CAWA: An Attention-Network for Credit Attribution

TL;DR

CAWA is a neural network model that uses attention mechanisms and distant supervision to improve credit attribution in documents, outperforming existing methods in accuracy and flexibility.

Contribution

CAWA introduces an end-to-end attention-based framework that models sentences as distributions over classes, eliminating the need for sentence-level labeled data.

Findings

CAWA outperforms state-of-the-art credit attribution methods.

CAWA achieves better multilabel classification results.

Model effectively uses distant supervision for credit attribution.

Abstract

Credit attribution is the task of associating individual parts in a document with their most appropriate class labels. It is an important task with applications to information retrieval and text summarization. When labeled training data is available, traditional approaches for sequence tagging can be used for credit attribution. However, generating such labeled datasets is expensive and time-consuming. In this paper, we present "Credit Attribution With Attention (CAWA)", a neural-network-based approach, that instead of using sentence-level labeled data, uses the set of class labels that are associated with an entire document as a source of distant-supervision. CAWA combines an attention mechanism with a multilabel classifier into an end-to-end learning framework to perform credit attribution. CAWA labels the individual sentences from the input document using the resultant attention-weights. CAWA improves upon the state-of-the-art credit attribution approach by not constraining a sentence to belong to just one class, but modeling each sentence as a distribution over all classes, leading to better modeling of semantically-similar classes. Experiments on the credit attribution task on a variety of datasets show that the sentence class labels generated by CAWA outperform the competing approaches. Additionally, on the multilabel text classification task, CAWA performs better than the competing credit attribution approaches.