Related papers: Data Extraction via Semantic Regular Expression Sy…

We propose a novel approach to program synthesis, focusing on synthesizing database queries. At a high level, our proposed algorithm takes as input a sketch with soft constraints encoding user intent, and then iteratively interacts with the…

Text embedding models have significantly contributed to advancements in natural language processing by adeptly capturing semantic properties of textual data. However, the ability of these models to generalize across a wide range of…

Due to the lack of parallel data in current Grammatical Error Correction (GEC) task, models based on Sequence to Sequence framework cannot be adequately trained to obtain higher performance. We propose two data synthesis methods which can…

Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. In this paper we conceptualize extractive summarization as a sentence ranking task and propose a…

Large language models (LLMs) can improve their accuracy on various tasks through iteratively refining and revising their output based on feedback. We observe that these revisions can introduce errors, in which case it is better to roll back…

Joint logical-numerical reasoning remains a major challenge for language models, yet existing datasets rely on fixed rule sets and offer limited control over task complexity, constraining their generalizability for evaluation and training.…

Large Language Models (LLMs) have achieved impressive progress across a wide range of tasks, yet their heavy reliance on English-centric training data leads to significant performance degradation in non-English languages. While existing…

The challenges facing speech recognition systems, such as variations in pronunciations, adverse audio conditions, and the scarcity of labeled data, emphasize the necessity for a post-processing step that corrects recurring errors. Previous…

While compositional accounts of human language understanding are based on a hierarchical tree-like process, neural models like transformers lack a direct inductive bias for such tree structures. Introducing syntactic inductive biases could…

Using multisets, we develop novel techniques for mechanizing the proofs of the synthesis conjectures for list-sorting algorithms, and we demonstrate them in the Theorema system. We use the classical principle of extracting the algorithm as…

Grammar Error Correction(GEC) mainly relies on the availability of high quality of large amount of synthetic parallel data of grammatically correct and erroneous sentence pairs. The quality of the synthetic data is evaluated on how well the…

Agentic Retrieval-Augmented Generation (RAG) empowers large language models to autonomously plan and retrieve information for complex problem-solving. However, the development of robust agents is hindered by the scarcity of high-quality…

Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words,…

In this work, we present Semantic Gesticulator, a novel framework designed to synthesize realistic gestures accompanying speech with strong semantic correspondence. Semantically meaningful gestures are crucial for effective non-verbal…

Multimodal relation extraction (MRE) is a crucial task in the fields of Knowledge Graph and Multimedia, playing a pivotal role in multimodal knowledge graph construction. However, existing methods are typically limited to extracting a…

Semantic parsing, which converts natural language questions into logic forms, plays a crucial role in reasoning within structured environments. However, existing methods encounter two significant challenges: reliance on extensive manually…

Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation. Despite these benefits, the efficiency of…

We study the problem of recognizing structured text, i.e. text that follows certain formats, and propose to improve the recognition accuracy of structured text by specifying regular expressions (regexes) for biasing. A biased recognizer…

This project investigated new approaches and technologies to enhance the accessibility of mathematical content and its semantic information for a broad range of information retrieval applications. To achieve this goal, the project addressed…

In medical fields, text classification is one of the most important tasks that can significantly reduce human workload through structured information digitization and intelligent decision support. Despite the popularity of learning-based…