Search Results for author:
Found 5 papers, 3 papers with code
HalluCana: Fixing LLM Hallucination with A Canary Lookahead
In this paper, we present HalluCana, a canary lookahead to detect and correct factuality hallucinations of Large Language Models (LLMs) in long-form generation.
REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking
Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE).
Ranked #1 on
Coreference Resolution
on DWIE
ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking
The model is capable of generalising to large-scale knowledge bases such as Wikidata (which has 15 times more entities than Wikipedia) and of zero-shot entity linking.
Ranked #1 on
Entity Linking
on WebQSP-WD
(using extra training data)
Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems
Developing Text Normalization (TN) systems for Text-to-Speech (TTS) on new languages is hard.
Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection
Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences.
