中文
相关论文

相关论文: Rotations and Interpretability of Word Embeddings:…

200 篇论文

As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation. They capture semantic and syntactic relations among words but the…

计算与语言 · 计算机科学 2020-07-03 Lutfi Kerem Senel , Ihsan Utlu , Furkan Şahinuç , Haldun M. Ozaktas , Aykut Koç

A notable property of word embeddings is that word relationships can exist as linear substructures in the embedding space. For example, $\textit{gender}$ corresponds to $\vec{\textit{woman}} - \vec{\textit{man}}$ and $\vec{\textit{queen}} -…

计算与语言 · 计算机科学 2019-09-06 Kawin Ethayarajh

Distributed vector representations for natural language vocabulary get a lot of attention in contemporary computational linguistics. This paper summarizes the experience of applying neural network language models to the task of calculating…

计算与语言 · 计算机科学 2015-05-01 Andrey Kutuzov , Igor Andreev

Word embeddings are useful for a wide variety of tasks, but they lack interpretability. By rotating word spaces, interpretable dimensions can be identified while preserving the information contained in the embeddings without any loss. In…

计算与语言 · 计算机科学 2019-09-16 Philipp Dufter , Hinrich Schütze

Word embeddings are widely used in Natural Language Processing, mainly due to their success in capturing semantic information from massive corpora. However, their creation process does not allow the different meanings of a word to be…

计算与语言 · 计算机科学 2017-06-22 Massimiliano Mancini , Jose Camacho-Collados , Ignacio Iacobacci , Roberto Navigli

Many loss functions in representation learning are invariant under a continuous symmetry transformation. For example, the loss function of word embeddings (Mikolov et al., 2013) remains unchanged if we simultaneously rotate all word and…

机器学习 · 统计学 2020-07-21 Robert Bamler , Stephan Mandt

While important properties of word vector representations have been studied extensively, far less is known about the properties of sentence vector representations. Word vectors are often evaluated by assessing to what degree they exhibit…

计算与语言 · 计算机科学 2020-03-10 Xunjie Zhu , Gerard de Melo

Representing words by vectors, or embeddings, enables computational reasoning and is foundational to automating natural language tasks. For example, if word embeddings of similar words contain similar values, word similarity can be readily…

计算与语言 · 计算机科学 2022-02-02 Carl Allen

Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…

计算与语言 · 计算机科学 2021-12-13 Elizabeth Salesky , David Etter , Matt Post

The problem of comparing two bodies of text and searching for words that differ in their usage between them arises often in digital humanities and computational social science. This is commonly approached by training word embeddings on each…

计算与语言 · 计算机科学 2021-12-30 Hila Gonen , Ganesh Jawahar , Djamé Seddah , Yoav Goldberg

Word embedding models offer continuous vector representations that can capture rich contextual semantics based on their word co-occurrence patterns. While these word vectors can provide very effective features used in many NLP tasks such as…

计算与语言 · 计算机科学 2017-02-27 Cem Safak Sahin , Rajmonda S. Caceres , Brandon Oselio , William M. Campbell

Word embeddings have become a standard resource in the toolset of any Natural Language Processing practitioner. While monolingual word embeddings encode information about words in the context of a particular language, cross-lingual…

计算与语言 · 计算机科学 2020-11-12 Yerai Doval , Jose Camacho-Collados , Luis Espinosa-Anke , Steven Schockaert

Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…

计算与语言 · 计算机科学 2020-03-04 Yerai Doval , Jose Camacho-Collados , Luis Espinosa-Anke , Steven Schockaert

While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be…

计算与语言 · 计算机科学 2016-08-23 Jifan Chen , Kan Chen , Xipeng Qiu , Qi Zhang , Xuanjing Huang , Zheng Zhang

Vector space word representations are learned from distributional information of words in large corpora. Although such statistics are semantically informative, they disregard the valuable information that is contained in semantic lexicons…

计算与语言 · 计算机科学 2015-03-24 Manaal Faruqui , Jesse Dodge , Sujay K. Jauhar , Chris Dyer , Eduard Hovy , Noah A. Smith

Word embeddings are now ubiquitous forms of word representation in natural language processing. There have been applications of word embeddings for monolingual word sense disambiguation (WSD) in English, but few comparisons have been done.…

计算与语言 · 计算机科学 2017-04-11 Hong Jin Kang , Tao Chen , Muthu Kumar Chandrasekaran , Min-Yen Kan

Usually bilingual word vectors are trained "online". Mikolov et al. showed they can also be found "offline", whereby two pre-trained embeddings are aligned with a linear transformation, using dictionaries compiled from expert knowledge. In…

计算与语言 · 计算机科学 2017-02-14 Samuel L. Smith , David H. P. Turban , Steven Hamblin , Nils Y. Hammerla

The paper introduces manually annotated test sets for the task of tracing diachronic (temporal) semantic shifts in Russian. The two test sets are complementary in that the first one covers comparatively strong semantic changes occurring to…

计算与语言 · 计算机科学 2019-07-31 Vadim Fomin , Daria Bakshandaeva , Julia Rodina , Andrey Kutuzov

We present an introductory investigation into continuous-space vector representations of sentences. We acquire pairs of very similar sentences differing only by a small alterations (such as change of a noun, adding an adjective, noun or…

计算与语言 · 计算机科学 2019-10-09 Petra Barančíková , Ondřej Bojar

This paper evaluates morphology-based embeddings for English and Russian languages. Despite the interest and introduction of several morphology-based word embedding models in the past and acclaimed performance improvements on word…

计算与语言 · 计算机科学 2021-03-15 Vitaly Romanov , Albina Khusainova
‹ 上一页 1 2 3 10 下一页 ›