Papers with BiDAF
AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models (D19-3)
Copied to clipboard
| Challenge: | Existing interpretation codebases make it difficult to apply these methods to new models and tasks. |
| Approach: | They propose a framework for interpreting NLP models that provides explanations for specific models. |
| Outcome: | The proposed framework provides interpretation primitives for any AllenNLP model and task, a suite of built-in interpretation methods, and a library of front-end visualization components. |
MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods to predict the start and end positions of answer spans generate two probability vectors. |
| Approach: | They propose a method that extends the probability vector to a probability matrix. |
| Outcome: | The proposed method improves on SQuAD 1.1 and three other question answering benchmarks. |
Look at the First Sentence: Position Bias in Question Answering (2020.emnlp-main)
Copied to clipboard
| Challenge: | Extractive question answering models are trained to predict start and end positions of answers . recent QA models outperform humans in some datasets due to their simplicity and effectiveness. |
| Approach: | They propose to use prior distribution of answer positions as a bias model to reduce position bias. |
| Outcome: | The proposed model outperforms BERT from 37.48% to 81.64% when trained on a biased SQUAD dataset. |
Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering (D19-1)
Copied to clipboard
| Challenge: | Existing QG models suffer from a “semantic drift” problem, i.e., the semantics of the model-generated question drifts away from the given context and answer. |
| Approach: | They propose two semantics-enhanced rewards obtained from downstream question paraphrasing and question answering tasks to regularize the QG model to generate semantically valid questions. |
| Outcome: | The proposed method achieves state-of-the-art performance w.r.t. traditional evaluation metrics and performs best on QA-based evaluation metrics. |
pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference (N19-1)
Copied to clipboard
| Challenge: | Existing inference models that rely heavily on unsupervised single-word embeddings struggle to learn implied relationships between pairs of words. |
| Approach: | They propose to use word embeddings to learn and use background knowledge about implied relationships between words that are crucial for cross-sentence inference problems. |
| Outcome: | The proposed models gain 2.7% on the recently released SQuAD 2.0 and 1.3% on MultiNLI, and 8.8% on the adversarial SQu AD datasets. |
ScholarlyRead: A New Dataset for Scientific Article Reading Comprehension (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing studies on MRC on scholarly articles have focused on general domain datasets of news articles and elementary school-level storybooks. |
| Approach: | They propose to generate automatic questions from span-of-word-based scholarly articles’ Reading Comprehension dataset with approximately 10K manually checked passage-question-answer instances. |
| Outcome: | The proposed model yields the F1 score of 37.31% and is useful for building Question-Answering (QA) systems on scientific articles. |