PyTorchKR Papers

최신 논문

총 409편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2007.11348

Massive Multi-Document Summarization of Product Reviews with Weak Supervision

Product reviews summarization is a type of Multi-Document Summarization (MDS) task in which the summarized document sets are often far larger than in traditional MDS (up to tens of thousands of reviews). We highlight this difference and coin the term "Massive Multi-Document Summarization" (MMDS) to denote an MDS task that involves hundreds of documents or more. Prior work on product reviews summarization considered small samples of the reviews, mainly due to the difficulty of handling massive document sets. We show that summarizing small samples can result in loss of important information and provide misleading evaluation results. We propose a schema for summarizing a massive set of reviews on top of a standard summarization algorithm. Since writing large volumes of reference summaries needed for advanced neural network models is impractical, our solution relies on weak supervision. Finally, we propose an evaluation scheme that is based on multiple crowdsourced reference summaries and aims to capture the massive review collection. We show that an initial implementation of our schema significantly improves over several baselines in ROUGE scores, and exhibits strong coherence in a manual linguistic quality assessment.

arXiv:2007.08954공식 코드 · Papers with Code

SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this paper, we propose SummPip: an unsupervised method for multi-document summarization, in which we convert the original documents to a sentence graph, taking both linguistic and deep representation into account, then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary. Experiments on Multi-News and DUC-2004 datasets show that our method is competitive to previous unsupervised methods and is even comparable to the neural supervised approaches. In addition, human evaluation shows our system produces consistent and complete summaries compared to human written ones.

arXiv:2006.15020

Pre-training via Paraphrasing

We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective. MARGE provides an alternative to the dominant masked language modeling paradigm, where we self-supervise the reconstruction of target text by retrieving a set of related texts (in many languages) and conditioning on them to maximize the likelihood of generating the original. We show it is possible to jointly learn to do retrieval and reconstruction, given only a random initialization. The objective noisily captures aspects of paraphrase, translation, multi-document summarization, and information retrieval, allowing for strong zero-shot performance on several tasks. For example, with no additional task-specific training we achieve BLEU scores of up to 35.8 for document translation. We further show that fine-tuning gives strong performance on a range of discriminative and generative tasks in many languages, making MARGE the most generally applicable pre-training method to date.

arXiv:2006.08748공식 코드 · Papers with Code

DynE: Dynamic Ensemble Decoding for Multi-Document Summarization

Sequence-to-sequence (s2s) models are the basis for extensive work in natural language processing. However, some applications, such as multi-document summarization, multi-modal machine translation, and the automatic post-editing of machine translation, require mapping a set of multiple distinct inputs into a single output sequence. Recent work has introduced bespoke architectures for these multi-input settings, and developed models which can handle increasingly longer inputs; however, the performance of special model architectures is limited by the available in-domain training data. In this work we propose a simple decoding methodology which ensembles the output of multiple instances of the same model on different inputs. Our proposed approach allows models trained for vanilla s2s tasks to be directly used in multi-input settings. This works particularly well when each of the inputs has significant overlap with the others, as when compressing a cluster of news articles about the same event into a single coherent summary, and we obtain state-of-the-art results on several multi-document summarization datasets.

arXiv:2006.04660공식 코드 · Papers with Code

Read what you need: Controllable Aspect-based Opinion Summarization of Tourist Reviews

Manually extracting relevant aspects and opinions from large volumes of user-generated text is a time-consuming process. Summaries, on the other hand, help readers with limited time budgets to quickly consume the key ideas from the data. State-of-the-art approaches for multi-document summarization, however, do not consider user preferences while generating summaries. In this work, we argue the need and propose a solution for generating personalized aspect-based opinion summaries from large collections of online tourist reviews. We let our readers decide and control several attributes of the summary such as the length and specific aspects of interest among others. Specifically, we take an unsupervised approach to extract coherent aspects from tourist reviews posted on TripAdvisor. We then propose an Integer Linear Programming (ILP) based extractive technique to select an informative subset of opinions around the identified aspects while respecting the user-specified values for various control parameters. Finally, we evaluate and compare our summaries using crowdsourcing and ROUGE-based metrics and obtain competitive results.

