REVIEW 3 cited by
A Simple and Effective Approach to the Story Cloze Test
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
In the Story Cloze Test, a system is presented with a 4-sentence prompt to a story, and must determine which one of two potential endings is the 'right' ending to the story. Previous work has shown that ignoring the training set and training a model on the validation set can achieve high accuracy on this task due to stylistic differences between the story endings in the training set and validation and test sets. Following this approach, we present a simpler fully-neural approach to the Story Cloze Test using skip-thought embeddings of the stories in a feed-forward network that achieves close to state-of-the-art performance on this task without any feature engineering. We also find that considering just the last sentence of the prompt instead of the whole prompt yields higher accuracy with our approach.
Forward citations
Cited by 3 Pith papers
-
On saturated triangulation-free convex geometric graphs
Saturated triangulation-free convex geometric graphs can have as few as O(n log n) edges, and every edge count from that bound up to the maximum is achievable.
-
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
MesaNet uses conjugate-gradient-optimal test-time regression in a chunkwise-parallelizable recurrent layer, achieving strong language modeling and benchmark performance at up to 1B scale.
-
Reinforcement Learning with Rubric Anchors
Rubric-based rewards extend reinforcement learning to open-ended text generation, yielding a 30B model that outperforms a 671B model on humanities-style benchmarks.
Discussion (0). Continue with ORCID to comment.