Related papers: Topic Sensitive Neural Headline Generation

Recent neural headline generation models have shown great results, but are generally trained on very large datasets. We focus our efforts on improving headline quality on smaller datasets by the means of pretraining. We propose new methods…

Topic models have evolved from conventional Bayesian probabilistic models to recent Neural Topic Models (NTMs). Although NTMs have shown promising performance when trained and tested on a specific corpus, their generalisation ability across…

We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. In particular, we assume that global latent topics are shared across documents, a word is generated…

Topic modelling is a popular unsupervised method for identifying the underlying themes in document collections that has many applications in information retrieval. A topic is usually represented by a list of terms ranked by their…

Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret.…

Context information around words helps in determining their actual meaning, for example "networks" used in contexts of artificial neural networks or biological neuron networks. Generative topic models infer topic-word distributions, taking…

We propose a novel document generation process based on hierarchical latent tree models (HLTMs) learned from data. An HLTM has a layer of observed word variables at the bottom and multiple layers of latent variables on top. For each…

Topic modelling is a pivotal unsupervised machine learning technique for extracting valuable insights from large document collections. Existing neural topic modelling methods often encode contextual information of documents, while ignoring…

The growing complexity of legal cases has lead to an increasing interest in legal information retrieval systems that can effectively satisfy user-specific information needs. However, such downstream systems typically require documents to be…

Pre-trained language models (e.g. BART) have shown impressive results when fine-tuned on large summarization datasets. However, little is understood about this fine-tuning process, including what knowledge is retained from pre-training time…

Topic models are popular statistical tools for detecting latent semantic topics in a text corpus. They have been utilized in various applications across different fields. However, traditional topic models have some limitations, including…

We present an approach to generating topics using a model trained only for document title generation, with zero examples of topics given during training. We leverage features that capture the relevance of a candidate span in a document for…

Headline generation is a special type of text summarization task. While the amount of available training data for this task is almost unlimited, it still remains challenging, as learning to generate headlines for news articles implies that…

Language models are typically applied at the sentence level, without access to the broader document context. We present a neural language model that incorporates document context in the form of a topic model-like architecture, thus…

Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with…

We present a new topic model that generates documents by sampling a topic for one whole sentence at a time, and generating the words in the sentence using an RNN decoder that is conditioned on the topic of the sentence. We argue that this…

We consider the problem of automatically generating a narrative biomedical evidence summary from multiple trial reports. We evaluate modern neural models for abstractive summarization of relevant article abstracts from systematic reviews…

The encoder-decoder model is widely used in natural language generation tasks. However, the model sometimes suffers from repeated redundant generation, misses important phrases, and includes irrelevant entities. Toward solving these…

Certain type of documents such as tweets are collected by specifying a set of keywords. As topics of interest change with time it is beneficial to adjust keywords dynamically. The challenge is that these need to be specified ahead of…

Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for…