Related papers: TIE: Topological Information Enhanced Structural R…
Document-level information extraction (IE) is a crucial task in natural language processing (NLP). This paper conducts a systematic review of recent document-level IE literature. In addition, we conduct a thorough error analysis with…
We present the architecture and the evaluation of a new system for recognizing textual entailment (RTE). In RTE we want to identify automatically the type of a logical relation between two input texts. In particular, we are interested in…
Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the…
We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered…
Information Extraction (IE) from the tables present in scientific articles is challenging due to complicated tabular representations and complex embedded text. This paper presents TabLeX, a large-scale benchmark dataset comprising table…
Tabular data in digital documents is widely used to express compact and important information for readers. However, it is challenging to parse tables from unstructured digital documents, such as PDFs and images, into machine-readable format…
Open Information Extraction (OIE) is a structured prediction (SP) task in Natural Language Processing (NLP) that aims to extract structured $n$-ary tuples - usually subject-relation-object triples - from free text. The word embeddings in…
Many real-world processes evolve in cascades over complex networks, whose topologies are often unobservable and change over time. However, the so-termed adoption times when blogs mention popular news items, individuals in a community catch…
The understanding of the immense and intricate topological structure of the World Wide Web (WWW) is a major scientific and technological challenge. This has been tackled recently by characterizing the properties of its representative graphs…
As Large Language Models (LLMs) evolve into the core of Web-based autonomous agents and complex Web Information Systems, their ability to faithfully translate natural language into rigorous structured formats has become paramount, as this…
The task of information extraction (IE) is to extract structured knowledge from text. However, it is often not straightforward to utilize IE output due to the mismatch between the IE ontology and the downstream application needs. We propose…
The task of text-to-SQL parsing, which aims at converting natural language questions into executable SQL queries, has garnered increasing attention in recent years, as it can assist end users in efficiently extracting vital information from…
Retrieval-Augmented Generation (RAG) systems depend on the geometric properties of vector representations to retrieve contextually appropriate evidence. When source documents interleave multiple topics within contiguous text, standard…
We introduce a Recursive INsertion-based Encoder (RINE), a novel approach for semantic parsing in task-oriented dialog. Our model consists of an encoder network that incrementally builds the semantic parse tree by predicting the…
Recent works on relational triple extraction have shown the superiority of jointly extracting entities and relations over the pipelined extraction manner. However, most existing joint models fail to balance the modeling of entity features…
Online learning to rank is a sequential decision-making problem where in each round the learning agent chooses a list of items and receives feedback in the form of clicks from the user. Many sample-efficient algorithms have been proposed…
End-to-end visual information extraction (VIE) aims at integrating the hierarchical subtasks of VIE, including text spotting, word grouping, and entity labeling, into a unified framework. Dealing with the gaps among the three subtasks plays…
Retrieval-Augmented Generation (RAG) systems typically treat documents as flat text, ignoring the structured metadata and linked relationships that knowledge graphs provide. In this paper, we investigate whether structured linked data,…
Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key…
Large language models (LLMs) have demonstrated remarkable advances in reasoning capabilities. However, their performance remains constrained by limited access to explicit and structured domain knowledge. Retrieval-Augmented Generation (RAG)…