Text-to-SQL is the task that aims at translating natural language questions into SQL queries. Existing methods directly align the natural language with SQL Language and train one encoder-decoder-based model to fit all questions. However, they underestimate the inherent structural characteristics of SQL, as well as the gap between specific structure knowledge and general knowledge. This leads to structure errors in the generated SQL. To address the above challenges, we propose a retrieval-argument framework, namely ReFSQL. It contains two parts, structure-enhanced retriever and the generator. Structure-enhanced retriever is designed to identify samples with comparable specific knowledge in an unsupervised way. Subsequently, we incorporate the retrieved samples’ SQL into the input, enabling the model to acquire prior knowledge of similar SQL grammar. To further bridge the gap between specific and general knowledge, we present a mahalanobis contrastive learning method, which facilitates the transfer of the sample toward the specific knowledge distribution constructed by the retrieved samples. Experimental results on five datasets verify the effectiveness of our approach in improving the accuracy and robustness of Text-to-SQL generation. Our framework has achieved improved performance when combined with many other backbone models (including the 11B flan-T5) and also achieved state-of-the-art performance when compared to existing methods that employ the fine-tuning approach.

Recent research has investigated the use of generative language models to produce regular expressions with semantic-based approaches. However, these approaches have shown shortcomings in practical applications, particularly in terms of functional correctness, which refers to the ability to reproduce the intended function inputs by the user. To address this issue, we present a novel method called Unit-Test Driven Reinforcement Learning (UTD-RL). Our approach differs from previous methods by taking into account the crucial aspect of functional correctness and transforming it into a differentiable gradient feedback using policy gradient techniques. In which functional correctness can be evaluated through Unit Tests, a testing method that ensures regular expressions meets its design and performs as intended. Experiments conducted on three public datasets demonstrate the effectiveness of the proposed method in generating regular expressions. This method has been employed in a regulatory scenario where regular expressions can be utilized to ensure that all online content is free from non-compliant elements, thereby significantly reducing the workload of relevant personnel.

Contrastive learning has achieved impressive success in generation tasks to militate the “exposure bias” problem and discriminatively exploit the different quality of references. Existing works mostly focus on contrastive learning on the instance-level without discriminating the contribution of each word, while keywords are the gist of the text and dominant the constrained mapping relationships. Hence, in this work, we propose a hierarchical contrastive learning mechanism, which can unify hybrid granularities semantic meaning in the input text. Concretely, we first propose a keyword graph via contrastive correlations of positive-negative pairs to iteratively polish the keyword representations. Then, we construct intra-contrasts within instance-level and keyword-level, where we assume words are sampled nodes from a sentence distribution. Finally, to bridge the gap between independent contrast levels and tackle the common contrast vanishing problem, we propose an inter-contrast mechanism that measures the discrepancy between contrastive keyword nodes respectively to the instance distribution. Experiments demonstrate that our model outperforms competitive baselines on paraphrasing, dialogue generation, and storytelling tasks.

The title generation task that summarizes article content in recapitulatory words relies heavily on utilizing the corresponding key context. To generate a title with appropriate information in the content and avoid repetition, we propose a title generation framework with two complementary components in this paper. First, we propose a Timestep aware Sentence Embedding (TSE) mechanism, which updates the sentences’ representations by re-locating the critical words in the corresponding sentence for each decoding step. Then, we present an Acme Coverage (AC) mechanism to solve the repetition problem and preserve the remaining valuable keywords after each decoding step according to the final vocabulary distribution. We conduct comprehensive experiments on various title generation tasks with different backbones, the evaluation scores of ROUGE and METEOR in varying degrees are significantly outperforming most of the existing state-of-the-art approaches. The experimental results demonstrate the effectiveness and generality of our novel generation framework TSE-AC.

Knowledge-driven conversation approaches have achieved remarkable research attention recently. However, generating an informative response with multiple relevant knowledge without losing fluency and coherence is still one of the main challenges. To address this issue, this paper proposes a method that uses recurrent knowledge interaction among response decoding steps to incorporate appropriate knowledge. Furthermore, we introduce a knowledge copy mechanism using a knowledge-aware pointer network to copy words from external knowledge according to knowledge attention distribution. Our joint neural conversation model which integrates recurrent Knowledge-Interaction and knowledge Copy (KIC) performs well on generating informative responses. Experiments demonstrate that our model with fewer parameters yields significant improvements over competitive baselines on two datasets Wizard-of-Wikipedia(average Bleu +87%; abs.: 0.034) and DuConv(average Bleu +20%; abs.: 0.047)) with different knowledge formats (textual & structured) and different languages (English & Chinese).