The logical negation property (LNP), which implies generating different predictions for semantically opposite inputs (p is true iff ¬p is false), is an important property that a trustworthy language model must satisfy. However, much recent evidence shows that large-size pre-trained language models (PLMs) do not satisfy this property. In this paper, we perform experiments using probing tasks to assess PLMs’ LNP understanding. Unlike previous studies that only examined negation expressions, we expand the boundary of the investigation to lexical semantics. Through experiments, we observe that PLMs violate the LNP frequently. To alleviate the issue, we propose a novel intermediate training task, named meaning-matching, designed to directly learn a meaning text correspondence, instead of relying on the distributional hypothesis. Through multiple experiments, we find that the task enables PLMs to learn lexical semantic information. Also, through fine-tuning experiments on 7 GLUE tasks, we confirm that it is a safe intermediate task that guarantees a similar or better performance of downstream tasks. Finally, we observe that our proposed approach outperforms our previous counterparts despite its time and resource efficiency.

Open information extraction (OIE) is the task of extracting facts "(Subject, Relation, Object)” from natural language text. We propose several new methods for training neural OIE models in this paper. First, we propose a novel method for computing syntactically rich text embeddings using the structure of dependency trees. Second, we propose a new discriminative training approach to OIE in which tokens in the generated fact are classified as “real” or “fake”, i.e., those tokens that are in both the generated and gold tuples, and those that are only in the generated tuple but not in the gold tuple. We also address the issue of repetitive tokens in generated facts and improve the models’ ability to generate implicit facts. Our approach reduces repetitive tokens by a factor of 23%. Finally, we present paraphrased versions of the CaRB, OIE2016, and LSOIE datasets, and show that the models’ performance substantially improves when trained on augmented datasets. Our best model beats the SOTA of IMoJIE on the recent CaRB dataset, with an improvement of 39.63% in F1 score.

The goal of open information extraction (OIE) is to extract facts from natural language text, and to represent them as structured triples of the form <subject,predicate, object>. For example, given the sentence “Beethoven composed the Ode to Joy.”, we are expected to extract the triple <Beethoven, composed, Ode to Joy>. In this work, we systematically compare different neural network architectures and training approaches, and improve the performance of the currently best models on the OIE16 benchmark (Stanovsky and Dagan, 2016) by 0.421 F1 score and 0.420 AUC-PR, respectively, in our experiments (i.e., by more than 200% in both cases). Furthermore, we show that appropriate problem and loss formulations often affect the performance more than the network architecture.