Search Results for author:
Found 6 papers, 3 papers with code
Neural Conversational QA: Learning to Reason vs Exploiting Patterns
Neural Conversational QA tasks such as ShARC require systems to answer questions based on the contents of a given passage.
Variational Learning for Unsupervised Knowledge Grounded Dialogs
Recent methods for knowledge grounded dialogs generate responses by incorporating information from an external textual document.
Inductive Quantum Embedding
Our training runs 9-times faster than the original QE scheme on this task.
Neural Conversational QA: Learning to Reason v.s. Exploiting Patterns
On studying recent state-of-the-art models on the ShARCQA task, we found indications that the models learn spurious clues/patterns in the dataset.
Unsupervised Learning of Interpretable Dialog Models
However these states need to be handcrafted and annotated in the data.
Finding Dominant User Utterances And System Responses in Conversations
We propose a novel SimCluster algorithm that extends standard K-means algorithm to simultaneously cluster user utterances and agent utterances by taking their adjacency information into account.
