Relational databases play an important role in this Big Data era. Howeve...
The standard task-oriented dialogue pipeline uses intent classification ...
We use paraphrases as a unique source of data to analyze contextualized
...
Many statistical models have high accuracy on test benchmarks, but are n...
A growing number of people engage in online health forums, making it
imp...
Extensive work has argued in favour of paying crowd workers a wage that ...
Natural language processing methods have been applied in a variety of mu...
In this paper, we introduce personalized word embeddings, and examine th...
Word embeddings are usually derived from corpora containing text from ma...
Many NLP applications, such as biomedical data and technical support, ha...
Word embeddings are powerful representations that form the foundation of...
This paper introduces the Eighth Dialog System Technology Challenge. In ...
Diplomacy is a seven-player non-stochastic, non-cooperative game, where
...
Task-oriented dialog systems need to know when a query falls outside the...
Many annotation tools have been developed, covering a wide variety of ta...
We examine a large dialog corpus obtained from the conversation history ...
In a corpus of data, outliers are either errors: mistakes in the data th...
This paper introduces the Seventh Dialog System Technology Challenges (D...
Disentangling conversations mixed together in a single stream of message...
To be informative, an evaluation must measure how well systems generaliz...
Despite the recent popularity of word embedding methods, there is only a...
One weakness of machine-learned NLP models is that they typically perfor...
General treebank analyses are graph structured, but parsers are typicall...
Linguistically diverse datasets are critical for training and evaluating...