Related papers: RASAT: Integrating Relational Structures into Pret…

Structured embedding transformations offer a promising approach for enhancing the efficiency and coherence of language model inference. The introduction of Structural Embedding Projection (SEP) provides a mechanism for refining token…

In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture. In this paper, we present a simple yet effective approach that adapts transformer-based seq-to-seq model to robust…

Large language models (LLMs) with in-context learning have significantly improved the performance of text-to-SQL task. Previous works generally focus on using exclusive SQL generation prompt to improve the LLMs' reasoning ability. However,…

Text-to-SQL enables users to interact with databases through natural language, simplifying access to structured data. Although highly capable large language models (LLMs) achieve strong accuracy for complex queries, they incur unnecessary…

Understanding the relationships between protein sequence, structure and function is a long-standing biological challenge with manifold implications from drug design to our understanding of evolution. Recently, protein language models have…

Translating natural language into SQL (Test2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language models (LLMs) have significantly improved fluency in SQL…

We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are attractive owing to their ability to convert prosody. While…

Table learning, which lies at the intersection of machine learning and modern database systems, has recently attracted growing attention. However, existing table learning frameworks typically require explicit data export and extensive…

Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries over a single table. We focus on the Spider dataset, a complex and cross-domain text-to-SQL task, which…

Translating natural language utterances to executable queries is a helpful technique in making the vast amount of data stored in relational databases accessible to a wider range of non-tech-savvy end users. Prior work in this area has…

We present BRIDGE, a powerful sequential architecture for modeling dependencies between natural language questions and relational databases in cross-DB semantic parsing. BRIDGE represents the question and DB schema in a tagged sequence…

Advances in large language models have accelerated progress in text-to-SQL, methods for converting natural language queries into valid SQL queries. A key bottleneck for developing generalizable text-to-SQL models is the lack of large-scale…

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new direction in speech research. The approach benefits by performing model training without using lexicon and alignments. However, this poses a new problem of…

Large language models revolutionize Text2SQL through supervised fine-tuning, yet a crucial limitation is overlooked: the complexity of databases leads to an increased context length, consequently resulting in higher GPU memory demands for…

Most recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution system that uses a text-to-text (seq2seq) paradigm to predict…

Multilingual T5 (mT5) pretrains a sequence-to-sequence model on massive monolingual texts, which has shown promising results on many cross-lingual tasks. In this paper, we improve multilingual text-to-text transfer Transformer with…

Generative language models have shown significant potential in single-turn Text-to-SQL. However, their performance does not extend equivalently to multi-turn Text-to-SQL. This is primarily due to generative language models' inadequacy in…

In-context learning using large language models has recently shown surprising results for semantic parsing tasks such as Text-to-SQL translation. Prompting GPT-3 or Codex using several examples of question-SQL pairs can produce excellent…

The data-centric paradigm has emerged as a pivotal direction in artificial intelligence (AI), emphasizing the role of high-quality training data. This shift is especially critical in the Text-to-SQL task, where the scarcity, limited…

Text-to-SQL is a task that converts a natural language question into a structured query language (SQL) to retrieve information from a database. Large language models (LLMs) work well in natural language generation tasks, but they are not…