Related papers: Xpose: Bi-directional Engineering for Hidden Query…
We introduce CogRE, a novel framework for relation extraction (RE), enhancing RE from both accuracy and explainability. The framework has two key components: (i) a reasoning mechanism that formulates relation extraction as a series of…
Structured information extraction from unstructured text is critical for emerging Software 3.0 systems where LLM agents autonomously interact with APIs and tools. Recent approaches apply large language models directly to extraction tasks…
Despite exciting progress on cryptography, secure and efficient query processing over outsourced data remains an open challenge. We develop a communication-efficient and information-theoretically secure system, entitled Obscure for…
Understanding the internals of Integrated Circuits (ICs), referred to as Hardware Reverse Engineering (HRE), is of interest to both legitimate and malicious parties. HRE is a complex process in which semi-automated steps are interwoven with…
We formulate query-subquery nets and use them to create the first framework for developing algorithms for evaluating queries to Horn knowledge bases with the properties that: the approach is goal-directed; each subquery is processed only…
In this work we focus on multi-turn passage retrieval as a crucial component of conversational search. One of the key challenges in multi-turn passage retrieval comes from the fact that the current turn query is often underspecified due to…
Abstraction without regret refers to the vision of using high-level programming languages for systems development without experiencing a negative impact on performance. A database system designed according to this vision offers both…
Machine Translation Quality Estimation (QE) is a task of predicting the quality of machine translations without relying on any reference. Recently, the predictor-estimator framework trains the predictor as a feature extractor, which…
Translating SQL dialects across different relational database management systems (RDBMSs) is crucial for migrating RDBMS-based applications to the cloud. Traditional SQL dialect translation tools rely on manually-crafted rules,…
Knowledge graph question answering (KGQA) aims to answer natural language questions using knowledge graphs. Recent research leverages large language models (LLMs) to enhance KGQA reasoning, but faces limitations: retrieval-based methods are…
Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be categorised into generative and discriminative approaches,…
Information Extraction (IE) is crucial for converting unstructured data into structured formats like Knowledge Graphs (KGs). A key task within IE is Relation Extraction (RE), which identifies relationships between entities in text. Various…
The rise of Large Language Models (LLMs) has accelerated the long-standing goal of enabling natural language querying over complex, hybrid databases. Yet, this ambition exposes a dual challenge: reasoning jointly over structured,…
Event relation extraction (ERE) is a critical and fundamental challenge for natural language processing. Existing work mainly focuses on directly modeling the entire document, which cannot effectively handle long-range dependencies and…
Information retrieval (IR) or knowledge retrieval, is a critical component for many down-stream tasks such as open-domain question answering (QA). It is also very challenging, as it requires succinctness, completeness, and correctness. In…
Universal Information Extraction (UIE) is an area of interest due to the challenges posed by varying targets, heterogeneous structures, and demand-specific schemas. However, previous works have only achieved limited success by unifying a…
XML data projection (or pruning) is a natural optimization for main memory query engines: given a query Q over a document D, the subtrees of D that are not necessary to evaluate Q are pruned, thus producing a smaller document D'; the query…
Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…
This full research paper focuses on skill acquisition in Hardware Reverse Engineering (HRE) - an important field of cyber security. HRE is a prevalent technique routinely employed by security engineers (i) to detect malicious hardware…
Retrieval augmented generation (RAG) pipelines are commonly used in tasks such as question-answering (QA), relying on retrieving relevant documents from a vector store computed using a pretrained embedding model. However, if the retrieved…