To build robust question answering systems, we need the ability to verify whether answers to questions are truly correct, not just “good enough” in the context of imperfect QA datasets. We explore the use of natural language inference (NLI) as a way to achieve this goal, as NLI inherently requires the premise (document context) to contain all necessary information to support the hypothesis (proposed answer to the question). We leverage large pre-trained models and recent prior datasets to construct powerful question conversion and decontextualization modules, which can reformulate QA instances as premise-hypothesis pairs with very high reliability. Then, by combining standard NLI datasets with NLI examples automatically derived from QA training data, we can train NLI models to evaluate QA models’ proposed answers. We show that our approach improves the confidence estimation of a QA model across different domains, evaluated in a selective QA setting. Careful manual analysis over the predictions of our NLI model shows that it can further identify cases where the QA model produces the right answer for the wrong reason, i.e., when the answer sentence cannot address all aspects of the question.
more »
« less
Repurposing Entailment for Multi-Hop Question Answering Tasks
Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with \textit{multiple} sentences, it remains unclear how best to utilize entailment models pre-trained on large scale datasets such as SNLI, which are based on sentence pairs. We introduce Multee, a general architecture that can effectively use entailment models for multi-hop QA tasks. Multee uses (i) a local module that helps locate important sentences, thereby avoiding distracting information, and (ii) a global module that aggregates information by effectively incorporating importance weights. Importantly, we show that both modules can use entailment functions pre-trained on a large scale NLI datasets. We evaluate performance on MultiRC and OpenBookQA, two multihop QA datasets. When using an entailment function pre-trained on NLI datasets, Multee outperforms QA models trained only on the target QA datasets and the OpenAI transformer models.
more »
« less
- Award ID(s):
- 1815358
- PAR ID:
- 10098274
- Date Published:
- Journal Name:
- North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies
- Volume:
- 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Commonsense question answering has primarily been tackled through supervised transfer learning, where a language model pre-trained on large amounts of data is used as the starting point. While successful, the approach requires large amounts of labeled question-answer pairs, with increasingly larger amounts of data required as the complexity of scenarios or tasks such as commonsense QA increases. In this paper, we hypothesize that large-scale pre-training of language models encodes the necessary commonsense knowledge to answer common questions in context without labeled data. We propose a novel framework called Iterative Self Distillation for QA (ISD-QA), which extracts the “dark knowledge” encoded during largescale pre-training of language models to provide supervision for commonsense question answering. We show that the approach can be used to train common neural QA models for commonsense question answering by distilling knowledge from language models in an unsupervised manner. With no bells and whistles, we achieve an average of 68% of the performance of fully supervised QA models while requiring no labeled training data. Extensive experiments on three public benchmarks (OpenBookQA, HellaSWAG, and CommonsenseQA) show the effectiveness of the proposed approach.more » « less
-
Clinical question answering (QA) aims to automatically answer questions from medical professionals based on clinical texts. Studies show that neural QA models trained on one corpus may not generalize well to new clinical texts from a different institute or a different patient group, where large-scale QA pairs are not readily available for model retraining. To address this challenge, we propose 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. In order to generate diverse types of questions that are essential for training QA models, we further introduce a seq2seq-based question phrase prediction (QPP) module that can be used together with most existing QG models to diversify the generation. Our comprehensive experiment results show that the QA corpus generated by our framework can improve QA models on the new contexts (up to 8% absolute gain in terms of Exact Match), and that the QPP module plays a crucial role in achieving the gain.more » « less
-
Knowledge graph reasoning plays a pivotal role in many real-world applications, such as network alignment, computational fact-checking, recommendation, and many more. Among these applications, knowledge graph completion (KGC) and multi-hop question answering over knowledge graph (Multi-hop KGQA) are two representative reasoning tasks. In the vast majority of the existing works, the two tasks are considered separately with different models or algorithms. However, we envision that KGC and Multi-hop KGQA are closely related to each other. Therefore, the two tasks will benefit from each other if they are approached adequately. In this work, we propose a neural model named BiNet to jointly handle KGC and multi-hop KGQA, and formulate it as a multi-task learning problem. Specifically, our proposed model leverages a shared embedding space and an answer scoring module, which allows the two tasks to automatically share latent features and learn the interactions between natural language question decoder and answer scoring module. Compared to the existing methods, the proposed BiNet model addresses both multi-hop KGQA and KGC tasks simultaneously with superior performance. Experiment results show that BiNet outperforms state-of-the-art methods on a wide range of KGQA and KGC benchmark datasets.more » « less
-
Gradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their simplicity, flexibility, and most importantly, the fact that they directly reflect the model internals. In this paper, however, we demonstrate that the gradients of a model are easily manipulable, and thus bring into question the reliability of gradient-based analyses. In particular, we merge the layers of a target model with a Facade Model that overwhelms the gradients without affecting the predictions. This Facade Model can be trained to have gradients that are misleading and irrelevant to the task, such as focusing only on the stop words in the input. On a variety of NLP tasks (sentiment analysis, NLI, and QA), we show that the merged model effectively fools different analysis tools: saliency maps differ significantly from the original model’s, input reduction keeps more irrelevant input tokens, and adversarial perturbations identify unimportant tokens as being highly important.more » « less