English
Related papers

Related papers: Representation biases in sentence transformers

200 papers

This study investigates the internal representations of verb-particle combinations within transformer-based large language models (LLMs), specifically examining how these models capture lexical and syntactic nuances at different neural…

Computation and Language · Computer Science 2024-12-20 Hassane Kissane , Achim Schilling , Patrick Krauss

Transformer-based embedding methods have dominated the field of sentence representation in recent years. Although they have achieved remarkable performance on NLP missions, such as semantic textual similarity (STS) tasks, their black-box…

Computation and Language · Computer Science 2025-05-15 Fei Yang

Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…

Computation and Language · Computer Science 2019-08-30 Jindřich Libovický , Pranava Madhyastha

Learning effective sentence representations is crucial for many Natural Language Processing (NLP) tasks, including semantic search, semantic textual similarity (STS), and clustering. While multiple transformer models have been developed for…

Computation and Language · Computer Science 2023-11-30 Liya Wang , Jason Chou , Dave Rouck , Alex Tien , Diane M Baumgartner

We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks. Sentence-level…

Computation and Language · Computer Science 2019-10-25 Xiaofei Ma , Zhiguo Wang , Patrick Ng , Ramesh Nallapati , Bing Xiang

Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to…

Computation and Language · Computer Science 2022-11-14 Yixuan Zhou , Changhe Song , Jingbei Li , Zhiyong Wu , Yanyao Bian , Dan Su , Helen Meng

We propose new static word embeddings optimised for sentence semantic representation. We first extract word embeddings from a pre-trained Sentence Transformer, and improve them with sentence-level principal component analysis, followed by…

Computation and Language · Computer Science 2025-10-01 Takashi Wada , Yuki Hirakawa , Ryotaro Shimizu , Takahiro Kawashima , Yuki Saito

Pre-trained language models perform well on a variety of linguistic tasks that require symbolic reasoning, raising the question of whether such models implicitly represent abstract symbols and rules. We investigate this question using the…

Computation and Language · Computer Science 2021-09-16 Jason Wei , Dan Garrette , Tal Linzen , Ellie Pavlick

Transformer neural networks, particularly Bidirectional Encoder Representations from Transformers (BERT), have shown remarkable performance across various tasks such as classification, text summarization, and question answering. However,…

Machine Learning · Computer Science 2025-02-18 Matteo Bonino , Giorgia Ghione , Giansalvo Cirrincione

Both humans and neural language models are able to perform subject-verb number agreement (SVA). In principle, semantics shouldn't interfere with this task, which only requires syntactic knowledge. In this work we test whether meaning…

Computation and Language · Computer Science 2022-09-22 Karim Lasri , Olga Seminck , Alessandro Lenci , Thierry Poibeau

While there has been much recent work studying how linguistic information is encoded in pre-trained sentence representations, comparatively little is understood about how these models change when adapted to solve downstream tasks. Using a…

Computation and Language · Computer Science 2020-05-01 Amil Merchant , Elahe Rahimtoroghi , Ellie Pavlick , Ian Tenney

Semantic similarity analysis and modeling is a fundamentally acclaimed task in many pioneering applications of natural language processing today. Owing to the sensation of sequential pattern recognition, many neural networks like RNNs and…

Computation and Language · Computer Science 2023-06-27 Praneeth Nemani , Satyanarayana Vollala

To achieve deep natural language understanding, syntactic constituent parsing plays a crucial role and is widely required by many artificial intelligence systems for processing both text and speech. A recent approach involves using standard…

Computation and Language · Computer Science 2026-05-14 Daniel Fernández-González , Cristina Outeiriño Cid

Pre-training models such as BERT have achieved great success in many natural language processing tasks. However, how to obtain better sentence representation through these pre-training models is still worthy to exploit. Previous work has…

Computation and Language · Computer Science 2021-03-30 Jianlin Su , Jiarun Cao , Weijie Liu , Yangyiwen Ou

Representing text into a multidimensional space can be done with sentence embedding models such as Sentence-BERT (SBERT). However, training these models when the data has a complex multilevel structure requires individually trained…

Computation and Language · Computer Science 2023-05-11 Paolo Tirotta , Akira Yuasa , Masashi Morita

The choice of sentence encoder architecture reflects assumptions about how a sentence's meaning is composed from its constituent words. We examine the contribution of these architectures by holding them randomly initialised and fixed,…

Computation and Language · Computer Science 2019-10-09 Joseph Enguehard , Dan Busbridge , Vitalii Zhelezniak , Nils Hammerla

Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In this work, we focus on BERT, a deep neural network that…

Computation and Language · Computer Science 2020-05-11 Timothee Mickus , Denis Paperno , Mathieu Constant , Kees van Deemter

Transformers underlie almost all state-of-the-art language models in computational linguistics, yet their cognitive adequacy as models of human sentence processing remains disputed. In this work, we use a surprisal-based linking mechanism…

Computation and Language · Computer Science 2026-03-18 Titus von der Malsburg , Sebastian Padó

Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word representation, called BERT, achieves the state-of-the-art…

Computation and Language · Computer Science 2020-06-02 Bin Wang , C. -C. Jay Kuo

This paper studies the performances of BERT combined with tree structure in short sentence ranking task. In retrieval-based question answering system, we retrieve the most similar question of the query question by ranking all the questions…

Computation and Language · Computer Science 2019-09-09 Tong Guo , Huilin Gao