The evaluation of abstractive summarization models typically uses test data that is identically distributed as training data. In real-world practice, documents to be summarized may contain input noise caused by text extraction artifacts or data pipeline bugs. The robustness of model performance under distribution shift caused by such noise is relatively under studied. We present a large empirical study quantifying the sometimes severe loss in performance – up to 12 ROUGE-1 points – from different types of input noise for a range of datasets and model sizes. We then propose a light-weight method for detecting and removing such noise in the input during model inference without requiring any extra training, auxiliary models, or even prior knowledge of the type of noise. Our proposed approach effectively mitigates the loss in performance, recovering a large fraction of the performance drop, sometimes as large as 11 ROUGE-1 points.

While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs still poses a significant challenge. One such task is long input summarization, where inputs are longer than the maximum input context of most models. Through an extensive set of experiments, we investigate what model architectural changes and pretraining paradigms most efficiently adapt a pretrained Transformer for long input summarization. We find that a staggered, block-local Transformer with global encoder tokens strikes a good balance of performance and efficiency, and that an additional pretraining phase on long sequences meaningfully improves downstream summarization performance. Based on our findings, we introduce PEGASUS-X, an extension of the PEGASUS model with additional long input pretraining to handle inputs of up to 16K tokens, which achieves strong performance on long input summarization tasks comparable with much larger models.

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural generation models (FROST, Narayan et al, 2021) that are trained to first create a composition of the output and then generate by conditioning on it and the input. Our approach avoids text degeneration by first sampling a composition in the form of an entity chain and then using beam search to generate the best possible text grounded to this entity chain. Experiments on summarization (CNN/DailyMail and XSum) and question generation (SQuAD), using existing and newly proposed automaticmetrics together with human-based evaluation, demonstrate that Composition Sampling is currently the best available decoding strategy for generating diverse meaningful outputs.

Relation linking (RL) is a vital module in knowledge-based question answering (KBQA) systems. It aims to link the relations expressed in natural language (NL) to the corresponding ones in knowledge graph (KG). Existing methods mainly rely on the textual similarities between NL and KG to build relation links. Due to the ambiguity of NL and the incompleteness of KG, many relations in NL are implicitly expressed, and may not link to a single relation in KG, which challenges the current methods. In this paper, we propose an implicit RL method called ImRL, which links relation phrases in NL to relation paths in KG. To find proper relation paths, we propose a novel path ranking model that aligns not only textual information in the word embedding space but also structural information in the KG embedding space between relation phrases in NL and relation paths in KG. Besides, we leverage a gated mechanism with attention to inject prior knowledge from external paraphrase dictionaries to address the relation phrases with vague meaning. Our experiments on two benchmark and a newly-created datasets show that ImRL significantly outperforms several state-of-the-art methods, especially for implicit RL.

Abstractive summarization quality had large improvements since recent language pretraining techniques. However, currently there is a lack of datasets for the growing needs of conversation summarization applications. Thus we collected ForumSum, a diverse and high-quality conversation summarization dataset with human written summaries. The conversations in ForumSum dataset are collected from a wide variety of internet forums. To make the dataset easily expandable, we also release the process of dataset creation. Our experiments show that models trained on ForumSum have better zero-shot and few-shot transferability to other datasets than the existing large chat summarization dataset SAMSum. We also show that using a conversational corpus for pre-training improves the quality of the chat summarization model.

We introduce a simple but flexible mechanism to learn an intermediate plan to ground the generation of abstractive summaries. Specifically, we prepend (or prompt) target summaries with entity chains—ordered sequences of entities mentioned in the summary. Transformer-based sequence-to-sequence models are then trained to generate the entity chain and then continue generating the summary conditioned on the entity chain and the input. We experimented with both pretraining and finetuning with this content planning objective. When evaluated on CNN/DailyMail, XSum, SAMSum, and BillSum, we demonstrate empirically that the grounded generation with the planning objective improves entity specificity and planning in summaries for all datasets, and achieves state-of-the-art performance on XSum and SAMSum in terms of rouge. Moreover, we demonstrate empirically that planning with entity chains provides a mechanism to control hallucinations in abstractive summaries. By prompting the decoder with a modified content plan that drops hallucinated entities, we outperform state-of-the-art approaches for faithfulness when evaluated automatically and by humans.

Question generation, the task of automatically creating questions that can be answered by a certain span of text within a given passage, is important for question-answering and conversational systems in digital assistants such as Alexa, Cortana, Google Assistant and Siri. Recent sequence to sequence neural models have outperformed previous rule-based systems. Existing models mainly focused on using one or two sentences as the input. Long text has posed challenges for sequence to sequence neural models in question generation – worse performances were reported if using the whole paragraph (with multiple sentences) as the input. In reality, however, it often requires the whole paragraph as context in order to generate high quality questions. In this paper, we propose a maxout pointer mechanism with gated self-attention encoder to address the challenges of processing long text inputs for question generation. With sentence-level inputs, our model outperforms previous approaches with either sentence-level or paragraph-level inputs. Furthermore, our model can effectively utilize paragraphs as inputs, pushing the state-of-the-art result from 13.9 to 16.3 (BLEU_4).