Related papers: Large Language Model-Powered Query-Driven Event Ti…
Recently, Large Language Models (LLMs) have demonstrated great potential in various data mining tasks, such as knowledge question answering, mathematical reasoning, and commonsense reasoning. However, the reasoning capability of LLMs on…
Nowadays, time-stamped web documents related to a general news query floods spread throughout the Internet, and timeline summarization targets concisely summarizing the evolution trajectory of events along the timeline. Unlike traditional…
In the field of Natural Language Processing (NLP), Large Language Models (LLMs) have shown great potential in document-level event extraction tasks, but existing methods face challenges in the design of prompts. To address this issue, we…
In the last two decades, automatic extractive text summarization on lectures has demonstrated to be a useful tool for collecting key phrases and sentences that best represent the content. However, many current approaches utilize dated…
Event extraction lies at the cores of investment analysis and asset management in the financial field, and thus has received much attention. The 2019 China conference on knowledge graph and semantic computing (CCKS) challenge sets up a…
In text documents such as news articles, the content and key events usually revolve around a subset of all the entities mentioned in a document. These entities, often deemed as salient entities, provide useful cues of the aboutness of a…
Legal professionals often struggle with lengthy judgments and require efficient summarization for quick comprehension. To address this challenge, we investigate the need for structured planning in legal case summarization, particularly…
Event logs, as viewed in process mining, contain event data describing the execution of operational processes. Most process mining techniques take an event log as input and generate insights about the underlying process by analyzing the…
Solving real-world problems, particularly with deep learning, relies on the availability of abundant, quality data. In this paper we develop a novel framework that maximises the utility of time-series datasets that contain only small…
Time is an important dimension in our physical world. Lots of facts can evolve with respect to time. For example, the U.S. President might change every four years. Therefore, it is important to consider the time dimension and empower the…
Large Language Models (LLMs) continue to advance natural language processing with their ability to generate human-like text across a range of tasks. Despite the remarkable success of LLMs in Natural Language Processing (NLP), their…
Event relation detection is a fundamental NLP task, leveraged in many downstream applications, whose modeling requires datasets annotated with event relations of various types. However, systematic and complete annotation of these relations…
The Query-By-Document (QBD) problem is an information retrieval problem where the query is a document, and the retrieved candidates are documents that match the query document, often in a domain or query specific manner. This can be crucial…
Large language models (LLMs) are typically deployed with fixed parameters, and their performance is often improved by allocating more computation at inference time. While such test-time scaling can be effective, it cannot correct model…
This paper addresses the problem of predicting the k events that are most likely to occur next, over historical real-time event streams. Existing approaches to causal prediction queries have a number of limitations. First, they exhaustively…
We evaluate the performance of various text embedding models and pipeline configurations for AI-driven search systems. We compare sentence-transformer and generative embedding models (e.g., All-MPNet, BGE, GTE, and Qwen) at different…
Automated fact verification plays an essential role in fostering trust in the digital space. Despite the growing interest, the verification of temporal facts has not received much attention in the community. Temporal fact verification…
Using a single model across various tasks is beneficial for training and applying deep neural sequence models. We address the problem of developing generalist representations of text that can be used to perform a range of different tasks…
Event correlation reasoning infers whether a natural language paragraph containing multiple events conforms to human common sense. For example, "Andrew was very drowsy, so he took a long nap, and now he is very alert" is sound and…
The time at which a message is communicated is a vital piece of metadata in many real-world natural language processing tasks such as Topic Detection and Tracking (TDT). TDT systems aim to cluster a corpus of news articles by event, and in…