DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries

• URL: http://arxiv.org/abs/2405.16153v3
• Date: Wed, 19 Jun 2024 13:26:53 GMT
• Title: DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entries
• Authors: Xiaodong Liu,
• Abstract summary: This paper presents a significant improvement on the previous conference paper known as DefSent. We propose a novel method to progressively build entry embeddings not subject to the limitations. As a result, definition sentences can be projected into a quasi-isotropic or isotropic vector space of unlimited dictionary entries.
• Score: 5.317095505067784
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents a significant improvement on the previous conference paper known as DefSent. The prior study seeks to improve sentence embeddings of language models by projecting definition sentences into the vector space of dictionary entries. We discover that this approach is not fully explored due to the methodological limitation of using word embeddings of language models to represent dictionary entries. This leads to two hindrances. First, dictionary entries are constrained by the single-word vocabulary, and thus cannot be fully exploited. Second, semantic representations of language models are known to be anisotropic, but pre-processing word embeddings for DefSent is not allowed because its weight is frozen during training and tied to the prediction layer. In this paper, we propose a novel method to progressively build entry embeddings not subject to the limitations. As a result, definition sentences can be projected into a quasi-isotropic or isotropic vector space of unlimited dictionary entries, so that sentence embeddings of noticeably better quality are attainable. We abbreviate our approach as DefSent+ (a plus version of DefSent), involving the following strengths: 1) the task performance on measuring sentence similarities is significantly improved compared to DefSent; 2) when DefSent+ is used to further train data-augmented models like SIMCSE, SNCSE, and SynCSE, state-of-the-art performance on measuring sentence similarities can be achieved among the approaches without using manually labeled datasets; 3) DefSent+ is also competitive in feature-based transfer for NLP downstream tasks.

Related papers

• Word-Level Representation From Bytes For Language Modeling [46.28198397863388]
  Sub-word tokenization is not robust to noise and difficult to generalize to new languages. We introduce a cross-attention network that builds word-level representation directly from bytes, and a sub-word level prediction based on word-level hidden states. Byte2Word is on par with the strong sub-word baseline BERT but only takes up 10% of embedding size.
  arXiv  Detail & Related papers  (2022-11-23T03:11:13Z)
• Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework [68.04940365847543]
  We propose a semi-supervised sentence embedding framework, GenSE, that effectively leverages large-scale unlabeled data. Our method include three parts: 1) Generate: A generator/discriminator model is jointly trained to synthesize sentence pairs from open-domain unlabeled corpus; 2) Discriminate: Noisy sentence pairs are filtered out by the discriminator to acquire high-quality positive and negative sentence pairs; 3) Contrast: A prompt-based contrastive approach is presented for sentence representation learning with both annotated and synthesized data.
  arXiv  Detail & Related papers  (2022-10-30T10:15:21Z)
• Dict-BERT: Enhancing Language Model Pre-training with Dictionary [42.0998323292348]
  Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. In this work, we focus on enhancing language model pre-training by leveraging definitions of rare words in dictionaries. We propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions.
  arXiv  Detail & Related papers  (2021-10-13T04:29:14Z)
• Semantic-Preserving Adversarial Text Attacks [85.32186121859321]
  We propose a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) method to examine the vulnerability of deep models. Our method achieves the highest attack success rates and semantics rates by changing the smallest number of words compared with existing methods.
  arXiv  Detail & Related papers  (2021-08-23T09:05:18Z)
• DefSent: Sentence Embeddings using Definition Sentences [8.08585816311037]
  We propose DefSent, a sentence embedding method that uses definition sentences from a word dictionary. DefSent is more broadly applicable than methods using NLI datasets without constructing additional datasets.
  arXiv  Detail & Related papers  (2021-05-10T13:13:39Z)
• Dictionary-based Debiasing of Pre-trained Word Embeddings [28.378270372391498]
  We propose a method for debiasing pre-trained word embeddings using dictionaries. Our proposed method does not require the types of biases to be pre-defined in the form of word lists. Experimental results on standard benchmark datasets show that the proposed method can accurately remove unfair biases encoded in pre-trained word embeddings.
  arXiv  Detail & Related papers  (2021-01-23T15:44:23Z)
• On the Sentence Embeddings from Pre-trained Language Models [78.45172445684126]
  In this paper, we argue that the semantic information in the BERT embeddings is not fully exploited. We find that BERT always induces a non-smooth anisotropic semantic space of sentences, which harms its performance of semantic similarity. We propose to transform the anisotropic sentence embedding distribution to a smooth and isotropic Gaussian distribution through normalizing flows that are learned with an unsupervised objective.
  arXiv  Detail & Related papers  (2020-11-02T13:14:57Z)
• Grounded Compositional Outputs for Adaptive Language Modeling [59.02706635250856]
  A language model's vocabulary$-$typically selected before training and permanently fixed later$-$affects its size. We propose a fully compositional output embedding layer for language models. To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary.
  arXiv  Detail & Related papers  (2020-09-24T07:21:14Z)
• Attention Word Embedding [23.997145283950346]
  We introduce the Attention Word Embedding (AWE) model, which integrates the attention mechanism into the CBOW model. We also propose AWE-S, which incorporates subword information. We demonstrate that AWE and AWE-S outperform the state-of-the-art word embedding models both on a variety of word similarity datasets.
  arXiv  Detail & Related papers  (2020-06-01T14:47:48Z)
• Toward Better Storylines with Sentence-Level Language Models [54.91921545103256]
  We propose a sentence-level language model which selects the next sentence in a story from a finite set of fluent alternatives. We demonstrate the effectiveness of our approach with state-of-the-art accuracy on the unsupervised Story Cloze task.
  arXiv  Detail & Related papers  (2020-05-11T16:54:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.