| Challenge: | Recent work establishes dataset difficulty and removes annotation artifacts via partial-input baselines. |
| Approach: | They propose to use partial-input baselines to establish dataset difficulty . they show how trivial patterns only visible in the full input can evade partial-output baseline . |
| Outcome: | The proposed model can solve 15% of previously-thought "hard" examples. |
Similar Papers
Partial-input baselines show that NLI models can ignore context, but they don’t. (2022.naacl-main)
Copied to clipboard
| Challenge: | Researchers have shown that many datasets contain statistical biases, or "annotation artifacts" that systems leverage to correctly predict entailment. |
| Approach: | They propose to use edited contexts to examine RoBERTa models' sensitivity to edited context to examine their model's sensitivity. |
| Outcome: | The proposed model can learn to condition on context, despite being trained on artifact-ridden datasets. |
Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN (2022.naacl-main)
Copied to clipboard
| Challenge: | XML-CNN has been a popular research topic in NLP due to its superior performance . however, the increasing complexity brings difficulties to ensure the true architectural progress . |
| Approach: | They propose to re-examine an influential multi-label text classification method . they propose suitable baselines for multi-level text classification tasks . |
| Outcome: | The proposed method performs better than the original model, the authors show . they show that the re-implementation reveals contradictory results to the original work . |
Breaking NLI Systems with Sentences that Require Simple Lexical Inferences (P18-2)
Copied to clipboard
| Challenge: | a new test set shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge. |
| Approach: | They create a new NLI test set that shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge. |
| Outcome: | The new examples are simpler than the SNLI test set, but the state-of-the-art systems perform poorly on it. |
Revisiting Pathologies of Neural Models under Input Reduction (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that modern neural models tend to be miscalibrated. |
| Approach: | They examine why models produce high-confidence predictions on inputs that appear nonsensical to humans . previous work suggested that models fail to assign low probabilities due to model overconfidence . |
| Outcome: | The proposed methods can be extended to reduce the number of examples but with the cost of miscalibration. |
A guide to the dataset explosion in QA, NLI, and commonsense reasoning (2020.coling-tutorials)
Copied to clipboard
| Challenge: | a tutorial aims to provide an up-to-date guide to the recent datasets . the target audience is the NLP practitioners who are lost in dozens of the recent data sets. |
| Approach: | This tutorial provides an up-to-date guide to the recent datasets . it surveys old and new methodological issues with dataset construction . |
| Outcome: | This tutorial aims to provide an up-to-date guide to the recent datasets . it surveys the old and new methodological issues with dataset construction . |
Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks (N18-2)
Copied to clipboard
| Challenge: | Existing work on simple question answering over knowledge graphs involves increasingly complex NN architectures. |
| Approach: | They propose to decompose the problem into entity detection, entity linking, relation prediction, evidence combination and heuristics. |
| Outcome: | The proposed approach outperforms existing models and benchmarks on a simple QA task. |
MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain (2021.acl-short)
Copied to clipboard
| Challenge: | a large number of crowdworker-constructed datasets have been used to conduct natural language inference (NLI) on unstructured, domainspecific texts such as patient notes, pathology reports, and scientific papers. |
| Approach: | They investigate whether MedNLI contains lexical and syntactic annotation artifacts associated with annotation process that allow hypothesis-only classifiers to achieve better-than-random performance. |
| Outcome: | The proposed model outperforms a majority-class baseline model on a physician-annotated dataset with premises extracted from clinical notes. |
Are Neural Topic Models Broken? (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation paradigms are often divorced from real-world use . recent results have challenged the validity of the prevailing model evaluation paradigm . |
| Approach: | They show that neural topic models fare worse in both respects compared to an established classical method. |
| Outcome: | The proposed method outperforms the members of the ensemble in both respects. |
An Empirical Study of Building a Strong Baseline for Constituency Parsing (P18-2)
Copied to clipboard
| Challenge: | Sequence-to-sequence models have been used for natural language generation tasks such as machine translation and summarization. |
| Approach: | They propose to build a strong baseline based on general purpose sequence-to-sequence models for constituency parsing. |
| Outcome: | The proposed model outperforms existing models in natural language generation tasks without any explicit task-specific knowledge or architecture of constituent parsing. |
On the Transferability of Minimal Prediction Preserving Inputs in Question Answering (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work establishes the presence of short, uninterpretable input fragments that yield high confidence and accuracy in neural models. |
| Approach: | They investigate competing hypotheses for the existence of MPPIs in question answering . they discover a perplexing invariance of MPIs to random training seed, model architecture, pretraining, and training domain. |
| Outcome: | The proposed model performance is higher than comparable short queries. |