LS-Tree: Model Interpretation When the Data Are Linguistic
We study the problem of interpreting trained classification models in the setting of linguistic data sets. Leveraging a parse tree, we propose to assign least-squares based importance scores to each word of an instance by exploiting syntactic constituency structure. We establish an axiomatic characterization of these importance scores by relating them to the Banzhaf value in coalitional game theory. Based on these importance scores, we develop a principled method for detecting and quantifying interactions between words in a sentence. We demonstrate that the proposed method can aid in interpretability and diagnostics for several widely-used language models.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Combining Prediction and Interpretation in Decision Trees (PrInDT) -- a Linguistic Example
In this paper, we show that conditional inference trees and ensembles are suitable methods for modeling linguistic variation. As against earlier linguistic applications, however, we claim that their suitability is strong…
Prediction4Couv: A New Treebank for French
The question of the type of text used as primary data in treebanks is of certain importance. First, it has an influence at the discourse level: an article is not organized in the same way as a novel or a technical docume…
Vocal Bursts Type PredictionA Fast Interpretable Fuzzy Tree Learner
Fuzzy rule-based systems have been mostly used in interpretable decision-making because of their interpretable linguistic rules. However, interpretability requires both sensible linguistic partitions and small rule-base …
Computational EfficiencyIncremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention
When reading temporarily ambiguous garden-path sentences, misinterpretations sometimes linger past the point of disambiguation. This phenomenon has traditionally been studied in psycholinguistic experiments using online …
Question AnsweringSentenceTask 2Incremental Tree Substitution Grammar for Parsing and Sentence Prediction
In this paper, we present the first incremental parser for Tree Substitution Grammar (TSG). A TSG allows arbitrarily large syntactic fragments to be combined into complete trees; we show how constraints (including lexica…
Language ModelingLanguage ModellingMachine TranslationPrediction+3