paper-with-me

Papers

A comparative evaluation and analysis of three generations of Distributional Semantic Models

2021-05-20 · Alessandro Lenci, Magnus Sahlgren, Patrick Jeuniaux, Amaru Cuba Gyllensten, Martina Miliani

Distributional semantics has deeply changed in the last decades. First, predict models stole the thunder from traditional count ones, and more recently both of them were replaced in many NLP applications by contextualized vectors produced by Transformer neural language models. Although an extensive body of research has been devoted to Distributional Semantic Model (DSM) evaluation, we still lack a thorough comparison with respect to tested models, semantic tasks, and benchmark datasets. Moreover, previous work has mostly focused on task-driven evaluation, instead of exploring the differences between the way models represent the lexical semantic space. In this paper, we perform a comprehensive evaluation of type distributional vectors, either produced by static DSMs or obtained by averaging the contextualized vectors generated by BERT. First of all, we investigate the performance of embeddings in several semantic tasks, carrying out an in-depth statistical analysis to identify the major factors influencing the behavior of DSMs. The results show that i.) the alleged superiority of predict based models is more apparent than real, and surely not ubiquitous and ii.) static DSMs surpass contextualized representations in most out-of-context semantic tasks and datasets. Furthermore, we borrow from cognitive neuroscience the methodology of Representational Similarity Analysis (RSA) to inspect the semantic spaces generated by distributional models. RSA reveals important differences related to the frequency and part-of-speech of lexical items.

📄 PDF Abstract BibTeX arXiv:2105.09825

Code (1)

Unipisa/DSMs-evaluation 공식 구현

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
WordPiece 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Improving the Distributional Alignment of LLMs using Supervision

2025-07-01 · Gauri Kambhatla, Sanjana Gautam, Angela Zhang, Alex Liu 외 arxiv

The ability to accurately align LLMs with diverse population groups on subjective questions would have great value. In this work, we show that adding simple supervision can more consistently improve the alignment of LLM-…

Challenging distributional models with a conceptual network of philosophical terms

2021-06-01 · NAACL 2021 4 · Yvette Oortwijn, Jelke Bloem, Pia Sommerauer, Francois Meyer 외

Computational linguistic research on language change through distributional semantic (DS) models has inspired researchers from fields such as philosophy and literary studies, who use these methods for the exploration and…

Philosophy

Beyond One Output: Visualizing and Comparing Distributions of Language Model Generations

2026-04-20 · Emily Reif, Claire Yang, Jared Hwang, Deniz Nazar 외 arxiv

Users typically interact with and evaluate language models via single outputs, but each output is just one sample from a broad distribution of possible completions. This interaction hides distributional structure such as…

Semantic Relatedness for All (Languages): A Comparative Analysis of Multilingual Semantic Relatedness Using Machine Translation

2018-05-16 · Andre Freitas, Siamak Barzegar, Juliano Efson Sales, Siegfried Handschuh 외

This paper provides a comparative analysis of the performance of four state-of-the-art distributional semantic models (DSMs) over 11 languages, contrasting the native language-specific models with the use of machine tran…

AllMachine TranslationTranslation

A Comparative Analysis of Expected and Distributional Reinforcement Learning

2019-01-30 · Clare Lyle, Pablo Samuel Castro, Marc G. Bellemare

Since their introduction a year ago, distributional approaches to reinforcement learning (distributional RL) have produced strong results relative to the standard approach which models expected values (expected RL). Howe…

Distributional Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)