paper-with-me

Papers

Word2vec Conjecture and A Limitative Result

2020-10-24 · Falcon Z. Dai

Being inspired by the success of \texttt{word2vec} \citep{mikolov2013distributed} in capturing analogies, we study the conjecture that analogical relations can be represented by vector spaces. Unlike many previous works that focus on the distributional semantic aspect of \texttt{word2vec}, we study the purely \emph{representational} question: can \emph{all} semantic word-word relations be represented by differences (or directions) of vectors? We call this the word2vec conjecture and point out some of its desirable implications. However, we will exhibit a class of relations that cannot be represented in this way, thus falsifying the conjecture and establishing a limitative result for the representability of semantic relations by vector spaces over fields of characteristic 0, e.g., real or complex numbers.

📄 PDF Abstract BibTeX arXiv:2010.12719

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Artifical intelligence and inherent mathematical difficulty

2024-08-01 · Walter Dean, Alberto Naibo

This paper explores the relationship of artificial intelligence to the task of resolving open questions in mathematics. We first present an updated version of a traditional argument that limitative results from computabi…

Automated Theorem Proving

A Short Note on the Exact Counting of Tree-Child Networks

2021-10-08 · Michael Fuchs, Hexuan Liu, Guan-Ru Yu

Tree-child networks are an important network class which are used in phylogenetics to model reticulate evolution. In a recent paper, Pons and Batle (2021) conjectured a relation between tree-child networks and certain wo…

Relation

LLM The Genius Paradox: A Linguistic and Math Expert's Struggle with Simple Word-based Counting Problems

2024-10-18 · Nan Xu, Xuezhe Ma

Interestingly, LLMs yet struggle with some basic tasks that humans find trivial to handle, e.g., counting the number of character r's in the word "strawberry". There are several popular conjectures (e.g., tokenization, a…

In-Context LearningMath

Neural Word Embedding as Implicit Matrix Factorization

2014-12-01 · NeurIPS 2014 12 · Omer Levy, Yoav Goldberg

We analyze skip-gram with negative-sampling (SGNS), a word embedding method introduced by Mikolov et al., and show that it is implicitly factorizing a word-context matrix, whose cells are the pointwise mutual information…

Word Similarity

Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words

2022-05-10 · ACL 2022 5 · Kaitlyn Zhou, Kawin Ethayarajh, Dallas Card, Dan Jurafsky

Cosine similarity of contextual embeddings is used in many NLP tasks (e.g., QA, IR, MT) and metrics (e.g., BERTScore). Here, we uncover systematic ways in which word similarities estimated by cosine over BERT embeddings …