Lorenzo Bertolini


2022

pdf bib
Testing Large Language Models on Compositionality and Inference with Phrase-Level Adjective-Noun Entailment
Lorenzo Bertolini | Julie Weeds | David Weir
Proceedings of the 29th International Conference on Computational Linguistics

Previous work has demonstrated that pre-trained large language models (LLM) acquire knowledge during pre-training which enables reasoning over relationships between words (e.g, hyponymy) and more complex inferences over larger units of meaning such as sentences. Here, we investigate whether lexical entailment (LE, i.e. hyponymy or the is a relation between words) can be generalised in a compositional manner. Accordingly, we introduce PLANE (Phrase-Level Adjective-Noun Entailment), a new benchmark to test models on fine-grained compositional entailment using adjective-noun phrases. Our experiments show that knowledge extracted via In–Context and transfer learning is not enough to solve PLANE. However, a LLM trained on PLANE can generalise well to out–of–distribution sets, since the required knowledge can be stored in the representations of subwords (SW) tokens.

2021

pdf bib
Data Augmentation for Hypernymy Detection
Thomas Kober | Julie Weeds | Lorenzo Bertolini | David Weir
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

The automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed representations has generally been impeded by the limited availability of high quality training data. We have developed two novel data augmentation techniques which generate new training examples from existing ones. First, we combine the linguistic principles of hypernym transitivity and intersective modifier-noun composition to generate additional pairs of vectors, such as “small dog - dog” or “small dog - animal”, for which a hypernymy relationship can be assumed. Second, we use generative adversarial networks (GANs) to generate pairs of vectors for which the hypernymy relation can also be assumed. We furthermore present two complementary strategies for extending an existing dataset by leveraging linguistic resources such as WordNet. Using an evaluation across 3 different datasets for hypernymy detection and 2 different vector spaces, we demonstrate that both of the proposed automatic data augmentation and dataset extension strategies substantially improve classifier performance.

pdf bib
Representing Syntax and Composition with Geometric Transformations
Lorenzo Bertolini | Julie Weeds | David Weir | Qiwei Peng
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021