Related papers: Data Ambiguity Strikes Back: How Documentation Imp…

Data augmentation has attracted a lot of research attention in the deep learning era for its ability in alleviating data sparseness. The lack of labeled data for unseen evaluation databases is exactly the major challenge for cross-domain…

The proliferation of complex structured data in hybrid sources, such as PDF documents and web pages, presents unique challenges for current Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) in providing accurate…

Today's Web of Data is noisy. Linked Data often needs extensive preprocessing to enable efficient use of heterogeneous resources. While consistent and valid data provides the key to efficient data processing and aggregation we are facing…

Maintaining consistent model performance across domains is a fundamental challenge in machine learning. While recent work has explored using LLM-generated data for fine-tuning, its impact on cross-domain generalization remains poorly…

Questions regarding implicitness, ambiguity and underspecification are crucial for understanding the task validity and ethical concerns of multimodal image+text systems, yet have received little attention to date. This position paper maps…

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…

Sentences containing multiple semantic operators with overlapping scope often create ambiguities in interpretation, known as scope ambiguities. These ambiguities offer rich insights into the interaction between semantic structure and world…

Existing large language models (LLMs) for machine translation are typically fine-tuned on sentence-level translation instructions and achieve satisfactory performance at the sentence level. However, when applied to document-level…

Cognitive computing systems require human labeled data for evaluation, and often for training. The standard practice used in gathering this data minimizes disagreement between annotators, and we have found this results in data that fails to…

One of the major challenges of machine translation (MT) is ambiguity, which can in some cases be resolved by accompanying context such as images. However, recent work in multimodal MT (MMT) has shown that obtaining improvements from images…

Repairing inconsistent knowledge bases is a task that has been assessed, with great advances over several decades, from within the knowledge representation and reasoning and the database theory communities. As information becomes more…

Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries. State-of-the-art (SOTA) systems use large, pre-trained and finetuned language models, such as the T5-family, in conjunction…

Education that suits the individual learning level is necessary to improve students' understanding. The first step in achieving this purpose by using large language models (LLMs) is to adjust the textual difficulty of the response to…

Large Language Models (LLMs) have been achieving competent performance on a wide range of downstream tasks, yet existing work shows that inference on structured data is challenging for LLMs. This is because LLMs need to either understand…

Due to the lack of a large collection of high-quality labeled sentence pairs with textual similarity scores, existing approaches for Semantic Textual Similarity (STS) mostly rely on unsupervised techniques or training signals that are only…

User queries are often underspecified and may admit multiple valid interpretations. Rather than silently making assumptions about the user's intent, a helpful assistant should surface such ambiguity by asking a clarifying question. Doing so…

Recent advances in Text-to-SQL have achieved strong results in static, single-turn tasks, where models generate SQL queries from natural language questions. However, these systems fall short in real-world interactive scenarios, where user…

Linguistic ambiguity is and has always been one of the main challenges in Natural Language Processing (NLP) systems. Modern Transformer architectures like BERT, T5 or more recently InstructGPT have achieved some impressive improvements in…

The advent of multimodal learning has brought a significant improvement in document AI. Documents are now treated as multimodal entities, incorporating both textual and visual information for downstream analysis. However, works in this…

Ambiguous questions persist in open-domain question answering, because formulating a precise question with a unique answer is often challenging. Previously, Min et al. (2020) have tackled this issue by generating disambiguated questions for…