Pre-trained language models have recently shown that training on large corpora using the language modeling objective enables few-shot and zero-shot capabilities on a variety of NLP tasks, including commonsense reasoning tasks. This is achieved using text interactions with the model, usually by posing the task as a natural language text completion problem. While using language model probabilities to obtain task specific scores has been generally useful, it often requires task-specific heuristics such as length normalization, or probability calibration. In this work, we consider the question answering format, where we need to choose from a set of (free-form) textual choices of unspecified lengths given a context. We present ALC (Answer-Level Calibration), where our main suggestion is to model context-independent biases in terms of the probability of a choice without the associated context and to subsequently remove it using an unsupervised estimate of similarity with the full context. We show that our unsupervised answer-level calibration consistently improves over or is competitive with baselines using standard evaluation metrics on a variety of tasks including commonsense reasoning tasks. Further, we show that popular datasets potentially favor models biased towards easy cues which are available independent of the context. We analyze such biases using an associated F1-score. Our analysis indicates that answer-level calibration is able to remove such biases and leads to a more robust measure of model capability.

Many existing approaches for interpreting text classification models focus on providing importance scores for parts of the input text, such as words, but without a way to test or improve the interpretation method itself. This has the effect of compounding the problem of understanding or building trust in the model, with the interpretation method itself adding to the opacity of the model. Further, importance scores on individual examples are usually not enough to provide a sufficient picture of model behavior. To address these concerns, we propose MOXIE (MOdeling conteXt-sensitive InfluencE of words) with an aim to enable a richer interface for a user to interact with the model being interpreted and to produce testable predictions. In particular, we aim to make predictions for importance scores, counterfactuals and learned biases with MOXIE. In addition, with a global learning objective, MOXIE provides a clear path for testing and improving itself. We evaluate the reliability and efficiency of MOXIE on the task of sentiment analysis.

The recent growth in the popularity and success of deep learning models on NLP classification tasks has accompanied the need for generating some form of natural language explanation of the predicted labels. Such generated natural language (NL) explanations are expected to be faithful, i.e., they should correlate well with the model’s internal decision making. In this work, we focus on the task of natural language inference (NLI) and address the following question: can we build NLI systems which produce labels with high accuracy, while also generating faithful explanations of its decisions? We propose Natural-language Inference over Label-specific Explanations (NILE), a novel NLI method which utilizes auto-generated label-specific NL explanations to produce labels along with its faithful explanation. We demonstrate NILE’s effectiveness over previously reported methods through automated and human evaluation of the produced labels and explanations. Our evaluation of NILE also supports the claim that accurate systems capable of providing testable explanations of their decisions can be designed. We discuss the faithfulness of NILE’s explanations in terms of sensitivity of the decisions to the corresponding explanations. We argue that explicit evaluation of faithfulness, in addition to label and explanation accuracy, is an important step in evaluating model’s explanations. Further, we demonstrate that task-specific probes are necessary to establish such sensitivity.

Word Sense Disambiguation (WSD) is a long-standing but open problem in Natural Language Processing (NLP). WSD corpora are typically small in size, owing to an expensive annotation process. Current supervised WSD methods treat senses as discrete labels and also resort to predicting the Most-Frequent-Sense (MFS) for words unseen during training. This leads to poor performance on rare and unseen senses. To overcome this challenge, we propose Extended WSD Incorporating Sense Embeddings (EWISE), a supervised model to perform WSD by predicting over a continuous sense embedding space as opposed to a discrete label space. This allows EWISE to generalize over both seen and unseen senses, thus achieving generalized zero-shot learning. To obtain target sense embeddings, EWISE utilizes sense definitions. EWISE learns a novel sentence encoder for sense definitions by using WordNet relations and also ConvE, a recently proposed knowledge graph embedding method. We also compare EWISE against other sentence encoders pretrained on large corpora to generate definition embeddings. EWISE achieves new state-of-the-art WSD performance.

In this paper, we establish the effectiveness of using hard negatives, coupled with a siamese network and a suitable loss function, for the tasks of answer selection and answer triggering. We show that the choice of sampling strategy is key for achieving improved performance on these tasks. Evaluating on recent answer selection datasets - InsuranceQA, SelQA, and an internal QA dataset, we show that using hard negatives with relatively simple model architectures (bag of words and LSTM-CNN) drives significant performance gains. On InsuranceQA, this strategy alone improves over previously reported results by a minimum of 1.6 points in P@1. Using hard negatives with a Transformer encoder provides a further improvement of 2.3 points. Further, we propose to use quadruplet loss for answer triggering, with the aim of producing globally meaningful similarity scores. We show that quadruplet loss function coupled with the selection of hard negatives enables bag-of-words models to improve F1 score by 2.3 points over previous baselines, on SelQA answer triggering dataset. Our results provide key insights into answer selection and answer triggering tasks.