Natural Language

Natural language processing (NLP) focuses on enabling computers to understand, interpret, and generate human language. Current research heavily utilizes large language models (LLMs), such as BERT and others, to tackle diverse tasks including text-to-SQL translation, semantic analysis of images, and even controlling robots via natural language commands. The field's impact spans various sectors, from improving search engines and e-commerce platforms to advancing healthcare diagnostics and facilitating more efficient scientific research through automated literature analysis and data extraction.

Papers

June 6, 2023

June 5, 2023

Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language
Kevin Ellis
Language Model LeArning Abstract Natural Language Scientific Inference Human Like Hypothesis Class Inductive Learning

June 3, 2023

Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models
Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
Language Model Natural Language Image Generation Pre Trained Entity Mention Table Semantics Entity Knowledge Image Generation Task Specific Knowledge

June 2, 2023

May 31, 2023

Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding
Parker Glenn, Parag Pravin Dakle, Preethi Raghavan
Natural Language Semantic Parsing Text to SQL Semantic Parser Text to SQL Parser

May 26, 2023

Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks
Agam Shah, Sudheer Chava
Large Language Model Generative Model Natural Language System Performance Better Zero Zero to HeRo FINancial Task

May 25, 2023

May 24, 2023

May 23, 2023

Natural Language

Papers

Language acquisition: do children and language models follow similar learning stages?

Natural Language Commanding via Program Synthesis

Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language

Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models

NLPositionality: Characterizing Design Biases of Datasets and Models

GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration

An Empirical Study on Challenging Math Problem Solving with GPT-4

Correcting Semantic Parses with Natural Language through Dynamic Schema Encoding

Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks

Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language

Asking Before Acting: Gather Information in Embodied Decision Making with Language Models

Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation

Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective

Transferring Visual Attributes from Natural Language to Verified Image Generation

GlobalBench: A Benchmark for Global Progress in Natural Language Processing

Modeling rapid language learning by distilling Bayesian priors into artificial neural networks

Question Answering as Programming for Solving Time-Sensitive Questions

Process-To-Text: A Framework for the Quantitative Description of Processes in Natural Language

Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning

Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study