Skip to search formSkip to main contentSkip to account menu

Evaluating Models’ Local Decision Boundaries via Contrast Sets

A more rigorous annotation paradigm for NLP that helps to close systematic gaps in the test data, and recommends that the dataset authors manually perturb the test instances in small but meaningful ways that (typically) change the gold label, creating contrast sets.
View on ACL (opens in a new tab)

AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models

This work introduces AllenNLP Interpret, a flexible framework for interpreting NLP models, which provides interpretation primitives for anyAllenNLP model and task, a suite of built-in interpretation methods, and a library of front-end visualization components.
View on ACL (opens in a new tab)

An Improved Neural Baseline for Temporal Relation Extraction

A new neural system is proposed that achieves about 10% absolute improvement in accuracy over the previous best system (25% error reduction) on two benchmark datasets and could serve as a strong baseline for future research in this area.
View on ACL (opens in a new tab)

Evaluating NLP Models via Contrast Sets

A new annotation paradigm for NLP is proposed that helps to close systematic gaps in the test data, and it is recommended that after a dataset is constructed, the dataset authors manually perturb the test instances in small but meaningful ways that change the gold label, creating contrast sets.
View PDF on arXiv (opens in a new tab)

MedICaT: A Dataset of Medical Images, Captions, and Textual References

Using MedICaT, a dataset of medical images in context, the task of subfigure to subcaption alignment in compound figures is introduced and the utility of inline references in image-text matching is demonstrated.
View on ACL (opens in a new tab)

Obtaining Faithful Interpretations from Compositional Neural Networks

It is found that the intermediate outputs of NMNs differ from the expected output, illustrating that the network structure does not provide a faithful explanation of model behaviour, and particular choices for module architecture are proposed that yield much better faithfulness, at a minimal cost to accuracy.
View on ACL (opens in a new tab)

Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering

This work proposes a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser, and shows that this inductive bias towards tree structures dramatically improves systematic generalization to out-of- distribution examples.
View on MIT Press (opens in a new tab)

ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension

The first component of ReCLIP is a region-scoring method that isolates object proposals via cropping and blurring, and passes them to CLIP, but it is found that CLIP is largely incapable of performing spatial reasoning off-the-shelf.
View on ACL (opens in a new tab)

Improving Generalization in Coreference Resolution via Adversarial Training

This work uses the technique of adversarial gradient-based training to retrain the state-of-the-art system and demonstrates that the retrained system achieves higher performance on the CoNLL dataset (both with and without the change of named entities) and the GAP dataset.
View on ACL (opens in a new tab)

Correlation Clustering with Same-Cluster Queries Bounded by Optimal Cost

This paper presents an efficient algorithm that recovers an exact optimal clustering using at most $2C_{OPT} $ queries and an efficient algorithms that outputs a $2-approximation using at least two queries, both of which are efficient against several known correlation clustering algorithms.
View PDF on arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)