• 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
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
Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources
TLDR
Investigation of unsupervised techniques for acquiring monolingual sentence-level paraphrases from a corpus of temporally and topically clustered news articles collected from thousands of web-based news sources shows that edit distance data is cleaner and more easily-aligned than the heuristic data. Expand
Automatically Constructing a Corpus of Sentential Paraphrases
TLDR
The creation of the recently-released Microsoft Research Paraphrase Corpus, which contains 5801 sentence pairs, each hand-labeled with a binary judgment as to whether the pair constitutes a paraphrase, is described. 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
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
Monolingual Machine Translation for Paraphrase Generation
TLDR
Human evaluation shows that this SMT system outperforms baseline paraphrase generation techniques and, in a departure from previous work, offers better coverage and scalability than the current best-of-breed paraphrasing approaches. Expand
Correcting ESL Errors Using Phrasal SMT Techniques
TLDR
A pilot study of the use of phrasal Statistical Machine Translation techniques to identify and correct writing errors made by learners of English as a Second Language shows that application of the SMT paradigm can capture errors not well addressed by widely-used proofing tools designed for native speakers. Expand
...
1
2
3
4
5
...