arXiv:2005.09740

GLEAKE: Global and Local Embedding Automatic Keyphrase Extraction

Automated methods for granular categorization of large corpora of text documents have become increasingly more important with the rate scientific, news, medical, and web documents are growing in the last few years. Automatic keyphrase extraction (AKE) aims to automatically detect a small set of single or multi-words from within a single textual document that captures the main topics of the document. AKE plays an important role in various NLP and information retrieval tasks such as document summarization and categorization, full-text indexing, and article recommendation. Due to the lack of sufficient human-labeled data in different textual contents, supervised learning approaches are not ideal for automatic detection of keyphrases from the content of textual bodies. With the state-of-the-art advances in text embedding techniques, NLP researchers have focused on developing unsupervised methods to obtain meaningful insights from raw datasets. In this work, we introduce Global and Local Embedding Automatic Keyphrase Extractor (GLEAKE) for the task of AKE. GLEAKE utilizes single and multi-word embedding techniques to explore the syntactic and semantic aspects of the candidate phrases and then combines them into a series of embedding-based graphs. Moreover, GLEAKE applies network analysis techniques on each embedding-based graph to refine the most significant phrases as a final set of keyphrases. We demonstrate the high performance of GLEAKE by evaluating its results on five standard AKE datasets from different domains and writing styles and by showing its superiority with regards to other state-of-the-art methods.

arXiv:2005.10070공식 코드 · Papers with Code

A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal

Multi-document summarization (MDS) aims to compress the content in large document collections into short summaries and has important applications in story clustering for newsfeeds, presentation of search results, and timeline generation. However, there is a lack of datasets that realistically address such use cases at a scale large enough for training supervised models for this task. This work presents a new dataset for MDS that is large both in the total number of document clusters and in the size of individual clusters. We build this dataset by leveraging the Wikipedia Current Events Portal (WCEP), which provides concise and neutral human-written summaries of news events, with links to external source articles. We also automatically extend these source articles by looking for related articles in the Common Crawl archive. We provide a quantitative analysis of the dataset and empirical results for several state-of-the-art MDS techniques.

arXiv:2005.10043공식 코드 · Papers with Code

Leveraging Graph to Improve Abstractive Multi-Document Summarization

Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents such as similarity graph and discourse graph, to more effectively process multiple input documents and produce abstractive summaries. Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents. Our model can also take advantage of graphs to guide the summary generation process, which is beneficial for generating coherent and concise summaries. Furthermore, pre-trained language models can be easily combined with our model, which further improve the summarization performance significantly. Empirical results on the WikiSum and MultiNews dataset show that the proposed architecture brings substantial improvements over several strong baselines.

arXiv:2005.06377공식 코드 · Papers with Code

SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative Sampling

Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summary which is costly to obtain. Recently, there have been a growing number of efforts to alleviate either or both of the two drawbacks. In this paper, we present a proof-of-concept study to a weakly supervised summary evaluation approach without the presence of reference summaries. Massive data in existing summarization datasets are transformed for training by pairing documents with corrupted reference summaries. In cross-domain tests, our strategy outperforms baselines with promising improvements, and show a great advantage in gauging linguistic qualities over all metrics.

arXiv:2005.03975공식 코드 · Papers with Code

CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management

We present CAiRE-COVID, a real-time question answering (QA) and multi-document summarization system, which won one of the 10 tasks in the Kaggle COVID-19 Open Research Dataset Challenge, judged by medical experts. Our system aims to tackle the recent challenge of mining the numerous scientific articles being published on COVID-19 by answering high priority questions from the community and summarizing salient question-related information. It combines information extraction with state-of-the-art QA and query-focused multi-document summarization techniques, selecting and highlighting evidence snippets from existing literature given a query. We also propose query-focused abstractive and extractive multi-document summarization methods, to provide more relevant information related to the question. We further conduct quantitative experiments that show consistent improvements on various metrics for each module. We have launched our website CAiRE-COVID for broader use by the medical community, and have open-sourced the code for our system, to bootstrap further study by other researches.

