Papers

Learn more about AI2's Lasting Impact Award
AI2 Irvine
All Years
Viewing 11-20 of 28 papers
  • Obtaining Faithful Interpretations from Compositional Neural Networks

    Sanjay Subramanian, Ben Bogin, Nitish Gupta, Tomer Wolfson, Sameer Singh, Jonathan Berant, Matt Gardner ACL2020
    Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional structure of the problem in the network architecture. However, prior work implicitly assumed that the structure of the network modules, describing the abstract reasoning process, provides a faithful explanation of the model's reasoning; that is, that all modules perform their intended behaviour. In this work, we propose and conduct a systematic evaluation of the intermediate outputs of NMNs on NLVR2 and DROP, two datasets which require composing multiple reasoning steps. We find that the intermediate outputs differ from the expected output, illustrating that the network structure does not provide a faithful explanation of model behaviour. To remedy that, we train the model with auxiliary supervision and propose particular choices for module architecture that yield much better faithfulness, at a minimal cost to accuracy.
  • QuASE: Question-Answer Driven Sentence Encoding.

    Hangfeng He, Qiang Ning, Dan RothACL2020
    Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, {\em can we use QAMR (Michael et al., 2017) to improve named entity recognition?} We suggest that simply further pre-training BERT is often not the best option, and propose the {\em question-answer driven sentence encoding (QuASE)} framework. QuASE learns representations from QA data, using BERT or other state-of-the-art contextual language models. In particular, we observe the need to distinguish between two types of sentence encodings, depending on whether the target task is a single- or multi-sentence input; in both cases, the resulting encoding is shown to be an easy-to-use plugin for many downstream tasks. This work may point out an alternative way to supervise NLP tasks.
  • Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering

    Ben Bogin, Sanjay Subramanian, Matt Gardner, Jonathan BerantTACL2020
    Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-ofthe-art models in grounded question answering often do not explicitly perform decomposition, leading to difficulties in generalization to out-of-distribution examples. In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. Our model effectively induces latent trees, driven by end-to-end (the answer) supervision only. We show that this inductive bias towards tree structures dramatically improves systematic generalization to out-of-distribution examples compared to strong baselines on an arithmetic expressions benchmark as well as on CLOSURE, a dataset that focuses on systematic generalization of models for grounded question answering. On this challenging dataset, our model reaches an accuracy of 92.8%, significantly higher than prior models that almost perfectly solve the task on a random, in-distribution split.
  • Analyzing Compositionality in Visual Question Answering

    Sanjay Subramanian, Sameer Singh, Matt GardnerNeurIPS • ViGIL Workshop2019
    Since the release of the original Visual Question Answering (VQA) dataset, several newer datasets for visual reasoning have been introduced, often with the express intent of requiring systems to perform compositional reasoning. Recently, transformer models pretrained on large amounts of images and associated text have been shown to perform much better than simple baselines on such compositional reasoning datasets as NLVR2 and GQA. In this paper, we analyze the performance of one of these models, LXMERT, on these two datasets. We show that despite the model’s strong quantitative results, it may not be performing compositional reasoning because it does not need many relational cues to achieve this performance and more generally uses relatively little linguistic information. Our analysis utilizes experiments with relational linguistic cues removed, the input reduction technique, and a syntactic probe.
  • Evaluating Question Answering Evaluation

    Anthony Chen, Gabriel Stanovsky, Sameer Singh, Matt GardnerEMNLP • MRQA Workshop2019
    As the complexity of question answering (QA) datasets evolve, moving away from restricted formats like span extraction and multiple-choice (MC) to free-form answer generation, it is imperative to understand how well current metrics perform in evaluating QA. This is especially important as existing metrics (BLEU, ROUGE, METEOR, and F1) are computed using n-gram similarity and have a number of well-known drawbacks. In this work, we study the suitability of existing metrics in QA. For generative QA, we show that while current metrics do well on existing datasets, converting multiple-choice datasets into free-response datasets is challenging for current metrics. We also look at span-based QA, where F1 is a reasonable metric. We show that F1 may not be suitable for all extractive QA tasks depending on the answer types. Our study suggests that while current metrics may be suitable for existing QA datasets, they limit the complexity of QA datasets that can be created. This is especially true in the context of free-form QA, where we would like our models to be able to generate more complex and abstractive answers, thus necessitating new metrics that go beyond n-gram based matching. As a step towards a better QA metric, we explore using BERTScore, a recently proposed metric for evaluating translation, for QA. We find that although it fails to provide stronger correlation with human judgements, future work focused on tailoring a BERT-based metric to QA evaluation may prove fruitful.
  • On Making Reading Comprehension More Comprehensive

