Neighboring Words Affect Human Interpretation of Saliency Explanations

• URL: http://arxiv.org/abs/2305.02679v2
• Date: Sat, 6 May 2023 12:22:19 GMT
• Title: Neighboring Words Affect Human Interpretation of Saliency Explanations
• Authors: Alon Jacovi, Hendrik Schuff, Heike Adel, Ngoc Thang Vu, Yoav Goldberg
• Abstract summary: Word-level saliency explanations are often used to communicate feature-attribution in text-based models. Recent studies found that superficial factors such as word length can distort human interpretation of the communicated saliency scores. We investigate how the marking of a word's neighboring words affect the explainee's perception of the word's importance in the context of a saliency explanation.
• Score: 65.29015910991261
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Word-level saliency explanations ("heat maps over words") are often used to communicate feature-attribution in text-based models. Recent studies found that superficial factors such as word length can distort human interpretation of the communicated saliency scores. We conduct a user study to investigate how the marking of a word's neighboring words affect the explainee's perception of the word's importance in the context of a saliency explanation. We find that neighboring words have significant effects on the word's importance rating. Concretely, we identify that the influence changes based on neighboring direction (left vs. right) and a-priori linguistic and computational measures of phrases and collocations (vs. unrelated neighboring words). Our results question whether text-based saliency explanations should be continued to be communicated at word level, and inform future research on alternative saliency explanation methods.

Related papers

• Survey in Characterization of Semantic Change [0.1474723404975345]
  Understanding the meaning of words is vital for interpreting texts from different cultures. Semantic changes can potentially impact the quality of the outcomes of computational linguistics algorithms.
  arXiv  Detail & Related papers  (2024-02-29T12:13:50Z)
• Quantifying the redundancy between prosody and text [67.07817268372743]
  We use large language models to estimate how much information is redundant between prosody and the words themselves. We find a high degree of redundancy between the information carried by the words and prosodic information across several prosodic features. Still, we observe that prosodic features can not be fully predicted from text, suggesting that prosody carries information above and beyond the words.
  arXiv  Detail & Related papers  (2023-11-28T21:15:24Z)
• Lost in Context? On the Sense-wise Variance of Contextualized Word Embeddings [11.475144702935568]
  We quantify how much the contextualized embeddings of each word sense vary across contexts in typical pre-trained models. We find that word representations are position-biased, where the first words in different contexts tend to be more similar.
  arXiv  Detail & Related papers  (2022-08-20T12:27:25Z)
• Human Interpretation of Saliency-based Explanation Over Text [65.29015910991261]
  We study saliency-based explanations over textual data. We find that people often mis-interpret the explanations. We propose a method to adjust saliencies based on model estimates of over- and under-perception.
  arXiv  Detail & Related papers  (2022-01-27T15:20:32Z)
• Disambiguatory Signals are Stronger in Word-initial Positions [48.18148856974974]
  We point out the confounds in existing methods for comparing the informativeness of segments early in the word versus later in the word. We find evidence across hundreds of languages that indeed there is a cross-linguistic tendency to front-load information in words.
  arXiv  Detail & Related papers  (2021-02-03T18:19:16Z)
• Speakers Fill Lexical Semantic Gaps with Context [65.08205006886591]
  We operationalise the lexical ambiguity of a word as the entropy of meanings it can take. We find significant correlations between our estimate of ambiguity and the number of synonyms a word has in WordNet. This suggests that, in the presence of ambiguity, speakers compensate by making contexts more informative.
  arXiv  Detail & Related papers  (2020-10-05T17:19:10Z)
• Characterizing the Effect of Sentence Context on Word Meanings: Mapping Brain to Behavior [0.0]
  This paper aims to answer whether the subjects are aware of such changes and agree with them. Subjects were asked to judge how the word change from their generic meaning when the words were used in specific sentences. Results support the hypothesis that word meaning change systematically depending on sentence context.
  arXiv  Detail & Related papers  (2020-07-27T20:12:30Z)
• Prosody leaks into the memories of words [2.309770674164469]
  The average predictability (aka informativity) of a word in context has been shown to condition word duration. This study extends past work in two directions; it investigated informativity effects in another large language, Mandarin Chinese. Results indicated that words with low informativity have shorter durations, replicating the effect found in English.
  arXiv  Detail & Related papers  (2020-05-29T17:58:33Z)
• Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods [51.34667808471513]
  We investigate the importance of two factors, semantic sparsity and frequency growth rates of semantic neighbors, formalized in the distributional semantics paradigm. We show that both factors are predictive word emergence although we find more support for the latter hypothesis.
  arXiv  Detail & Related papers  (2020-01-21T19:09:49Z)

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.