Papers by Shubhi Tyagi
ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking (2022.naacl-industry)
Copied to clipboard
| Challenge: | Entity linking is the task of recognising mentions of entities in unstructured text documents and linking them to the corresponding entities in a Knowledge Base (KB) the largest public EL dataset is Wikipedia, which covers just 3% of the entities in Wikidata. |
| Approach: | They propose a model which performs mention detection, fine-grained entity typing, and entity disambiguation for all mentions within a document in a single forward pass. |
| Outcome: | The proposed model outperforms state-of-the-art methods on standard datasets by an average of 3.7 F1 and can generalise to large-scale knowledge bases such as Wikidata and zero-shot entity linking. |
HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to detect factual hallucinations w.r.t. world knowledge require assistive generations (samples, drafts, etc.) Existing approaches to factuality hallucinism detection, such as SelfCheckGPT, require assistively generation (sequences, Drafts, and etc.). Existing studies on factualism hallucinosation detection require assistives generations (Sample, draft, etc). |
| Approach: | They propose a canary lookahead which detects and corrects factual hallucinations of Large Language Models in long-form generation by exploiting the internal factuality representation in the LLM hidden space. |
| Outcome: | The proposed method improves generation quality by 2.5x while consuming over 6 times less compute. |
Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems (2021.naacl-industry)
Copied to clipboard
| Challenge: | Developing Text Normalization systems for Text-to-Speech (TTS) on new languages is hard. |
| Approach: | They propose a novel architecture to facilitate Text Normalization systems for TTS on new languages . they use a granular tokenization mechanism that enables the system to learn majority of classes . |
| Outcome: | The proposed architecture performs comparable with the state-of-the-art systems on English . the proposed system learns most classes from training data and precodes them for other classes . |