Search Results for author:
Found 11 papers, 5 papers with code
Effective Social Chatbot Strategies for Increasing User Initiative
Many existing chatbots do not effectively support mixed initiative, forcing their users to either respond passively or lead constantly.
Lost in the Middle: How Language Models Use Long Contexts
While recent language models have the ability to take long contexts as input, relatively little is known about how well they use longer context.
Evaluating Human-Language Model Interaction
To evaluate human-LM interaction, we develop a new framework, Human-AI Language-based Interaction Evaluation (HALIE), that defines the components of interactive systems and dimensions to consider when designing evaluation metrics.
When can I Speak? Predicting initiation points for spoken dialogue agents
Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilted conversational flow.
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
We present Chirpy Cardinal, an open-domain social chatbot.
You Only Need One Model for Open-domain Question Answering
Recent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another reader model.
Hindsight: Posterior-guided training of retrievers for improved open-ended generation
Many text generation systems benefit from using a retriever to retrieve passages from a textual knowledge corpus (e. g., Wikipedia) which are then provided as additional context to the generator.
Human-like informative conversations: Better acknowledgements using conditional mutual information
This is because models trained with two contexts - new factual content and conversational history - generate responses that are non-specific w. r. t.
Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations
At the end of the competition, Chirpy Cardinal progressed to the finals with an average rating of 3. 6/5. 0, a median conversation duration of 2 minutes 16 seconds, and a 90th percentile duration of over 12 minutes.
Importance sampling for unbiased on-demand evaluation of knowledge base population
Our first contribution is a new importance-sampling based evaluation which corrects for this bias by annotating a new system{'}s predictions on-demand via crowdsourcing.
Motifs in Temporal Networks
Networks are a fundamental tool for modeling complex systems in a variety of domains including social and communication networks as well as biology and neuroscience.
