Human-annotated labels and explanations are critical for training explainable NLP models. However, unlike human-annotated labels whose quality is easier to calibrate (e.g., with a majority vote), human-crafted free-form explanations can be quite subjective. Before blindly using them as ground truth to train ML models, a vital question needs to be asked: How do we evaluate a human-annotated explanation’s quality? In this paper, we build on the view that the quality of a human-annotated explanation can be measured based on its helpfulness (or impairment) to the ML models’ performance for the desired NLP tasks for which the annotations were collected. In comparison to the commonly used Simulatability score, we define a new metric that can take into consideration the helpfulness of an explanation for model performance at both fine-tuning and inference. With the help of a unified dataset format, we evaluated the proposed metric on five datasets (e.g., e-SNLI) against two model architectures (T5 and BART), and the results show that our proposed metric can objectively evaluate the quality of human-annotated explanations, while Simulatability falls short.
Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support human annotators mostly focus on the label while neglecting the natural language explanation of a data point. This work proposes a novel AL architecture to support experts’ real-world need for label and explanation annotations in low-resource scenarios. Our AL architecture leverages an explanation-generation model to produce explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a novel data diversity-based AL sampling strategy that benefits from the explanation annotations. Automated and human evaluations demonstrate the effectiveness of incorporating explanations into AL sampling and the improved human annotation efficiency and trustworthiness with our AL architecture. Additional ablation studies illustrate the potential of our AL architecture for transfer learning, generalizability, and integration with large language models (LLMs). While LLMs exhibit exceptional explanation-generation capabilities for relatively simple tasks, their effectiveness in complex real-world tasks warrants further in-depth study.
Entity linking (EL) on short text is crucial for a variety of industrial applications. Compared with general long-text EL, short-text EL poses particular challenges as the limited context restricts the clues one can leverage to disambiguate textual mentions. On the other hand, existing studies mostly focus on black-box neural methods and thus lack interpretability, which is critical to industrial applications in certain areas. In this study, we extend upon LNN-EL, a monolingual short-text EL method based on interpretable first-order logic, by incorporating three sets of multilingual features to enable disambiguating mentions written in languages other than English. More specifically, we use multilingual autoencoding language models (i.e., mBERT) to capture the similarities between the mention with its context and the candidate entity; we use multilingual sequence-to-sequence language models (i.e., mBART and mT5) to represent the likelihood of the text given the candidate entity. We also propose a word-level context feature to capture the semantic evidence of the co-occurring mentions. We evaluate the proposed xLNN-EL approach on the QALD-9-multilingual dataset and demonstrate the cross-linguality of the model and the effectiveness of the features.
Building a natural language processing (NLP) model can be challenging for end-users such as analysts, journalists, investigators, etc., especially given that they will likely apply existing tools out of the box. In this article, we take a closer look at how two complementary approaches, a state-of-the-art human-in-the-loop (HITL) tool and a generative language model (GPT-3) perform out of the box, that is, without fine-tuning. Concretely, we compare these approaches when end-users with little technical background are given pattern extraction tasks from text. We discover that the HITL tool performs with higher precision, while GPT-3 requires some level of engineering in its input prompts as well as post-processing on its output before it can achieve comparable results. Future work in this space should look further into the advantages and disadvantages of the two approaches, HITL and generative language model, as well as into ways to optimally combine them.
We propose a probabilistic approach to select a subset of a target domain representative keywords from a candidate set, contrasting with a context domain. Such a task is crucial for many downstream tasks in natural language processing. To contrast the target domain and the context domain, we adapt the two-component mixture model concept to generate a distribution of candidate keywords. It provides more importance to the distinctive keywords of the target domain than common keywords contrasting with the context domain. To support the representativeness of the selected keywords towards the target domain, we introduce an optimization algorithm for selecting the subset from the generated candidate distribution. We have shown that the optimization algorithm can be efficiently implemented with a near-optimal approximation guarantee. Finally, extensive experiments on multiple domains demonstrate the superiority of our approach over other baselines for the tasks of keyword summary generation and trending keywords selection.
