English
Related papers

Related papers: Dwell in the Beginning: How Language Models Embed …

200 papers

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained…

Information Retrieval · Computer Science 2022-08-23 Xinyu Ma , Ruqing Zhang , Jiafeng Guo , Yixing Fan , Xueqi Cheng

Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a concise, objective…

Computation and Language · Computer Science 2021-01-26 Masahiro Kaneko , Danushka Bollegala

Generating textual descriptions for images has been an attractive problem for the computer vision and natural language processing researchers in recent years. Dozens of models based on deep learning have been proposed to solve this problem.…

Computer Vision and Pattern Recognition · Computer Science 2019-07-01 Ahmad Asadi , Reza Safabakhsh

In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic memory, where the retrieval of specific events is enabled by…

Computation and Language · Computer Science 2025-10-28 Anooshka Bajaj , Deven Mahesh Mistry , Sahaj Singh Maini , Yash Aggarwal , Zoran Tiganj

Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This bias is closely connected to the Lost-in-the-Middle phenomenon, where models underutilize…

Machine Learning · Computer Science 2026-05-28 Hanna Herasimchyk , Robin Labryga , Tomislav Prusina , Sören Laue

Lexical semantics and cognitive science point to affordances (i.e. the actions that objects support) as critical for understanding and representing nouns and verbs. However, study of these semantic features has not yet been integrated with…

Computation and Language · Computer Science 2022-07-07 Jack Merullo , Dylan Ebert , Carsten Eickhoff , Ellie Pavlick

Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…

Computation and Language · Computer Science 2022-04-26 Miaoran Zhang , Marius Mosbach , David Ifeoluwa Adelani , Michael A. Hedderich , Dietrich Klakow

In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a fine-tuning method…

Computation and Language · Computer Science 2021-01-26 Masahiro Kaneko , Danushka Bollegala

Contemporary deep learning models effectively handle languages with diverse morphology despite not being directly integrated into them. Morphology and word order are closely linked, with the latter incorporated into transformer-based models…

Computation and Language · Computer Science 2024-05-31 Poulami Ghosh , Shikhar Vashishth , Raj Dabre , Pushpak Bhattacharyya

Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…

Computation and Language · Computer Science 2019-09-10 Muhao Chen , Yingtao Tian , Haochen Chen , Kai-Wei Chang , Steven Skiena , Carlo Zaniolo

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

Computation and Language · Computer Science 2021-02-17 Shengjie Luo , Kaiyuan Gao , Shuxin Zheng , Guolin Ke , Di He , Liwei Wang , Tie-Yan Liu

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…

Position embeddings, encoding the positional relationships among tokens in text sequences, make great contributions to modeling local context features in Transformer-based pre-trained language models. However, in Extractive Question…

Computation and Language · Computer Science 2023-11-21 Mingxu Tao , Yansong Feng , Dongyan Zhao

One key challenge in multi-document summarization is to capture the relations among input documents that distinguish between single document summarization (SDS) and multi-document summarization (MDS). Few existing MDS works address this…

Computation and Language · Computer Science 2022-09-14 Congbo Ma , Wei Emma Zhang , Pitawelayalage Dasun Dileepa Pitawela , Yutong Qu , Haojie Zhuang , Hu Wang

Large Language Models (LLMs) often exhibit positional bias in long-context settings, under-attending to information in the middle of inputs. We investigate the presence of this bias in long-form summarization, its impact on faithfulness,…

Computation and Language · Computer Science 2025-07-08 David Wan , Jesse Vig , Mohit Bansal , Shafiq Joty

Word embeddings have recently been shown to reflect many of the pronounced societal biases (e.g., gender bias or racial bias). Existing studies are, however, limited in scope and do not investigate the consistency of biases across relevant…

Computation and Language · Computer Science 2019-04-30 Anne Lauscher , Goran Glavaš

In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural…

Computation and Language · Computer Science 2018-02-06 Yang Liu , Mirella Lapata

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain…

Computation and Language · Computer Science 2024-06-07 Chi Han , Jialiang Xu , Manling Li , Yi Fung , Chenkai Sun , Nan Jiang , Tarek Abdelzaher , Heng Ji

Large language models (LLMs) have increasingly been explored as powerful text embedders. Existing LLM-based text embedding approaches often leverage the embedding of the final token, typically a reserved special token such as [EOS].…

Computation and Language · Computer Science 2025-10-10 Chang Su , Dengliang Shi , Siyuan Huang , Jintao Du , Changhua Meng , Yu Cheng , Weiqiang Wang , Zhouhan Lin

Transformers are not suited for processing long documents, due to their quadratically increasing memory and time consumption. Simply truncating a long document or applying the sparse attention mechanism will incur the context fragmentation…

Computation and Language · Computer Science 2021-05-25 Siyu Ding , Junyuan Shang , Shuohuan Wang , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang