Picture for Neha Verma

Neha Verma

Merging Feed-Forward Sublayers for Compressed Transformers

Add code
Jan 10, 2025
Viaarxiv icon

Merging Text Transformer Models from Different Initializations

Add code
Mar 07, 2024
Figure 1 for Merging Text Transformer Models from Different Initializations
Figure 2 for Merging Text Transformer Models from Different Initializations
Figure 3 for Merging Text Transformer Models from Different Initializations
Figure 4 for Merging Text Transformer Models from Different Initializations
Viaarxiv icon

Pixel Representations for Multilingual Translation and Data-efficient Cross-lingual Transfer

Add code
May 23, 2023
Viaarxiv icon

Exploring Representational Disparities Between Multilingual and Bilingual Translation Models

Add code
May 23, 2023
Viaarxiv icon

IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces

Add code
Oct 11, 2022
Figure 1 for IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Figure 2 for IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Figure 3 for IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Figure 4 for IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Viaarxiv icon

Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review

Add code
Jul 07, 2021
Figure 1 for Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review
Figure 2 for Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review
Figure 3 for Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review
Figure 4 for Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review
Viaarxiv icon

FeTaQA: Free-form Table Question Answering

Add code
Apr 01, 2021
Figure 1 for FeTaQA: Free-form Table Question Answering
Figure 2 for FeTaQA: Free-form Table Question Answering
Figure 3 for FeTaQA: Free-form Table Question Answering
Figure 4 for FeTaQA: Free-form Table Question Answering
Viaarxiv icon

DART: Open-Domain Structured Data Record to Text Generation

Add code
Jul 06, 2020
Figure 1 for DART: Open-Domain Structured Data Record to Text Generation
Figure 2 for DART: Open-Domain Structured Data Record to Text Generation
Figure 3 for DART: Open-Domain Structured Data Record to Text Generation
Figure 4 for DART: Open-Domain Structured Data Record to Text Generation
Viaarxiv icon

Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations

Add code
Jun 08, 2019
Figure 1 for Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
Figure 2 for Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
Figure 3 for Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
Figure 4 for Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
Viaarxiv icon