Papers with BiDAF

6 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations