Although pretrained large language models (PLMs) have achieved state of the art on many natural language processing tasks, they lack an understanding of subtle expressions of implicit hate speech. Various attempts have been made to enhance the detection of implicit hate by augmenting external context or enforcing label separation via distance-based metrics. Combining these two approaches, we introduce FiADD, a novel focused inferential adaptive density discrimination framework. FiADD enhances the PLM finetuning pipeline by bringing the surface form/meaning of an implicit hate speech closer to its implied form while increasing the intercluster distance among various labels. We test FiADD on three implicit hate datasets and observe significant improvement in the two-way and three-way hate classification tasks. We further experiment on the generalizability of FiADD on three other tasks, detecting sarcasm, irony, and stance, in which surface and implied forms differ, and observe similar performance improvements. Consequently, we analyze the generated latent space to understand its evolution under FiADD, which corroborates the advantage of employing FiADD for implicit hate speech detection.

Detecting and removing hate speech content in a timely manner remains a challenge for social media platforms. Automated techniques such as deep learning models offer solutions which can keep up with the volume and velocity of user content production. Research in this area has mainly focused on either binary classification or on classifying tweets into generalised categories such as hateful, offensive, or neither. Less attention has been given to multiclass classification of online hate speech into the type of hate or group at which it is directed. By aggregating and re-annotating several relevant hate speech datasets, this study presents a dataset and evaluates several models for classifying tweets into the categories ethnicity, gender, religion, sexuality, and non-hate. We evaluate the dataset by training several models: logistic regression, LSTM, BERT, and GPT-2. For the LSTM model, we assess a range of NLP features using a multi-classification LSTM model, and conclude that the highest performing feature combination consists of word $n$-grams, character $n$-grams, and dependency tuples. We show that while more recent larger models can achieve a slightly higher performance, increased model complexity alone is not sufficient to achieve significantly improved models. We also compare this approach with a binary classification approach and evaluate the effect of dataset size on model performance.

Natural language querying allows users to formulate questions in a natural language without requiring specific knowledge of the database query language. Large language models have been very successful in addressing the text-to-SQL problem, which is about translating given questions in textual form into SQL statements. Document-oriented NoSQL databases are gaining popularity in the era of big data due to their ability to handle vast amounts of semi-structured data and provide advanced querying functionalities. However, studies on text-to-NoSQL systems, particularly on systems targeting document databases, are very scarce. In this study, we utilize large language models to create a cross-domain natural language to document database query dataset, DocSpider, leveraging the well-known text-to-SQL challenge dataset Spider. As a document database, we use MongoDB. Furthermore, we conduct experiments to assess the effectiveness of the DocSpider dataset to fine-tune a text-to-NoSQL model against a cross-language transfer learning approach, SQL-to-NoSQL, and zero-shot instruction prompting. The experimental results reveal a significant improvement in the execution accuracy of fine-tuned language models when utilizing the DocSpider dataset.

This paper explores the significant advancements in generating Structured Query Language (SQL) from natural language, primarily driven by Large Language Models (LLMs). These advancements have led to the development of sophisticated text-to-SQL integrated applications, enabling easier database (DB) querying for users unfamiliar with SQL syntax using natural language queries. However, reliance on LLMs exposes these applications to potential attacks through the introduction of malicious prompts or by compromising models with malicious data during the training phase. Such attacks pose severe risks, including unauthorized data access or even complete DB destruction upon success. To address these concerns, we introduce a novel large-scale dataset comprising malicious and safe prompts along with their corresponding SQL queries, enabling model fine-tuning on malicious query detection tasks. Moreover, we propose the implementation of two transformer-based classification solutions to aid in the detection of malicious attacks. Finally, we present a secure agent-based text-to-SQL architecture that incorporates these solutions to enhance overall system security, resulting in a 70% security enhancement overall compared to solely relying on a conventional text-to-SQL model.

Data-driven neural word embeddings (NWEs), grounded in distributional semantics, can capture various ranges of linguistic regularities, which can be further enriched by incorporating structured knowledge resources. This work proposes a novel post-processing approach for injecting semantic relationships into the vector space of both static and contextualized NWEs. Current solutions to retrofitting (RF) word embeddings often oversimplify the integration of semantic knowledge, neglecting the nuanced differences between relationships, which may result in suboptimal performance. Instead of applying multi-thresholding to distance boundaries in metric learning, we compute taxonomic similarity to dynamically adjust these boundaries during the semantic specialization of word embeddings. Benchmark evaluations on both static and contextualized word embeddings demonstrate that our dynamic-fitting (DF) approach produces SOTA correlation results of 0.78 and 0.76 on SimLex-999 and SimVerb-3500, respectively, highlighting the effectiveness of incorporating multiple semantic relationships in refining vector semantics. Our approach also outperforms existing RF methods in both supervised and unsupervised semantic relationships recognition tasks. It achieves top accuracy scores for hypernymy detection on the BLESS, WBLESS, and BIBLESS datasets (0.97, 0.89, and 0.83, respectively) and an F1 score of over 0.60 on four types of semantic relationship classification in the shared Subtask-2 of CogALex-V, surpassing all participant systems. In the analogy reasoning task of the Bigger Analogy Test Set, our approach outperforms existing RF methods on inferring relational similarity. These consistent improvements across various lexical semantics tasks suggest that our DF approach can effectively integrate distributional semantics with symbolic knowledge resources, thereby enhancing the representation capacity of word embeddings in downstream applications.

Research suggests that the texts produced using machine translation (MT) do not fully represent the linguistic traits of the natural language. Yet, the ever-increasing quality and access to MT is resulting in its steady adoption by both language professionals and general users. According to contact linguistic theories, such adoption might result in MT-specific language traits permeating the target languages. This work takes a first step into considering the changes that a language might endure over time by observing the variation of linguistic trends along a series of MT generations. We train ten sequential engines using each to produce the target side of the training corpus of the following and calculate a number of metrics to observe linguistic diversity at a lexical, morphological, and syntactic level for a large, fixed test set. Quantitative results show an initial loss of lexical diversity, which, albeit gradually, only continues at a much slower pace in the following MT generations. In turn, structural variations and, in particular, morphological variations across generations are less marked, which might indicate a more stable behaviour regarding grammatical consistency. Overall, the resulting MT language seems increasingly homogeneous, marked by the reduced presence or disappearance of low-frequency words, and compact, with a decreasing proportion of function words relative to content words.

Everyone is talking about bots. Much of the discussion has focused on downsides. It is too easy to use bots to cheat, but there are also many ways to use bots to improve your writing. Good writers use thesauruses. It is not cheating to use bots as a modern version of a thesaurus. It is also not cheating to use recommendation systems in a responsible way.