English
Related papers

Related papers: From Retrieval to Generation: Efficient and Effect…

200 papers

Entity Typing (ET) is the process of identifying the semantic types of every entity within a corpus. In contrast to Named Entity Recognition, where each token in a sentence is labelled with zero or one class label, ET involves labelling…

Computation and Language · Computer Science 2020-03-24 Michael Stewart , Wei Liu

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

Computation and Language · Computer Science 2022-11-01 Yiming Chen , Yan Zhang , Bin Wang , Zuozhu Liu , Haizhou Li

End-to-end automatic speech recognition (ASR) systems frequently misrecognize domain-specific phrases like named entities, which can cause catastrophic failures in downstream tasks. A new family of named entity correction methods based on…

Computation and Language · Computer Science 2026-02-16 Junjie An , Jingguang Tian , Tianyi Wang , Yu Gao , Xiaofeng Mou , Yi Xu

Entity Recognition (ER) within a text is a fundamental exercise in Natural Language Processing, enabling further depending tasks such as Knowledge Extraction, Text Summarisation, or Keyphrase Extraction. An entity consists of single words…

Computation and Language · Computer Science 2021-06-14 Andreas Waldis , Luca Mazzola

Current context augmentation methods, such as retrieval-augmented generation, are essential for solving knowledge-intensive reasoning tasks. However, they typically adhere to a rigid, brute-force strategy that executes retrieval at every…

Computation and Language · Computer Science 2026-01-15 Rubing Chen , Jian Wang , Wenjie Li , Xiao-Yong Wei , Qing Li

Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields…

Computation and Language · Computer Science 2021-10-05 Timo Schick , Hinrich Schütze

Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first…

Computation and Language · Computer Science 2023-01-26 Wenhao Yu , Dan Iter , Shuohang Wang , Yichong Xu , Mingxuan Ju , Soumya Sanyal , Chenguang Zhu , Michael Zeng , Meng Jiang

Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in machine intelligence. The taxonomy expansion task aims to find a position for a new term in an existing taxonomy to capture the emerging knowledge in the…

Computation and Language · Computer Science 2022-04-27 Suyuchen Wang , Ruihui Zhao , Xi Chen , Yefeng Zheng , Bang Liu

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…

Databases · Computer Science 2021-12-17 Naser Ahmadi , Hansjorg Sand , Paolo Papotti

Improving context faithfulness in large language models is essential for developing trustworthy retrieval augmented generation systems and mitigating hallucinations, especially in long-form question answering (LFQA) tasks or scenarios…

Computation and Language · Computer Science 2025-03-04 Kun Li , Tianhua Zhang , Yunxiang Li , Hongyin Luo , Abdalla Moustafa , Xixin Wu , James Glass , Helen Meng

Most of the existing information retrieval systems are based on bag of words model and are not equipped with common world knowledge. Work has been done towards improving the efficiency of such systems by using intelligent algorithms to…

Artificial Intelligence · Computer Science 2015-03-17 Pekka Malo , Pyry Siitari , Ankur Sinha

Generative pre-trained transformer (GPT) models have shown promise in clinical entity and relation extraction tasks because of their precise extraction and contextual understanding capability. In this work, we further leverage the Unified…

Computation and Language · Computer Science 2024-07-16 Kriti Bhattarai , Inez Y. Oh , Zachary B. Abrams , Albert M. Lai

Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often…

Computation and Language · Computer Science 2023-11-07 Zilin Xiao , Linjun Shou , Xingyao Zhang , Jie Wu , Ming Gong , Jian Pei , Daxin Jiang

Existing segmentation models based on multimodal large language models (MLLMs), such as LISA, often struggle with novel or emerging entities due to their inability to incorporate up-to-date knowledge. To address this challenge, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Song Tang , Guangquan Jie , Henghui Ding , Yu-Gang Jiang

Entity Linking (EL) seeks to align entity mentions in text to entries in a knowledge-base and is usually comprised of two phases: candidate generation and candidate ranking. While most methods focus on the latter, it is the candidate…

Computation and Language · Computer Science 2021-03-09 Eleni Partalidou , Despina Christou , Grigorios Tsoumakas

Understanding the intention of the users and recognizing the semantic entities from their sentences, aka natural language understanding (NLU), is the upstream task of many natural language processing tasks. One of the main challenges is to…

Computation and Language · Computer Science 2022-09-07 Jiaxing Xu , Jianbin Cui , Jiangneng Li , Wenge Rong , Noboru Matsuda

Although Large Language Models (LLMs) demonstrate significant capabilities, their reliance on parametric knowledge often leads to inaccuracies. Retrieval Augmented Generation (RAG) mitigates this by incorporating external knowledge, but…

Artificial Intelligence · Computer Science 2025-11-04 Hailong Yin , Bin Zhu , Jingjing Chen , Chong-Wah Ngo

We propose Batch-Expansion Training (BET), a framework for running a batch optimizer on a gradually expanding dataset. As opposed to stochastic approaches, batches do not need to be resampled i.i.d. at every iteration, thus making BET more…

Machine Learning · Computer Science 2018-02-26 Michał Dereziński , Dhruv Mahajan , S. Sathiya Keerthi , S. V. N. Vishwanathan , Markus Weimer

Entity alignment aims to use pre-aligned seed pairs to find other equivalent entities from different knowledge graphs (KGs) and is widely used in graph fusion-related fields. However, as the scale of KGs increases, manually annotating…

Computation and Language · Computer Science 2025-03-28 Tao Meng , Shuo Shan , Hongen Shao , Yuntao Shou , Wei Ai , Keqin Li

This paper presents a Kernel Entity Salience Model (KESM) that improves text understanding and retrieval by better estimating entity salience (importance) in documents. KESM represents entities by knowledge enriched distributed…

Information Retrieval · Computer Science 2018-05-04 Chenyan Xiong , Zhengzhong Liu , Jamie Callan , Tie-Yan Liu