    Matt Gardner, Jonathan Berant, Hannaneh Hajishirzi, Alon Talmor, Sewon MinEMNLP • MRQA Workshop2019
    Machine reading comprehension, the task of evaluating a machine’s ability to comprehend a passage of text, has seen a surge in popularity in recent years. There are many datasets that are targeted at reading comprehension, and many systems that perform as well as humans on some of these datasets. Despite all of this interest, there is no work that systematically defines what reading comprehension is. In this work, we justify a question answering approach to reading comprehension and describe the various kinds of questions one might use to more fully test a system’s comprehension of a passage, moving beyond questions that only probe local predicate-argument structures. The main pitfall of this approach is that questions can easily have surface cues or other biases that allow a model to shortcut the intended reasoning process. We discuss ways proposed in current literature to mitigate these shortcuts, and we conclude with recommendations for future dataset collection efforts.
  • ORB: An Open Reading Benchmark for Comprehensive Evaluation of Machine Reading Comprehension

    Dheeru Dua, Ananth Gottumukkala, Alon Talmor, Sameer Singh, Matt GardnerEMNLP • MRQA Workshop2019
    Reading comprehension is one of the crucial tasks for furthering research in natural language understanding. A lot of diverse reading comprehension datasets have recently been introduced to study various phenomena in natural language, ranging from simple paraphrase matching and entity typing to entity tracking and understanding the implications of the context. Given the availability of many such datasets, comprehensive and reliable evaluation is tedious and time-consuming for researchers working on this problem. We present an evaluation server, ORB, that reports performance on seven diverse reading comprehension datasets, encouraging and facilitating testing a single model’s capability in understanding a wide variety of reading phenomena. The evaluation server places no restrictions on how models are trained, so it is a suitable test bed for exploring training paradigms and representation learning for general reading facility. As more suitable datasets are released, they will be added to the evaluation server. We also collect and include synthetic augmentations for these datasets, testing how well models can handle out-of-domain questions.
  • AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models

    Eric Wallace, Jens Tuyls, Junlin Wang, Sanjay Subramanian, Matthew Gardner, Sameer SinghEMNLP2019
    Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate this opacity by providing explanations for specific model predictions. Unfortunately, existing interpretation codebases make it difficult to apply these methods to new models and tasks, which hinders adoption for practitioners and burdens interpretability researchers. We introduce AllenNLP Interpret, a flexible framework for interpreting NLP models. The toolkit provides interpretation primitives (e.g., input gradients) for any AllenNLP model and task, a suite of built-in interpretation methods, and a library of front-end visualization components. We demonstrate the toolkit's flexibility and utility by implementing live demos for five interpretation methods (e.g., saliency maps and adversarial attacks) on a variety of models and tasks (e.g., masked language modeling using BERT and reading comprehension using BiDAF). ). These demos, alongside our code and tutorials, are available at https://allennlp. org/interpret.
  • Do NLP Models Know Numbers? Probing Numeracy in Embeddings

    Eric Wallace, Yizhong Wang, Sujian Li, Sameer Singh, Matt GardnerEMNLP2019
    The ability to understand and work with numbers (numeracy) is critical for many complex reasoning tasks. Currently, most NLP models treat numbers in text in the same way as other tokens---they embed them as distributed vectors. Is this enough to capture numeracy? We begin by investigating the numerical reasoning capabilities of a state-of-the-art question answering model on the DROP dataset. We find this model excels on questions that require numerical reasoning, i.e., it already captures numeracy. To understand how this capability emerges, we probe token embedding methods (e.g., BERT, GloVe) on synthetic list maximum, number decoding, and addition tasks. A surprising degree of numeracy is naturally present in standard embeddings. For example, GloVe and word2vec accurately encode magnitude for numbers up to 1,000. Furthermore, character-level embeddings are even more precise---ELMo captures numeracy the best for all pre-trained methods---but BERT, which uses sub-word units, is less exact.
  • Universal Adversarial Triggers for Attacking and Analyzing NLP

    Eric Wallace, Shi Feng, Nikhil Kandpal, Matthew Gardner, Sameer Singh EMNLP2019
    dversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a model to produce a specific prediction when concatenated to any input from a dataset. We propose a gradient-guided search over tokens which finds short trigger sequences (e.g., one word for classification and four words for language modeling) that successfully trigger the target prediction. For example, triggers cause SNLI entailment accuracy to drop from 89.94% to 0.55%, 72% of "why" questions in SQuAD to be answered "to kill american people", and the GPT-2 language model to spew racist output even when conditioned on non-racial contexts. Furthermore, although the triggers are optimized using white-box access to a specific model, they transfer to other models for all tasks we consider. Finally, since triggers are input-agnostic, they provide an analysis of global model behavior. For instance, they confirm that SNLI models exploit dataset biases and help to diagnose heuristics learned by reading comprehension models.
AI2 Irvine
All Years