Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence

• URL: http://arxiv.org/abs/2410.17161v2
• Date: Mon, 27 Jan 2025 21:17:48 GMT
• Title: Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
• Authors: İlker Işık, Ramazan Gokberk Cinbis, Ebru Aydin Gol,
• Abstract summary: We propose a novel approach for learning interchangeable tokens in language models. Our method addresses alpha-equivalence, the principle that renaming bound variables preserves semantics. Our method demonstrates promising generalization capabilities as well as a favorable inductive bias for alpha-equivalence.
• Score: 6.991281327290525
• License:
• Abstract: We propose a novel approach for learning interchangeable tokens in language models to obtain an extendable vocabulary that can generalize to new tokens. Our method addresses alpha-equivalence, the principle that renaming bound variables preserves semantics. This property arises in many formal languages such as temporal logics, where all proposition symbols represent the same concept but remain distinct. To handle such tokens, we develop a dual-part embedding approach. The first part is shared across all interchangeable tokens, enforcing that they represent the same core concept. The second part is randomly generated for each token, enabling distinguishability. As a baseline, we consider a simpler approach that uses alpha-renaming for data augmentation. We also present alpha-covariance, a metric for measuring robustness against alpha-conversions. When evaluated in a Transformer encoder-decoder model for solving linear temporal logic formulae and copying with extendable vocabulary, our method demonstrates promising generalization capabilities as well as a favorable inductive bias for alpha-equivalence.

Related papers

• Tokenization as Finite-State Transduction [24.19959327497118]
  We introduce a finite-state framework which can efficiently encode all possible tokenizations of a regular language. We show that Byte-Pair. Match (BPE) and MaxPiece (WordPiece) fit within this framework. An application of this is to guided generation, where the outputs of a language model are constrained to match some pattern.
  arXiv  Detail & Related papers  (2024-10-21T07:10:07Z)
• SEP: Self-Enhanced Prompt Tuning for Visual-Language Model [93.94454894142413]
  We introduce a novel approach named Self-Enhanced Prompt Tuning (SEP) SEP explicitly incorporates discriminative prior knowledge to enhance both textual-level and visual-level embeddings. Comprehensive evaluations across various benchmarks and tasks confirm SEP's efficacy in prompt tuning.
  arXiv  Detail & Related papers  (2024-05-24T13:35:56Z)
• Word Boundary Information Isn't Useful for Encoder Language Models [8.1305024841559]
  We train transformer encoders across four different training scales, and investigate several alternative approaches to including word boundary information. We find no substantial improvements from our alternative approaches, suggesting that modifying tokenisers to remove word boundary information isn't leading to a loss of useful information.
  arXiv  Detail & Related papers  (2024-01-15T19:21:08Z)
• Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency [71.42261918225773]
  Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
  arXiv  Detail & Related papers  (2023-05-31T16:47:20Z)
• Sequential Integrated Gradients: a simple but effective method for explaining language models [0.18459705687628122]
  We propose a new method for explaining language models called Sequential Integrated Gradients ( SIG) SIG computes the importance of each word in a sentence by keeping fixed every other words, only creatings between the baseline and word of interest. We show on various models and datasets that SIG proves to be a very effective method for explaining language models.
  arXiv  Detail & Related papers  (2023-05-25T08:44:11Z)
• Lexinvariant Language Models [84.2829117441298]
  Token embeddings, a mapping from discrete lexical symbols to continuous vectors, are at the heart of any language model (LM) We study textitlexinvariantlanguage models that are invariant to lexical symbols and therefore do not need fixed token embeddings in practice. We show that a lexinvariant LM can attain perplexity comparable to that of a standard language model, given a sufficiently long context.
  arXiv  Detail & Related papers  (2023-05-24T19:10:46Z)
• Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents [61.63208012250885]
  We formulate recognizing semantic differences as a token-level regression task. We study three unsupervised approaches that rely on a masked language model. Our results show that an approach based on word alignment and sentence-level contrastive learning has a robust correlation to gold labels.
  arXiv  Detail & Related papers  (2023-05-22T17:58:04Z)
• Fast End-to-End Speech Recognition via a Non-Autoregressive Model and Cross-Modal Knowledge Transferring from BERT [72.93855288283059]
  We propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once) The model consists of an encoder, a decoder, and a position dependent summarizer (PDS)
  arXiv  Detail & Related papers  (2021-02-15T15:18:59Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

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.