• Publications
  • Influence
A Diversity-Promoting Objective Function for Neural Conversation Models
TLDR
This work proposes using Maximum Mutual Information (MMI) as the objective function in neural models, and demonstrates that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations. Expand
Deep Reinforcement Learning for Dialogue Generation
TLDR
This work simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, non-repetitive turns, coherence, and ease of answering. Expand
A Persona-Based Neural Conversation Model
TLDR
This work presents persona-based models for handling the issue of speaker consistency in neural response generation that yield qualitative performance improvements in both perplexity and BLEU scores over baseline sequence-to-sequence models. Expand
DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation
TLDR
It is shown that conversational systems that leverage DialoGPT generate more relevant, contentful and context-consistent responses than strong baseline systems. Expand
What’s in a translation rule?
TLDR
The theory is used to introduce a linear algorithm that can be used to derive from word-aligned, parallel corpora the minimal set of syntactically motivated transformation rules that explain human translation data. Expand
Discourse Segmentation of Multi-Party Conversation
TLDR
A domain-independent topic segmentation algorithm for multi-party speech that combines knowledge about content using a text-based algorithm as a feature and about form using linguistic and acoustic cues about topic shifts extracted from speech. Expand
Scalable Inference and Training of Context-Rich Syntactic Translation Models
TLDR
This paper takes the framework for acquiring multi-level syntactic translation rules of (Galley et al., 2004) from aligned tree-string pairs, and presents two main extensions of their approach: instead of merely computing a single derivation that minimally explains a sentence pair, a large number of derivations that include contextually richer rules, and account for multiple interpretations of unaligned words. Expand
A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
TLDR
A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances. Expand
A Knowledge-Grounded Neural Conversation Model
TLDR
A novel, fully data-driven, and knowledge-grounded neural conversation model aimed at producing more contentful responses that generalizes the widely-used Sequence-to-Sequence (seq2seq) approach by conditioning responses on both conversation history and external “facts”, allowing the model to be versatile and applicable in an open-domain setting. Expand
Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
TLDR
Adversarial Information Maximization (AIM), an adversarial learning framework that addresses informativeness and diversity, and explicitly optimizes a variational lower bound on pairwise mutual information between query and response. Expand
...
1
2
3
4
5
...