arXiv:2005.03724공식 코드 · Papers with Code

SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization

We study unsupervised multi-document summarization evaluation metrics, which require neither human-written reference summaries nor human annotations (e.g. preferences, ratings, etc.). We propose SUPERT, which rates the quality of a summary by measuring its semantic similarity with a pseudo reference summary, i.e. selected salient sentences from the source documents, using contextualized embeddings and soft token alignment techniques. Compared to the state-of-the-art unsupervised evaluation metrics, SUPERT correlates better with human ratings by 18-39%. Furthermore, we use SUPERT as rewards to guide a neural-based reinforcement learning summarizer, yielding favorable performance compared to the state-of-the-art unsupervised summarizers. All source code is available at https://github.com/yg211/acl20-ref-free-eval.

arXiv:2005.02146

Artemis: A Novel Annotation Methodology for Indicative Single Document Summarization

We describe Artemis (Annotation methodology for Rich, Tractable, Extractive, Multi-domain, Indicative Summarization), a novel hierarchical annotation process that produces indicative summaries for documents from multiple domains. Current summarization evaluation datasets are single-domain and focused on a few domains for which naturally occurring summaries can be easily found, such as news and scientific articles. These are not sufficient for training and evaluation of summarization models for use in document management and information retrieval systems, which need to deal with documents from multiple domains. Compared to other annotation methods such as Relative Utility and Pyramid, Artemis is more tractable because judges don't need to look at all the sentences in a document when making an importance judgment for one of the sentences, while providing similarly rich sentence importance annotations. We describe the annotation process in detail and compare it with other similar evaluation systems. We also present analysis and experimental results over a sample set of 532 annotated documents.

arXiv:2005.00743

Synthesizer: Rethinking Self-Attention in Transformer Models

The dot product self-attention is known to be central and indispensable to state-of-the-art Transformer models. But is it really required? This paper investigates the true importance and contribution of the dot product-based self-attention mechanism on the performance of Transformer models. Via extensive experiments, we find that (1) random alignment matrices surprisingly perform quite competitively and (2) learning attention weights from token-token (query-key) interactions is useful but not that important after all. To this end, we propose \textsc{Synthesizer}, a model that learns synthetic attention weights without token-token interactions. In our experiments, we first show that simple Synthesizers achieve highly competitive performance when compared against vanilla Transformer models across a range of tasks, including machine translation, language modeling, text generation and GLUE/SuperGLUE benchmarks. When composed with dot product attention, we find that Synthesizers consistently outperform Transformers. Moreover, we conduct additional comparisons of Synthesizers against Dynamic Convolutions, showing that simple Random Synthesizer is not only $60\%$ faster but also improves perplexity by a relative $3.5\%$. Finally, we show that simple factorized Synthesizers can outperform Linformers on encoding only tasks.

arXiv:2005.00661공식 코드 · Papers with Code

On Faithfulness and Factuality in Abstractive Summarization

It is well known that the standard likelihood training and approximate decoding objectives in neural text generation models lead to less human-like responses for open-ended tasks such as language modeling and story generation. In this paper we have analyzed limitations of these models for abstractive document summarization and found that these models are highly prone to hallucinate content that is unfaithful to the input document. We conducted a large scale human evaluation of several neural abstractive summarization systems to better understand the types of hallucinations they produce. Our human annotators found substantial amounts of hallucinated content in all model generated summaries. However, our analysis does show that pretrained models are better summarizers not only in terms of raw metrics, i.e., ROUGE, but also in generating faithful and factual summaries as evaluated by humans. Furthermore, we show that textual entailment measures better correlate with faithfulness than standard metrics, potentially leading the way to automatic evaluation metrics as well as training and decoding criteria.

arXiv:2004.14119

Combining Word Embeddings and N-grams for Unsupervised Document Summarization

Graph-based extractive document summarization relies on the quality of the sentence similarity graph. Bag-of-words or tf-idf based sentence similarity uses exact word matching, but fails to measure the semantic similarity between individual words or to consider the semantic structure of sentences. In order to improve the similarity measure between sentences, we employ off-the-shelf deep embedding features and tf-idf features, and introduce a new text similarity metric. An improved sentence similarity graph is built and used in a submodular objective function for extractive summarization, which consists of a weighted coverage term and a diversity term. A Transformer based compression model is developed for sentence compression to aid in document summarization. Our summarization approach is extractive and unsupervised. Experiments demonstrate that our approach can outperform the tf-idf based approach and achieve state-of-the-art performance on the DUC04 dataset, and comparable performance to the fully supervised learning methods on the CNN/DM and NYT datasets.

