Recent unsupervised topic modelling approaches that use clustering techniques on word, token or document embeddings can extract coherent topics.A common limitation of such approaches is that they reveal nothing about inter-topic relationships which are essential in many real-world application domains.We present an unsupervised topic modelling method which harnesses Topological Data Analysis (TDA) to extract a topological skeleton of the manifold upon which contextualised word embeddings lie.We demonstrate that our approach, which performs on par with a recent baseline, is able to construct a network of coherent topics together with meaningful relationships between them.

While widely used in industry, recurrent neural networks (RNNs) are known to have deficiencies in dealing with long sequences (e.g. slow inference, vanishing gradients etc.). Recent research has attempted to accelerate RNN models by developing mechanisms to skip irrelevant words in input. Due to the lack of labelled data, it remains as a challenge to decide which words to skip, especially for low-resource classification tasks. In this paper, we propose Knowledge-AwareLeap-LSTM (KALL), a novel architecture which integrates prior human knowledge (created either manually or automatically) like in-domain keywords, terminologies or lexicons into Leap-LSTM to partially supervise the skipping process. More specifically, we propose a knowledge-oriented cost function for KALL; furthermore, we propose two strategies to integrate the knowledge: (1) the Factored KALL approach involves a keyword indicator as a soft constraint for the skip-ping process, and (2) the Gated KALL enforces the inclusion of keywords while maintaining a differentiable network in training. Experiments on different public datasets show that our approaches are1.1x~2.6x faster than LSTM with better accuracy and 23.6x faster than XLNet in a resource-limited CPU-only environment.

Recurrent neural networks (RNNs) suffer from well-known limitations and complications which include slow inference and vanishing gradients when processing long sequences in text classification.Recent studies have attempted to accelerate RNNs via various ad hoc mechanisms to skip irrelevant words in the input.However, word skipping approaches proposed to date effectively stop at each or a given time step to decide whether or not a given input word should be skipped, breaking the coherence of input processing in RNNs.Furthermore, current methods cannot change skip rates during inference and are consequently unable to support different skip rates in demanding real-world conditions.To overcome these limitations, we propose Pointer-LSTM, a novel LSTM framework which relies on a pointer network to select important words for target prediction.The model maintains a coherent input process for the LSTM modules and makes it possible to change the skip rate during inference.Our evaluation on four public data sets demonstrates that Pointer-LSTM (a) is 1.1x∼3.5xfaster than the standard LSTM architecture; (b) is more accurate than Leap-LSTM (the state-of-the-art LSTM skipping model) at high skip rates; and (c) reaches robust accuracy levels even when the skip rate is changed during inference.