paper-with-me

Papers

Sentence Analogies: Exploring Linguistic Relationships and Regularities in Sentence Embeddings

2020-03-09 · Xunjie Zhu, Gerard de Melo

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 regularities with regard to relationships of the sort considered in word analogies. In this paper, we investigate to what extent commonly used sentence vector representation spaces as well reflect certain kinds of regularities. We propose a number of schemes to induce evaluation data, based on lexical analogy data as well as semantic relationships between sentences. Our experiments consider a wide range of sentence embedding methods, including ones based on BERT-style contextual embeddings. We find that different models differ substantially in their ability to reflect such regularities.

📄 PDF Abstract BibTeX arXiv:2003.04036

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSentence EmbeddingSentence-EmbeddingSentence Embeddings

Similar Papers 제목 키워드 기반

Sentence Analogies: Linguistic Regularities in Sentence Embeddings

2020-12-01 · COLING 2020 8 · Xunjie Zhu, Gerard de Melo

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 de…

SentenceSentence EmbeddingSentence-EmbeddingSentence Embeddings

Insights into Analogy Completion from the Biomedical Domain

2017-06-07 · WS 2017 8 · Denis Newman-Griffis, Albert M. Lai, Eric Fosler-Lussier

Analogy completion has been a popular task in recent years for evaluating the semantic properties of word embeddings, but the standard methodology makes a number of assumptions about analogies that do not always hold, ei…

Word Embeddings

Analogies minus analogy test: measuring regularities in word embeddings

2020-10-07 · CONLL 2020 · Louis Fournier, Emmanuel Dupoux, Ewan Dunbar

Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim. We decompose and empirically analyze the classic arithm…

Word Embeddings

Paraphrases do not explain word analogies

2021-02-23 · EACL 2021 2 · Louis Fournier, Ewan Dunbar

Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between "jump" and "jumped" will be in a similar direction to that of "walk" and "walked," and so on). Se…

Word Embeddings

Long-form analogies generated by chatGPT lack human-like psycholinguistic properties

2023-06-07 · S. M. Seals, Valerie L. Shalin

Psycholinguistic analyses provide a means of evaluating large language model (LLM) output and making systematic comparisons to human-generated text. These methods can be used to characterize the psycholinguistic properti…

FormLanguage ModelingLanguage ModellingLarge Language Model