Picture for Vittorio Castelli

Vittorio Castelli

IBM Research AI, T.J. Watson Research Center, New York, USA

From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification

Add code
Mar 10, 2024
Figure 1 for From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
Figure 2 for From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
Figure 3 for From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
Figure 4 for From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
Viaarxiv icon

NewsQs: Multi-Source Question Generation for the Inquiring Mind

Add code
Feb 28, 2024
Figure 1 for NewsQs: Multi-Source Question Generation for the Inquiring Mind
Figure 2 for NewsQs: Multi-Source Question Generation for the Inquiring Mind
Figure 3 for NewsQs: Multi-Source Question Generation for the Inquiring Mind
Figure 4 for NewsQs: Multi-Source Question Generation for the Inquiring Mind
Viaarxiv icon

Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning

Add code
Aug 10, 2023
Figure 1 for Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
Figure 2 for Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
Figure 3 for Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
Figure 4 for Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning
Viaarxiv icon

Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge

Add code
May 30, 2023
Figure 1 for Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Figure 2 for Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Figure 3 for Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Figure 4 for Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge
Viaarxiv icon

Benchmarking Diverse-Modal Entity Linking with Generative Models

Add code
May 27, 2023
Figure 1 for Benchmarking Diverse-Modal Entity Linking with Generative Models
Figure 2 for Benchmarking Diverse-Modal Entity Linking with Generative Models
Figure 3 for Benchmarking Diverse-Modal Entity Linking with Generative Models
Figure 4 for Benchmarking Diverse-Modal Entity Linking with Generative Models
Viaarxiv icon

UNITE: A Unified Benchmark for Text-to-SQL Evaluation

Add code
May 26, 2023
Figure 1 for UNITE: A Unified Benchmark for Text-to-SQL Evaluation
Figure 2 for UNITE: A Unified Benchmark for Text-to-SQL Evaluation
Figure 3 for UNITE: A Unified Benchmark for Text-to-SQL Evaluation
Viaarxiv icon

Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification

Add code
May 24, 2023
Figure 1 for Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
Figure 2 for Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
Figure 3 for Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
Figure 4 for Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification
Viaarxiv icon

Taxonomy Expansion for Named Entity Recognition

Add code
May 22, 2023
Figure 1 for Taxonomy Expansion for Named Entity Recognition
Figure 2 for Taxonomy Expansion for Named Entity Recognition
Figure 3 for Taxonomy Expansion for Named Entity Recognition
Figure 4 for Taxonomy Expansion for Named Entity Recognition
Viaarxiv icon

Comparing Biases and the Impact of Multilingual Training across Multiple Languages

Add code
May 18, 2023
Figure 1 for Comparing Biases and the Impact of Multilingual Training across Multiple Languages
Figure 2 for Comparing Biases and the Impact of Multilingual Training across Multiple Languages
Figure 3 for Comparing Biases and the Impact of Multilingual Training across Multiple Languages
Figure 4 for Comparing Biases and the Impact of Multilingual Training across Multiple Languages
Viaarxiv icon

Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness

Add code
Jan 21, 2023
Figure 1 for Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
Figure 2 for Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
Figure 3 for Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
Figure 4 for Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
Viaarxiv icon