activity
20192024
most citedReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking

6 citations · 6 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2024

HalluCana: Fixing LLM Hallucination with A Canary Lookahead

Tianyi Li, Erenay Dayanik, Shubhi Tyagi +1

In this paper, we present HalluCana, a canary lookahead to detect and correct factuality hallucinations of Large Language Models (LLMs) in long-form generation. HalluCana detects a…

cs.CL2024

REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking

Nacime Bouziani, Shubhi Tyagi, Joseph Fisher +2

Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE). Howe…

cs.CL2022★ 6 cited

ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking

Tom Ayoola, Shubhi Tyagi, Joseph Fisher +2

We introduce ReFinED, an efficient end-to-end entity linking model which uses fine-grained entity types and entity descriptions to perform linking. The model performs mention detec…

cs.CL2021

Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems

Shubhi Tyagi, Antonio Bonafonte, Jaime Lorenzo-Trueba +1

Developing Text Normalization (TN) systems for Text-to-Speech (TTS) on new languages is hard. We propose a novel architecture to facilitate it for multiple languages while using da…

cs.CL2019

Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection

Shubhi Tyagi, Marco Nicolis, Jonas Rohnke +2

Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences. But something which is still lacking i…