SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings

• URL: http://arxiv.org/abs/2301.04704v1
• Date: Wed, 11 Jan 2023 20:25:53 GMT
• Title: SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings
• Authors: Jan Engler, Sandipan Sikdar, Marlene Lutz and Markus Strohmaier
• Abstract summary: Adding interpretability to word embeddings represents an area of active research in text representation. We present SensePOLAR, an extension of the original POLAR framework that enables word-sense aware interpretability for pre-trained contextual word embeddings.
• Score: 4.479834103607384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adding interpretability to word embeddings represents an area of active research in text representation. Recent work has explored thepotential of embedding words via so-called polar dimensions (e.g. good vs. bad, correct vs. wrong). Examples of such recent approaches include SemAxis, POLAR, FrameAxis, and BiImp. Although these approaches provide interpretable dimensions for words, they have not been designed to deal with polysemy, i.e. they can not easily distinguish between different senses of words. To address this limitation, we present SensePOLAR, an extension of the original POLAR framework that enables word-sense aware interpretability for pre-trained contextual word embeddings. The resulting interpretable word embeddings achieve a level of performance that is comparable to original contextual word embeddings across a variety of natural language processing tasks including the GLUE and SQuAD benchmarks. Our work removes a fundamental limitation of existing approaches by offering users sense aware interpretations for contextual word embeddings.

Related papers

• Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation [100.81837601210597]
  We propose Concept Curation (CoCu) to bridge the gap between visual and textual semantics in pre-training data. CoCu achieves superb zero-shot transfer performance and greatly boosts language-supervised segmentation baseline by a large margin.
  arXiv  Detail & Related papers  (2023-09-24T00:05:39Z)
• Textual Entailment Recognition with Semantic Features from Empirical Text Representation [60.31047947815282]
  A text entails a hypothesis if and only if the true value of the hypothesis follows the text. In this paper, we propose a novel approach to identifying the textual entailment relationship between text and hypothesis. We employ an element-wise Manhattan distance vector-based feature that can identify the semantic entailment relationship between the text-hypothesis pair.
  arXiv  Detail & Related papers  (2022-10-18T10:03:51Z)
• 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)
• A Survey On Neural Word Embeddings [0.4822598110892847]
  The study of meaning in natural language processing relies on the distributional hypothesis. The revolutionary idea of distributed representation for a concept is close to the working of a human mind. Neural word embeddings transformed the whole field of NLP by introducing substantial improvements in all NLP tasks.
  arXiv  Detail & Related papers  (2021-10-05T03:37:57Z)
• 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)
• LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution [76.615287796753]
  We introduce LexSubCon, an end-to-end lexical substitution framework based on contextual embedding models. This is achieved by combining contextual information with knowledge from structured lexical resources. Our experiments show that LexSubCon outperforms previous state-of-the-art methods on LS07 and CoInCo benchmark datasets.
  arXiv  Detail & Related papers  (2021-07-11T21:25:56Z)
• Interactive Re-Fitting as a Technique for Improving Word Embeddings [0.0]
  We make it possible for humans to adjust portions of a word embedding space by moving sets of words closer to one another. Our approach allows users to trigger selective post-processing as they interact with and assess potential bias in word embeddings.
  arXiv  Detail & Related papers  (2020-09-30T21:54:22Z)
• SLAM-Inspired Simultaneous Contextualization and Interpreting for Incremental Conversation Sentences [0.0]
  We propose a method to dynamically estimate the context and interpretations of polysemous words in sequential sentences. By using the SCAIN algorithm, we can sequentially optimize the interdependence between context and word interpretation while obtaining new interpretations online.
  arXiv  Detail & Related papers  (2020-05-29T16:40:27Z)
• A Survey on Contextual Embeddings [48.04732268018772]
  Contextual embeddings assign each word a representation based on its context, capturing uses of words across varied contexts and encoding knowledge that transfers across languages. We review existing contextual embedding models, cross-lingual polyglot pre-training, the application of contextual embeddings in downstream tasks, model compression, and model analyses.
  arXiv  Detail & Related papers  (2020-03-16T15:22:22Z)
• A Deep Neural Framework for Contextual Affect Detection [51.378225388679425]
  A short and simple text carrying no emotion can represent some strong emotions when reading along with its context. We propose a Contextual Affect Detection framework which learns the inter-dependence of words in a sentence.
  arXiv  Detail & Related papers  (2020-01-28T05:03:15Z)
• The POLAR Framework: Polar Opposites Enable Interpretability of Pre-Trained Word Embeddings [6.894744675083238]
  We introduce POLAR - a framework that adds interpretability to pre-trained word embeddings via the adoption of semantic differentials. We demonstrate the effectiveness of our framework by deploying it to various downstream tasks. We also show that the interpretable dimensions selected by our framework align with human judgement.
  arXiv  Detail & Related papers  (2020-01-27T15:58:57Z)

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.