Learning Corresponded Rationales for Text Matching

8 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Finding Generalizable Evidence by Learning to Convince Q&A Models (2019, methodology): “Prior work uses similar methods to explain what a specific model has learned (Lei et al., 2016; Li et al., 2016; Yu et al., 2019).”
EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction (2019, methodology): “Such methods are speciﬁc to text data select and rationales, i.e. parts of text, on which the model bases its prediction, see [15, 27] and very recently [5].”
A Game Theoretic Approach to Class-wise Selective Rationalization (2019, methodology): “The ﬁrst class of method is to explicitly introduce a generator that learns to select important subsets of inputs as explanations [12, 19, 21, 30, 31], which often comes with some information-theoretic properties.”
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control (2019, background): “Therefore the selective rationalization approach is easier to be adapted to new applications, such as question answering (Yu et al., 2018), image classification (Chen et al.”