Assessing Word Importance Using Models Trained for Semantic Tasks
Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve semantic task: Natural Language Inference and Paraphrase Identification. Using an attribution method aimed to explain the predictions of these models, we derive importance scores for each input token. We evaluate their relevance using a so-called cross-task evaluation: Analyzing the performance of one model on an input masked according to the other model's weight, we show that our method is robust with respect to the choice of the initial task. Additionally, we investigate the scores from the syntax point of view and observe interesting patterns, e.g. words closer to the root of a syntactic tree receive higher importance scores. Altogether, these observations suggest that our method can be used to identify important words in sentences without any explicit word importance labeling in training.
Code (1)
Tasks
Natural Language InferenceParaphrase IdentificationSimilar Papers 제목 키워드 기반
Assessing the Impact of Anisotropy in Neural Representations of Speech: A Case Study on Keyword Spotting
Pretrained speech representations like wav2vec2 and HuBERT exhibit strong anisotropy, leading to high similarity between random embeddings. While widely observed, the impact of this property on downstream tasks remains u…
Dynamic Time WarpingKeyword SpottingContextualizing the Limits of Model & Evaluation Dataset Curation on Semantic Similarity Classification Tasks
This paper demonstrates how the limitations of pre-trained models and open evaluation datasets factor into assessing the performance of binary semantic similarity classification tasks. As (1) end-user-facing documentatio…
ClassificationFrictionSemantic SimilaritySemantic Textual SimilarityAssessing the Lexico-Semantic Relational Knowledge Captured by Word and Concept Embeddings
Deep learning currently dominates the benchmarks for various NLP tasks and, at the basis of such systems, words are frequently represented as embeddings --vectors in a low dimensional space-- learned from large text corp…
BAHP: Benchmark of Assessing Word Embeddings in Historical Portuguese
High quality distributional models can capture lexical and semantic relations between words. Hence, researchers design various intrinsic tasks to test whether such relations are captured. However, most of the intrinsic t…
Outlier DetectionWord EmbeddingsWord Rotator's Distance
A key principle in assessing textual similarity is measuring the degree of semantic overlap between two texts by considering the word alignment. Such alignment-based approaches are intuitive and interpretable; however, t…
Semantic SimilaritySemantic Textual SimilaritySentenceWord Alignment+1