a Python library to democratize access to interpretability analyses of sequence generation models.

Attributing Context Usage in Language Models

An interpretability framework to detect and attribute context usage in language models' generations

Inseq: An Interpretability Toolkit for Sequence Generation Models

An open-source library to democratize access to model interpretability for sequence generation models

Towards User-centric Interpretability of Machine Translation Models

With the astounding advances of artificial intelligence in recent years, interpretability research has emerged as a fundamental effort to ensure the development of robust and transparent AI systems aligned with human needs. This talk will focus on user-centric interpretability applications aimed at improving our understanding of machine translation systems, with the ultimate goal of improving post-editing productivity and enjoyability.

Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties

We investigate whether and how using different architectures of probing models affects the performance of Italian transformers in encoding a wide spectrum of linguistic features.

DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages

DivEMT is a publicly available post-editing study of Neural Machine Translation over a typologically diverse set of target languages.