We introduce SparCAssist, a general-purpose risk assessment tool for the machine learning models trained for language tasks. It evaluates models' risk by inspecting their behavior on counterfactuals, namely out-of-distribution instances generated based on the given data instance. The counterfactuals are generated by replacing tokens in rational subsequences identified by ExPred, while the replacements are retrieved using HotFlip or the Masked-Language-Model-based algorithms. The main purpose of our system is to help the human annotators to assess the model's risk on deployment. The counterfactual instances generated during the assessment are the by-product and can be used to train more robust NLP models in the future.

Fact-checking on the Web has become the main mechanism through which we detect the credibility of the news or information. Existing fact-checkers verify the authenticity of the information (support or refute the claim) based on secondary sources of information. However, existing approaches do not consider the problem of model updates due to constantly increasing training data due to user feedback. It is therefore important to conduct user studies to correct models' inference biases and improve the model in a life-long learning manner in the future according to the user feedback. In this paper, we present FaxPlainAC, a tool that gathers user feedback on the output of explainable fact-checking models. FaxPlainAC outputs both the model decision, i.e., whether the input fact is true or not, along with the supporting/refuting evidence considered by the model. Additionally, FaxPlainAC allows for accepting user feedback both on the prediction and explanation. Developed in Python, FaxPlainAC is designed as a modular and easily deployable tool. It can be integrated with other downstream tasks and allowing for fact-checking human annotation gathering and life-long learning.

A desirable property of learning systems is to be both effective and interpretable. Towards this goal, recent models have been proposed that first generate an extractive explanation from the input text and then generate a prediction on just the explanation called explain-then-predict models. These models primarily consider the task input as a supervision signal in learning an extractive explanation and do not effectively integrate rationales data as an additional inductive bias to improve task performance. We propose a novel yet simple approach ExPred, which uses multi-task learning in the explanation generation phase effectively trading-off explanation and prediction losses. Next, we use another prediction network on just the extracted explanations for optimizing the task performance. We conduct an extensive evaluation of our approach on three diverse language datasets -- sentiment classification, fact-checking, and question answering -- and find that we substantially outperform existing approaches.

Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is typically sequentially processed and parameters are synchronously updated. Distributed architectures for asynchronous training that have been proposed either focus on scaling vocabulary sizes and dimensionality or suffer from expensive synchronization latencies. In this paper, we propose a scalable approach to train word embeddings by partitioning the input space instead in order to scale to massive text corpora while not sacrificing the performance of the embeddings. Our training procedure does not involve any parameter synchronization except a final sub-model merge phase that typically executes in a few minutes. Our distributed training scales seamlessly to large corpus sizes and we get comparable and sometimes even up to 45% performance improvement in a variety of NLP benchmarks using models trained by our distributed procedure which requires $1/10$ of the time taken by the baseline approach. Finally we also show that we are robust to missing words in sub-models and are able to effectively reconstruct word representations.

Complex machine learning models are deployed in several critical domains including healthcare and autonomous vehicles nowadays, albeit as functional blackboxes. Consequently, there has been a recent surge in interpreting decisions of such complex models in order to explain their actions to humans. Models which correspond to human interpretation of a task are more desirable in certain contexts and can help attribute liability, build trust, expose biases and in turn build better models. It is therefore crucial to understand how and which models conform to human understanding of tasks. In this paper we present a large-scale crowdsourcing study that reveals and quantifies the dissonance between human and machine understanding, through the lens of an image classification task. In particular, we seek to answer the following questions: Which (well performing) complex ML models are closer to humans in their use of features to make accurate predictions? How does task difficulty affect the feature selection capability of machines in comparison to humans? Are humans consistently better at selecting features that make image recognition more accurate? Our findings have important implications on human-machine collaboration, considering that a long term goal in the field of artificial intelligence is to make machines capable of learning and reasoning like humans.