1.3k citations · 12.3k across the 104 of their papers we have counts for
19 papers · 2 filters
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi +2
Answering questions that require multi-hop reasoning at web-scale necessitates retrieving multiple evidence documents, one of which often has little lexical or semantic relationshi…
MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models
Linqing Liu, Huan Wang, Jimmy Lin +2
Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge d…
ERASER: A Benchmark to Evaluate Rationalized NLP Models
Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani +4
State-of-the-art models in NLP are now predominantly based on deep neural networks that are opaque in terms of how they come to make predictions. This limitation has increased inte…
Sketch-Fill-A-R: A Persona-Grounded Chit-Chat Generation Framework
Michael Shum, Stephan Zheng, Wojciech Kryściński +2
Human-like chit-chat conversation requires agents to generate responses that are fluent, engaging and consistent. We propose Sketch-Fill-A-R, a framework that uses a persona-memory…
Evaluating the Factual Consistency of Abstractive Text Summarization
Wojciech Kryściński, Bryan McCann, Caiming Xiong +1
Currently used metrics for assessing summarization algorithms do not account for whether summaries are factually consistent with source documents. We propose a weakly-supervised, m…
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking
Jian-Guo Zhang, Kazuma Hashimoto, Chien-Sheng Wu +4
Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST mainly fall into one of two categories, namely, ontology-based and onto…