VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models

• URL: http://arxiv.org/abs/2203.07504v1
• Date: Mon, 14 Mar 2022 21:29:38 GMT
• Title: VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
• Abstract summary: VAST, the Valence-Assessing Semantics Test, is a novel intrinsic evaluation task for contextualized word embeddings. We show that VAST is useful for 7 other LMs, and can be used in 7 languages. We also show that 8 of 10 WEAT bias tests, which compare differences in word embedding associations between groups of words, exhibit more stereotype-congruent biases after isolating semantics.
• Score: 3.4157048274143316
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: VAST, the Valence-Assessing Semantics Test, is a novel intrinsic evaluation task for contextualized word embeddings (CWEs). VAST uses valence, the association of a word with pleasantness, to measure the correspondence of word-level LM semantics with widely used human judgments, and examines the effects of contextualization, tokenization, and LM-specific geometry. Because prior research has found that CWEs from GPT-2 perform poorly on other intrinsic evaluations, we select GPT-2 as our primary subject, and include results showing that VAST is useful for 7 other LMs, and can be used in 7 languages. GPT-2 results show that the semantics of a word incorporate the semantics of context in layers closer to model output, such that VAST scores diverge between our contextual settings, ranging from Pearson's rho of .55 to .77 in layer 11. We also show that multiply tokenized words are not semantically encoded until layer 8, where they achieve Pearson's rho of .46, indicating the presence of an encoding process for multiply tokenized words which differs from that of singly tokenized words, for which rho is highest in layer 0. We find that a few neurons with values having greater magnitude than the rest mask word-level semantics in GPT-2's top layer, but that word-level semantics can be recovered by nullifying non-semantic principal components: Pearson's rho in the top layer improves from .32 to .76. After isolating semantics, we show the utility of VAST for understanding LM semantics via improvements over related work on four word similarity tasks, with a score of .50 on SimLex-999, better than the previous best of .45 for GPT-2. Finally, we show that 8 of 10 WEAT bias tests, which compare differences in word embedding associations between groups of words, exhibit more stereotype-congruent biases after isolating semantics, indicating that non-semantic structures in LMs also mask biases.

Related papers

• Context-Aware Distillation and Ablation for Text2DSL [78.29352305480285]
  We replace prompt-only synthetic generation with context-aware distillation.<n>A teacher large language model operates under an explicitly defined structured context.<n>This scales the verified PolkitBench corpus from 4,204 to 10,073 pairs.
  arXiv  Detail & Related papers  (2026-06-21T16:27:24Z)
• Tomato, Tomahto, Tomate: Measuring the Role of Shared Semantics among Subwords in Multilingual Language Models [88.07940818022468]
  We take an initial step on measuring the role of shared semantics among subwords in the encoder-only multilingual language models (mLMs) We form "semantic tokens" by merging the semantically similar subwords and their embeddings. inspections on the grouped subwords show that they exhibit a wide range of semantic similarities.
  arXiv  Detail & Related papers  (2024-11-07T08:38:32Z)
• Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective [50.261681681643076]
  We propose a novel metric called SemVarEffect and a benchmark named SemVarBench to evaluate the causality between semantic variations in inputs and outputs in text-to-image synthesis. Our work establishes an effective evaluation framework that advances the T2I synthesis community's exploration of human instruction understanding.
  arXiv  Detail & Related papers  (2024-10-14T08:45:35Z)
• Breaking Down Word Semantics from Pre-trained Language Models through Layer-wise Dimension Selection [0.0]
  This paper aims to disentangle semantic sense from BERT by applying a binary mask to middle outputs across the layers. The disentangled embeddings are evaluated through binary classification to determine if the target word in two different sentences has the same meaning.
  arXiv  Detail & Related papers  (2023-10-08T11:07:19Z)
• Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics Interface of LMs Through Agentivity [68.8204255655161]
  We present the semantic notion of agentivity as a case study for probing such interactions. This suggests LMs may potentially serve as more useful tools for linguistic annotation, theory testing, and discovery.
  arXiv  Detail & Related papers  (2023-05-29T16:24:01Z)
• The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative [7.03497683558609]
  Construction Grammar (CxG) is a paradigm from cognitive linguistics emphasising the connection between syntax and semantics. We present an investigation of their capability to classify and understand one of the most commonly studied constructions, the English comparative correlative (CC) Our results show that all three investigated PLMs are able to recognise the structure of the CC but fail to use its meaning.
  arXiv  Detail & Related papers  (2022-10-24T13:01:24Z)
• Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations [3.4157048274143316]
  We compare the effects of contrastive visual semantic pretraining on contextualized English language representations formed by GPT-2 and CLIP. We find that contrastive visual semantic pretraining significantly mitigates the anisotropy found in contextualized word embeddings from GPT-2. Our results indicate that high anisotropy is not an inevitable consequence of contextualization.
  arXiv  Detail & Related papers  (2022-03-14T21:42:13Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• SChME at SemEval-2020 Task 1: A Model Ensemble for Detecting Lexical Semantic Change [58.87961226278285]
  This paper describes SChME, a method used in SemEval-2020 Task 1 on unsupervised detection of lexical semantic change. SChME usesa model ensemble combining signals of distributional models (word embeddings) and wordfrequency models where each model casts a vote indicating the probability that a word sufferedsemantic change according to that feature.
  arXiv  Detail & Related papers  (2020-12-02T23:56:34Z)
• SST-BERT at SemEval-2020 Task 1: Semantic Shift Tracing by Clustering in BERT-based Embedding Spaces [63.17308641484404]
  We propose to identify clusters among different occurrences of each target word, considering these as representatives of different word meanings. Disagreements in obtained clusters naturally allow to quantify the level of semantic shift per each target word in four target languages. Our approach performs well both measured separately (per language) and overall, where we surpass all provided SemEval baselines.
  arXiv  Detail & Related papers  (2020-10-02T08:38:40Z)
• BLiMP: The Benchmark of Linguistic Minimal Pairs for English [23.2834990762859]
  The Benchmark of Linguistic Minimal Pairs (shortened to BLiMP) is a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English. BLiMP consists of 67 sub-datasets, each containing 1000 minimal pairs isolating specific contrasts in syntax, morphology, or semantics. We find that state-of-the-art models identify morphological contrasts reliably, but they struggle with semantic restrictions on the distribution of quantifiers and negative polarity items.
  arXiv  Detail & Related papers  (2019-12-02T05:42:41Z)

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.