Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings

Abstract

Given a small corpus D T pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite of the limited size of D T . These embeddings may be used in various tasks involving D T . A popular strategy in limited data settings is to adapt pretrained embeddings E trained on a large corpus. To correct for sense drift, fine-tuning, regularization, projection, and pivoting have been proposed recently. Among these, regularization informed by a word's corpus frequency performed well, but we improve upon it using a new regularizer based on the stability of its cooccurrence with other words. However, a thorough comparison across ten topics, spanning three tasks, with standardized settings of hyper-parameters, reveals that even the best embedding adaptation strategies provide small gains beyond well-tuned baselines, which many earlier comparisons ignored. In a bold departure from adapting pretrained embeddings, we propose using D T to probe, attend to, and borrow fragments from any large, topic-rich source corpus (such as Wikipedia), which need not be the corpus used to pretrain embeddings. This step is made scalable and practical by suitable indexing. We reach the surprising conclusion that even limited corpus augmentation is more useful than adapting embeddings, which suggests that non-dominant sense information may be irrevocably obliterated from pretrained embeddings and cannot be salvaged by adaptation. All our code and data splits will be made publicly available at https://github.com/vihari/ focussed_embs.

A Volume-Aware Positional Attention-Based Recurrent Neural Network for Stock Index Prediction

“…On the other hand, trading volume is also an important feature that provides valuable information, as past trading volume predicts both the magnitude and the persistence of future price momentum [26], i.e., the time step with higher trading volume is generally more important, and the attention mechanism should pay more attention to such time steps. Thus, inspired by several taskoriented attention mechanisms [27,28], we take advantage of this feature of stock performance prediction and propose volume-aware attention to incorporate the trading volume into the original attention distribution to achieve attention recalibration.…”