Papers by Alex Lascarides
Learning the Effects of Physical Actions in a Multi-modal Environment (2023.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are trained on large corpora of disembodied texts. |
| Approach: | They propose a multi-modal task of predicting the outcomes of actions solely from realistic sensory inputs (images and text). They extend an LLM to model latent representations of objects to better predict action outcomes in an environment. |
| Outcome: | The proposed model can capture commonsense when augmented with visual information and generalize and learn commonsensical reasoning better. |
Interactive Symbol Grounding with Complex Referential Expressions (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing work on symbol grounding models (grounders) uses lazy few-shot learning to relate open-class words like green and above to their visual percepts; and symbolic reasoning with closed-class word categories like quantifiers and negation. |
| Approach: | They propose a procedure for learning to ground symbols from a sequence of stimuli consisting of an arbitrarily complex noun phrase and its designation in the visual scene. |
| Outcome: | The proposed procedure is based on a visual reference resolution task in which the learner is unaware of concepts that are part of the domain model and how they relate to visual percepts. |
Contrastive Learning with Narrative Twins for Modeling Story Salience (2026.eacl-long)
Copied to clipboard
| Challenge: | Understanding narratives requires identifying which events are most salient for a story’s progression. |
| Approach: | They propose a contrastive learning framework that learns story embeddings from narrative twins to distinguish a story from its distractor with similar surface features but different plot. |
| Outcome: | The proposed model outperforms a masked-language-model and summarizes sentences with the most reliable operation for identifying salient sentences. |