• Corpus ID: 207848054

Towards Domain Adaptation from Limited Data for Question Answering Using Deep Neural Networks

@article{Hazen2019TowardsDA,
  title={Towards Domain Adaptation from Limited Data for Question Answering Using Deep Neural Networks},
  author={Timothy J. Hazen and Shehzaad Dhuliawala and Daniel Boies},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.02655}
}
This paper explores domain adaptation for enabling question answering (QA) systems to answer questions posed against documents in new specialized domains. Current QA systems using deep neural network (DNN) technology have proven effective for answering general purpose factoid-style questions. However, current general purpose DNN models tend to be ineffective for use in new specialized domains. This paper explores the effectiveness of transfer learning techniques for this problem. In experiments… 

Figures and Tables from this paper

Contrastive Domain Adaptation for Question Answering using Limited Text Corpora

TLDR
This paper proposes a novel framework for domain adaptation called contrastive domain adaptation for QA (CAQA), which combines techniques from question generation and domain-invariant learning to answer out-of-domain questions in settings with limited text corpora.

Synthetic Question Value Estimation for Domain Adaptation of Question Answering

TLDR
This paper introduces a novel idea of training a question value estimator (QVE) that directly estimates the usefulness of synthetic questions for improving the target-domain QA performance and shows that the synthetic questions selected by QVE can help achieve better target- domain QAperformance, in comparison with existing techniques.

Domain Adaptation for Question Answering via Question Classification

TLDR
The effectiveness of the proposed QC4QA with consistent improvements against the state-of-the-art baselines on multiple datasets is demonstrated.

Adversarial Training Methods for Cross-Domain Question Answering

  • Computer Science
  • 2021
TLDR
The best variant combines two different and complementary approaches of adversarial training on a DistilBERT baseline, achieving >3% F1-score improvement over the regular fine-tuning process, outperforming several other adversarial and energybased approaches.

CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering

TLDR
This work proposes a simple yet effective framework, CliniQG4QA, which leverages question generation (QG) to synthesize QA pairs on new clinical contexts and boosts QA models without requiring manual annotations and introduces a seq2seq-based question phrase prediction (QPP) module that can be used together with most existing QG models to diversify the generation.

Importance Weighting for Robust QA

  • Computer Science
  • 2021
TLDR
This work addresses adaptation to new specialized domains with very little training data for MRC-QA by proposing two features for importance weighting that are applicable for an unsupervised setting, and presenting preliminary results comparing importanceWeighting with transfer learning.

Know When To Abstain: Calibrating Question Answering System under Domain Shift

TLDR
This project focuses on confidence modeling of QA systems under domain shift, and proposes a systematic approach to calibrate the model by augmenting it with a calibrator trained on a small subset of out-of-domain examples.

On the Universality of Deep Contextual Language Models

TLDR
This work explores the notion of ‘Universality’ by identifying seven dimensions across which a universal model should be able to scale, that is, perform equally well or reasonably well, to be useful across diverse settings.

Velocidapter: Task-oriented Dialogue Comprehension Modeling Pairing Synthetic Text Generation with Domain Adaptation

TLDR
A synthetic dialogue generation framework, Velocidapter, which addresses the corpus availability problem for dialogue comprehension and shows significant improvements using both the transformer-based BERTBase and BiDAF as base models.

Retrieving Knowledge in Tabular Form from Free-form Natural Language

  • Computer Science
  • 2021
TLDR
An extension to the architecture of bidirectional encoder representations from transformers is proposed and an improvement in machine reading comprehension compared with that in tables showed that language models that are efficient in knowledge retrieval can also fine-tune tasks efficiently.

References

SHOWING 1-10 OF 28 REFERENCES

Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering

TLDR
This paper first introduces syntactic information to help encode questions and then view and model different types of questions and the information shared among them as an adaptation task and proposed adaptation models for them.

Semi-Supervised QA with Generative Domain-Adaptive Nets

TLDR
A novel training framework for semi-supervised question answering is proposed, the Generative Domain-Adaptive Nets, which combines a generative model to generate questions based on the unlabeled text, and combines model- generated questions with human-generated questions for training question answering models.

Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering

TLDR
A stage-wise approach to fine tuning BERT on multiple datasets, starting with data that is "furthest" from the test data and ending with the "closest" data, is applied.

Adversarial Domain Adaptation for Machine Reading Comprehension

TLDR
An Adversarial Domain Adaptation framework for Machine Reading Comprehension (MRC), where pseudo questions are first generated for unlabeled passages in the target domain, and then a domain classifier is incorporated into an MRC model to predict which domain a given passage-question pair comes from.

Multi-Task Deep Neural Networks for Natural Language Understanding

TLDR
A Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks that allows domain adaptation with substantially fewer in-domain labels than the pre-trained BERT representations.

Universal Language Model Fine-tuning for Text Classification

TLDR
This work proposes Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduces techniques that are key for fine- Tuning a language model.

SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine

TLDR
It is shown that there is a meaningful gap between the human and machine performances, which suggests that the proposed dataset could well serve as a benchmark for question-answering.

emrQA: A Large Corpus for Question Answering on Electronic Medical Records

TLDR
A novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks is proposed and an instance of this methodology is demonstrated in generating a large- scale QA dataset for electronic medical records.

NewsQA: A Machine Comprehension Dataset

TLDR
NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs, is presented and analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment.

Overview of the MEDIQA 2019 Shared Task on Textual Inference, Question Entailment and Question Answering

TLDR
The shared task is motivated by a need to develop relevant methods, techniques and gold standards for inference and entailment in the medical domain, and their application to improve domain specific information retrieval and question answering systems.