Sina J. Semnani

Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models (EMNLP) [Paper] [Code][Demo]

🥖 CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition (EMNLP) [Paper] [Code][Demo]

🍋 LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World (Findings of ACL) [Paper] [Code]

🌿SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions (Findings of EMNLP) [Paper] [Code] [Demo]

Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations (EMNLP) [Paper] [Code] [Demo]

Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval (Findings of EMNLP) [Paper]

🍝SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing (Findings of ACL) [Paper]

Benchmarks Underestimate the Readiness of Multilingual Dialogue Agents [Paper]

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia (Findings of EMNLP) [Paper] [Code] [Demo]

SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models (Findings of NAACL) [Paper] [Code]

X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents (Findings of ACL) [Paper] [Code]

Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata (EMNLP) [Paper] [Code]

Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation (EACL) [Paper] [Code]

A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk Representation (Findings of ACL) [Paper] [Code]

ThingTalk: An Extensible, Executable Representation Language for Task-Oriented Dialogues [Paper] [Code]

Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation (EMNLP) [Paper] [Code]

AutoQA: From Databases to QA Semantic Parsers with Only Synthetic Training Data (EMNLP) [Paper] [Code]

Revisiting the Open-Domain Question Answering Pipeline [Paper]

Domain-Specific Question Answering at Scale for Conversational Systems [Paper]

BERT-A: Finetuning BERT with Adapters and Data Augmentation [Paper]

House Price Prediction using Satellite Imagery [Paper]