paper-with-me

홈 › Papers

Squashed Shifted PMI Matrix: Bridging Word Embeddings and Hyperbolic Spaces

2020-02-27 · Zhenisbek Assylbekov, Alibi Jangeldin

We show that removing sigmoid transformation in the skip-gram with negative sampling (SGNS) objective does not harm the quality of word vectors significantly and at the same time is related to factorizing a squashed shifted PMI matrix which, in turn, can be treated as a connection probabilities matrix of a random graph. Empirically, such graph is a complex network, i.e. it has strong clustering and scale-free degree distribution, and is tightly connected with hyperbolic spaces. In short, we show the connection between static word embeddings and hyperbolic spaces through the squashed shifted PMI matrix using analytical and empirical methods.

📄 PDF Abstract BibTeX arXiv:2002.12005

Code (2)

zh3nis/BPMI 공식 구현 pytorch
zh3nis/SGNS 공식 구현 pytorch

Tasks

ClusteringWord Embeddings

Similar Papers 제목 키워드 기반

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

Enhanced Word Representations for Bridging Anaphora Resolution

2018-03-13 · NAACL 2018 6 · Yufang Hou

Most current models of word representations(e.g.,GloVe) have successfully captured fine-grained semantics. However, semantic similarity exhibited in these word embeddings is not suitable for resolving bridging anaphora, …

Bridging Anaphora ResolutionSemantic SimilaritySemantic Textual SimilarityWord Embeddings

A Deterministic Algorithm for Bridging Anaphora Resolution

2018-11-14 · EMNLP 2018 10 · Yufang Hou

Previous work on bridging anaphora resolution (Poesio et al., 2004; Hou et al., 2013b) use syntactic preposition patterns to calculate word relatedness. However, such patterns only consider NPs' head nouns and hence do n…

Bridging Anaphora ResolutionWord Embeddings

Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings

2017-11-15 · ACL 2018 7 · Shaohui Kuang, Junhui Li, António Branco, Weihua Luo 외

In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations betwe…

Machine TranslationSentenceTranslationWord Embeddings

Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition

2019-03-29 · Shane Settle, Kartik Audhkhasi, Karen Livescu, Michael Picheny

Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems. However, A2W systems can have difficulties at training ti…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1