English
Related papers

Related papers: PEACH: Pretrained-embedding Explanation Across Con…

200 papers

Semantic Text Embedding is a fundamental NLP task that encodes textual content into vector representations, where proximity in the embedding space reflects semantic similarity. While existing embedding models excel at capturing general…

Computation and Language · Computer Science 2025-06-02 Yiqun Sun , Qiang Huang , Anthony K. H. Tung , Jun Yu

Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…

Computation and Language · Computer Science 2020-10-13 Mengjie Zhao , Philipp Dufter , Yadollah Yaghoobzadeh , Hinrich Schütze

Legal judgment prediction suffers from the problem of long case documents exceeding tens of thousands of words, in general, and having a non-uniform structure. Predicting judgments from such documents becomes a challenging task, more so on…

Computation and Language · Computer Science 2024-03-12 Nishchal Prasad , Mohand Boughanem , Taoufiq Dkaki

The meaning of a word often varies depending on its usage in different domains. The standard word embedding models struggle to represent this variation, as they learn a single global representation for a word. We propose a method to learn…

Computation and Language · Computer Science 2019-10-22 Lahari Poddar , Gyorgy Szarvas , Lea Frermann

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of…

Computation and Language · Computer Science 2020-10-02 Tianxiang Sun , Yunfan Shao , Xipeng Qiu , Qipeng Guo , Yaru Hu , Xuanjing Huang , Zheng Zhang

Since Pretrained Language Models (PLMs) are the cornerstone of the most recent Information Retrieval (IR) models, the way they encode semantic knowledge is particularly important. However, little attention has been given to studying the…

Computation and Language · Computer Science 2023-12-18 Jesús Lovón-Melgarejo , Jose G. Moreno , Romaric Besançon , Olivier Ferret , Lynda Tamine

The ability to understand and generate languages sets human cognition apart from other known life forms'. We study a way of combing two of the most successful routes to meaning of language--statistical language models and symbolic semantics…

Computation and Language · Computer Science 2022-06-14 Yichao Liang

While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive. Natural…

Computation and Language · Computer Science 2020-02-17 Ziqi Wang , Yujia Qin , Wenxuan Zhou , Jun Yan , Qinyuan Ye , Leonardo Neves , Zhiyuan Liu , Xiang Ren

External knowledge is often useful for natural language understanding tasks. We introduce a contextual text representation model called Conceptual-Contextual (CC) embeddings, which incorporates structured knowledge into text…

Computation and Language · Computer Science 2020-03-13 Xiao Zhang , Dejing Dou , Ji Wu

Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts. Building on prior work on contextualized and dynamic word embeddings, we…

Computation and Language · Computer Science 2021-06-09 Valentin Hofmann , Janet B. Pierrehumbert , Hinrich Schütze

Text clustering serves as a fundamental technique for organizing and interpreting unstructured textual data, particularly in contexts where manual annotation is prohibitively costly. With the rapid advancement of Large Language Models…

Computation and Language · Computer Science 2025-10-08 Chen Huang , Guoxiu He

Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel…

Computation and Language · Computer Science 2021-12-30 Haw-Shiuan Chang , Amol Agrawal , Andrew McCallum

Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have…

Computation and Language · Computer Science 2026-01-27 Kartik Sharma , Yiqiao Jin , Rakshit Trivedi , Srijan Kumar

Large Language Models (LLMs) excel in text classification, but their complexity hinders interpretability, making it difficult to understand the reasoning behind their predictions. Explainable AI (XAI) methods like LIME and SHAP offer local…

Computation and Language · Computer Science 2025-07-16 Yogachandran Rahulamathavan , Misbah Farooq , Varuna De Silva

Accurately dating historical texts is essential for organizing and interpreting cultural heritage collections. This article addresses temporal text classification using interpretable, feature-engineered tree-based machine learning models.…

Computation and Language · Computer Science 2025-12-01 Paulo J. N. Pinto , Armando J. Pinho , Diogo Pratas

Linguistic structures exhibit a rich array of global phenomena, however commonly used Markov models are unable to adequately describe these phenomena due to their strong locality assumptions. We propose a novel hierarchical model for…

Machine Learning · Computer Science 2015-03-10 Ehsan Shareghi , Gholamreza Haffari , Trevor Cohn , Ann Nicholson

In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models,…

Computation and Language · Computer Science 2020-04-30 Tao Shen , Yi Mao , Pengcheng He , Guodong Long , Adam Trischler , Weizhu Chen

Named entity recognition (NER) models are typically based on the architecture of Bi-directional LSTM (BiLSTM). The constraints of sequential nature and the modeling of single input prevent the full utilization of global information from…

Computation and Language · Computer Science 2019-11-20 Ying Luo , Fengshun Xiao , Hai Zhao

Recent pre-trained language models (PLMs) equipped with foundation reasoning skills have shown remarkable performance on downstream complex tasks. However, the significant structure reasoning skill has been rarely studied, which involves…

Computation and Language · Computer Science 2023-07-18 Siyuan Wang , Zhongyu Wei , Jiarong Xu , Taishan Li , Zhihao Fan

Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the…

Computation and Language · Computer Science 2020-01-16 Jean Maillard , Stephen Clark