3260 papers • 126 benchmarks • 313 datasets
Given a short text, finding an appropriate response (Source: http://staff.ustc.edu.cn/~cheneh/paper_pdf/2013/HaoWang.pdf)
(Image credit: Papersgraph)
These leaderboards are used to track progress in short-text-conversation-14
No benchmarks available.
Use these libraries to find short-text-conversation-14 models and implementations
No subtasks available.
Empirical study shows that NRM can generate grammatically correct and content-wise appropriate responses to over 75% of the input text, outperforming state-of-the-arts in the same setting, including retrieval-based and SMT-based models.
A large-scale cleaned Chinese conversation dataset, LCCC, which contains a base version (6.8million dialogues) and a large version (12.0 million dialogues), and pre-training dialogue models which are trained on LCCC-base and LCCC -large respectively.
This paper proposes formalizing short text conversation as a search problem at the first step, and employing state-of-the-art information retrieval techniques to carry out the task, investigating the significance as well as the limitation of the IR approach.
This work tackling addressee and response selection for multi-party conversation, in which systems are expected to select whom they address as well as what they say, and proposes two modeling frameworks.
This work presents bot#1337, a dialog system developed for the 1st NIPS Conversational Intelligence Challenge 2017 (ConvAI), which won the competition with an average dialogue quality score of 2.78 out of 5 given by human evaluators.
A statistical re-weighting method that assigns different weights for the multiple responses of the same query, and trains the common neural generation model with the weights and significantly reduces the number of generated generic responses.
This paper proposed two models for both DQ and ND subtasks which is constructed by hierarchical structure: embedding layer, utterance layer, context layer and memory layer, to hierarchical learn dialogue representation from word level, sentence level, context level to long range context level and outperform other models proposed by other researches.
The experimental results show that the richer semantics are not only able to provide informative and diverse responses, but also increase the overall performance of response quality, including fluency and coherence.
Adding a benchmark result helps the community track progress.