Coreference resolution is an important part of natural language processing used in machine translation, semantic search, and various other information retrieval and understanding systems. One of the challenges in this field is an evaluation of resolution approaches. There are many different metrics proposed, but most of them rely on certain assumptions, like equivalence between different mentions of the same discourse-world entity, and do not account for overrepresentation of certain types of coreferences present in the evaluation data. In this paper, a new coreference evaluation strategy that focuses on linguistic and semantic information is presented that can address some of these shortcomings. Evaluation model was developed in the broader context of developing coreference resolution capabilities for Lithuanian language; therefore, the experiment was also carried out using Lithuanian language resources, but the proposed evaluation strategy is not language-dependent.

The recent progress of deep learning techniques has produced models capable of achieving high scores on traditional Natural Language Inference (NLI) datasets. To understand the generalization limits of these powerful models, an increasing number of adversarial evaluation schemes have appeared. These works use a similar evaluation method: they construct a new NLI test set based on sentences with known logic and semantic properties (the adversarial set), train a model on a benchmark NLI dataset, and evaluate it in the new set. Poor performance on the adversarial set is identified as a model limitation. The problem with this evaluation procedure is that it may only indicate a sampling problem. A machine learning model can perform poorly on a new test set because the text patterns presented in the adversarial set are not well represented in the training sample. To address this problem, we present a new evaluation method, the Invariance under Equivalence test (IE test). The IE test trains a model with sufficient adversarial examples and checks the model’s performance on two equivalent datasets. As a case study, we apply the IE test to the state-of-the-art NLI models using synonym substitution as the form of adversarial examples. The experiment shows that, despite their high predictive power, these models usually produce different inference outputs for equivalent inputs, and, more importantly, this deficiency cannot be solved by adding adversarial observations in the training data.

Named entity recognition (NER) aims to identify mentions of named entities in an unstructured text and classify them into predefined named entity classes. While deep learning-based pre-trained language models help to achieve good predictive performances in NER, many domain-specific NER applications still call for a substantial amount of labeled data. Active learning (AL), a general framework for the label acquisition problem, has been used for NER tasks to minimize the annotation cost without sacrificing model performance. However, the heavily imbalanced class distribution of tokens introduces challenges in designing effective AL querying methods for NER. We propose several AL sentence query evaluation functions that pay more attention to potential positive tokens and evaluate these proposed functions with both sentence-based and token-based cost evaluation strategies. We also propose a better data-driven normalization approach to penalize sentences that are too long or too short. Our experiments on three datasets from different domains reveal that the proposed approach reduces the number of annotated tokens while achieving better or comparable prediction performance with conventional methods.

This article reports on designing and implementing a multiclass sentiment classification approach to handle the imbalanced class distribution of Arabic documents. The proposed approach, sentiment classification of Arabic documents (SCArD), combines the advantages of a clustering-based undersampling (CBUS) method and an ensemble learning model to aid machine learning (ML) classifiers in building accurate models against highly imbalanced datasets. The CBUS method applies two standard clustering algorithms: K-means and expectation–maximization, to balance the ratio between the major and the minor classes by decreasing the number of the major class instances and maintaining the number of the minor class instances at the cluster level. The merits of the proposed approach are that it does not remove the majority class instances from the dataset nor injects the dataset with artificial minority class instances. The resulting balanced datasets are used to train two ML classifiers, random forest and updateable Naïve Bayes, to develop prediction data models. The best prediction data models are selected based on F1-score rates. We applied two techniques to test SCArD and generate new predictions from the imbalanced test dataset. The first technique uses the best prediction data models. The second technique uses the majority voting ensemble learning model, which combines the best prediction data models to generate the final predictions. The experimental results showed that SCArD is promising and outperformed the other comparative classification models based on the F1-score rates.

Despite recent breakthroughs in Machine Learning for Natural Language Processing, the Natural Language Inference (NLI) problems still constitute a challenge. To this purpose, we contribute a new dataset that focuses exclusively on the factivity phenomenon; however, our task remains the same as other NLI tasks, that is prediction of entailment, contradiction, or neutral (ECN). In this paper, we describe the LingFeatured NLI corpus and present the results of analyses designed to characterize the factivity/non-factivity opposition in natural language. The dataset contains entirely natural language utterances in Polish and gathers 2432 verb-complement pairs and 309 unique verbs. The dataset is based on the National Corpus of Polish (NKJP) and is a representative subcorpus in regard to syntactic construction [V][że][cc]. We also present an extended version of the set (3035 sentences) consisting more sentences with internal negations. We prepared deep learning benchmarks for both sets. We found that transformer BERT-based models working on sentences obtained relatively good results ($\approx 89\%$ F1 score on base dataset). Even though better results were achieved using linguistic features ($\approx 91\%$ F1 score on base dataset), this model requires more human labor (humans in the loop) because features were prepared manually by expert linguists. BERT-based models consuming only the input sentences show that they capture most of the complexity of NLI/factivity. Complex cases in the phenomenon—for example, cases with entitlement (E) and non-factive verbs—still remain an open issue for further research.