awesome-text-interpretability

a model-based tool to characterize and diagnose datasets

propose an interaction attribution and detection framework called Archipelago; scalable in real-world settings; more interpretable explanations than comparable methods, which is important for analyzing the impact of interactions on predictions

An open question, however, is how human rationales fare with these automatic metrics - do not necessarily perform well- reveal irrelevance and redundancy. Our work leads to actionable suggestions for evaluating and characterizing rationales.

The syntactic signatures available in Sentence and Jabberwocky LSTM representations are similar, and can be predicted from either the Sentence or Jabberwocky EEG. From our results, we can infer which LSTM representations encode semantic and/or syntactic information. We confirm using syntactic and semantic probing tasks. Our results show that there are similarities between the way the brain and an LSTM represent stimuli from both the Sentence (within-distribution) and Jabberwocky (out-of-distribution) conditions.

Retrieve tripes from knowledge graphs and combine them using rules to produce explanations for fact checking

two novel evaluation scores: (i) tracks prediction changes when removing facts, (ii) assesses whether the answer is contained in the explanation or not; Further strengthen the coupling of answer and explanation prediction in the model architecture and during training

variational word masks (VMASK) that are inserted into a neural text classifier, after the word embedding layer, and trained jointly with the model. VMASK learns to restrict the information of globally irrelevant or noisy wordlevel features flowing to subsequent network layers, hence forcing the model to focus on important features to make predictions

a differentiable training-framework to create models which output faithful rationales on a sentence level, by solely applying supervision on the target task; model solves the task based on each rationale individually and learns to assign high scores to those which solved the task best

Provide a hierarchical visualisation of how words contribute to phrases and how phrases contribute to bigger piesces of text and eventually to the overall prediction.

3 datasets and delexicalized chain representations in which repeated noun phrases are replaced by variables, thus turning them into generalized reasoning chains