Compositional semantic parsing with large language models
Humans can reason compositionally when presented with new tasks. Previous research
shows that appropriate prompting techniques enable large language models (LLMs) to …
shows that appropriate prompting techniques enable large language models (LLMs) to …
State-of-the-art generalisation research in NLP: a taxonomy and review
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
A survey on compositional generalization in applications
The field of compositional generalization is currently experiencing a renaissance in AI, as
novel problem settings and algorithms motivated by various practical applications are being …
novel problem settings and algorithms motivated by various practical applications are being …
Compositional generalization in multilingual semantic parsing over Wikidata
Semantic parsing (SP) allows humans to leverage vast knowledge resources through
natural interaction. However, parsers are mostly designed for and evaluated on English …
natural interaction. However, parsers are mostly designed for and evaluated on English …
Latent constraints on unsupervised text-graph alignment with information asymmetry
Unsupervised text-graph alignment (UTGA) is a fundamental task that bidirectionally
generates texts and graphs without parallel data. Most available models of UTGA suffer from …
generates texts and graphs without parallel data. Most available models of UTGA suffer from …
Laziness is a virtue when it comes to compositionality in neural semantic parsing
Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-
down autoregressive fashion. Though such systems have achieved impressive results …
down autoregressive fashion. Though such systems have achieved impressive results …
PTAN: Principal Token-aware Adjacent Network for Compositional Temporal Grounding
Compositional temporal grounding (CTG) aims to localize the most relevant segment from
an untrimmed video based on a given natural language sentence, and the test samples for …
an untrimmed video based on a given natural language sentence, and the test samples for …
GenCHiP: Generating Robot Policy Code for High-Precision and Contact-Rich Manipulation Tasks
Large Language Models (LLMs) have been successful at generating robot policy code, but
so far these results have been limited to high-level tasks that do not require precise …
so far these results have been limited to high-level tasks that do not require precise …
[PDF][PDF] Unlocking Natural Language Generalization with Adaptive Retrieval-based Methods
A Drozdov - 2024 - scholarworks.umass.edu
Large language models (LLMs) exhibit strong performance on a variety of tasks without
additional task-specific fine-tuning. Their success is often attributed to incontext learning …
additional task-specific fine-tuning. Their success is often attributed to incontext learning …
[PDF][PDF] State-of-the-art generalisation research in NLP
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what 'good generalisation'entails and how it should be evaluated is …
processing (NLP). Yet, what 'good generalisation'entails and how it should be evaluated is …