A critical bottleneck in supervised machine learning is the need for large amounts of labeled data which is expensive and time-consuming to obtain. Although a small amount of labeled data cannot be used to train a model, it can be used effectively for the generation of humaninterpretable labeling functions (LFs). These LFs, in turn, have been used to generate a large amount of additional noisy labeled data in a paradigm that is now commonly referred to as data programming. Previous methods of generating LFs do not attempt to use the given labeled data further to train a model, thus missing opportunities for improving performance. Additionally, since the LFs are generated automatically, they are likely to be noisy, and naively aggregating these LFs can lead to suboptimal results. In this work, we propose an LF-based bi-level optimization framework WISDOM to solve these two critical limitations. WISDOM learns a joint model on the (same) labeled dataset used for LF induction along with any unlabeled data in a semi-supervised manner, and more critically, reweighs each LF according to its goodness, influencing its contribution to the semi-supervised loss using a robust bi-level optimization algorithm. We show that WISDOM significantly outperforms prior approaches on several text classification datasets.
Accurate prediction of the stock price volatility, the rate at which the price of a stock increases or decreases over a particular period, is an important problem in finance. Inaccurate prediction of stock price volatility might lead to investment risk and financial loss, while accurate prediction might generate significant returns for investors. Several studies investigated stock price volatility prediction in a regression task by using the transcripts of earning calls (quarterly conference calls held by public companies) with Natural Language Processing (NLP) techniques. Existing studies use the entire transcript and this degrades the performance due to noise caused by irrelevant information that might not have a significant impact on stock price volatility. In order to overcome these limitations, by considering stock price volatility prediction as a classification task, we explore several denoising approaches, ranging from general-purpose approaches to techniques specific to finance to remove the noise, and leverage AutoML systems that enable auto-exploration of a wide variety of models. Our preliminary findings indicate that domain-specific denoising approaches provide better results than general-purpose approaches, moreover AutoML systems provide promising results.
Entity linking (EL) is the task of disambiguating mentions appearing in text by linking them to entities in a knowledge graph, a crucial task for text understanding, question answering or conversational systems. In the special case of short-text EL, which poses additional challenges due to limited context, prior approaches have reached good performance by employing heuristics-based methods or purely neural approaches. Here, we take a different, neuro-symbolic approach that combines the advantages of using interpretable rules based on first-order logic with the performance of neural learning. Even though constrained to use rules, we show that we reach competitive or better performance with SoTA black-box neural approaches. Furthermore, our framework has the benefits of extensibility and transferability. We show that we can easily blend existing rule templates given by a human expert, with multiple types of features (priors, BERT encodings, box embeddings, etc), and even with scores resulting from previous EL methods, thus improving on such methods. As an example of improvement, on the LC-QuAD-1.0 dataset, we show more than 3% increase in F1 score relative to previous SoTA. Finally, we show that the inductive bias offered by using logic results in a set of learned rules that transfers from one dataset to another, sometimes without finetuning, while still having high accuracy.
Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation. Learning the implicit structured representations of entity names without context and external knowledge is particularly challenging. In this paper, we present a novel learning framework that combines active learning and weak supervision to solve this problem. Our experimental evaluation show that this framework enables the learning of high-quality models from merely a dozen or so labeled examples.
Entity resolution (ER) is the task of identifying different representations of the same real-world entities across databases. It is a key step for knowledge base creation and text mining. Recent adaptation of deep learning methods for ER mitigates the need for dataset-specific feature engineering by constructing distributed representations of entity records. While these methods achieve state-of-the-art performance over benchmark data, they require large amounts of labeled data, which are typically unavailable in realistic ER applications. In this paper, we develop a deep learning-based method that targets low-resource settings for ER through a novel combination of transfer learning and active learning. We design an architecture that allows us to learn a transferable model from a high-resource setting to a low-resource one. To further adapt to the target dataset, we incorporate active learning that carefully selects a few informative examples to fine-tune the transferred model. Empirical evaluation demonstrates that our method achieves comparable, if not better, performance compared to state-of-the-art learning-based methods while using an order of magnitude fewer labels.