arXiv:2004.12393공식 코드 · Papers with Code

Heterogeneous Graph Neural Networks for Extractive Document Summarization

As a crucial step in extractive document summarization, learning cross-sentence relations has been explored by a plethora of approaches. An intuitive way is to put them in the graph-based neural network, which has a more complex structure for capturing inter-sentence relationships. In this paper, we present a heterogeneous graph-based neural network for extractive summarization (HeterSumGraph), which contains semantic nodes of different granularity levels apart from sentences. These additional nodes act as the intermediary between sentences and enrich the cross-sentence relations. Besides, our graph structure is flexible in natural extension from a single-document setting to multi-document via introducing document nodes. To our knowledge, we are the first one to introduce different types of nodes into graph-based neural networks for extractive document summarization and perform a comprehensive qualitative analysis to investigate their benefits. The code will be released on Github

arXiv:2004.12727공식 코드 · Papers with Code

Screenplay Summarization Using Latent Narrative Structure

Most general-purpose extractive summarization models are trained on news articles, which are short and present all important information upfront. As a result, such models are biased on position and often perform a smart selection of sentences from the beginning of the document. When summarizing long narratives, which have complex structure and present information piecemeal, simple position heuristics are not sufficient. In this paper, we propose to explicitly incorporate the underlying structure of narratives into general unsupervised and supervised extractive summarization models. We formalize narrative structure in terms of key narrative events (turning points) and treat it as latent in order to summarize screenplays (i.e., extract an optimal sequence of scenes). Experimental results on the CSI corpus of TV screenplays, which we augment with scene-level summarization labels, show that latent turning points correlate with important aspects of a CSI episode and improve summarization performance over general extractive algorithms leading to more complete and diverse summaries.

arXiv:2004.11854공식 코드 · Papers with Code

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Sequence-to-sequence models usually transfer all encoder outputs to the decoder for generation. In this work, by contrast, we hypothesize that these encoder outputs can be compressed to shorten the sequence delivered for decoding. We take Transformer as the testbed and introduce a layer of stochastic gates in-between the encoder and the decoder. The gates are regularized using the expected value of the sparsity-inducing L0penalty, resulting in completely masking-out a subset of encoder outputs. In other words, via joint training, the L0DROP layer forces Transformer to route information through a subset of its encoder states. We investigate the effects of this sparsification on two machine translation and two summarization tasks. Experiments show that, depending on the task, around 40-70% of source encodings can be pruned without significantly compromising quality. The decrease of the output length endows L0DROP with the potential of improving decoding efficiency, where it yields a speedup of up to 1.65x on document summarization tasks against the standard Transformer. We analyze the L0DROP behaviour and observe that it exhibits systematic preferences for pruning certain word types, e.g., function words and punctuation get pruned most. Inspired by these observations, we explore the feasibility of specifying rule-based patterns that mask out encoder outputs based on information such as part-of-speech tags, word frequency and word position.

arXiv:2004.11779공식 코드 · Papers with Code

Exploring Explainable Selection to Control Abstractive Summarization

Like humans, document summarization models can interpret a document's contents in a number of ways. Unfortunately, the neural models of today are largely black boxes that provide little explanation of how or why they generated a summary in the way they did. Therefore, to begin prying open the black box and to inject a level of control into the substance of the final summary, we developed a novel select-and-generate framework that focuses on explainability. By revealing the latent centrality and interactions between sentences, along with scores for sentence novelty and relevance, users are given a window into the choices a model is making and an opportunity to guide those choices in a more desirable direction. A novel pair-wise matrix captures the sentence interactions, centrality, and attribute scores, and a mask with tunable attribute thresholds allows the user to control which sentences are likely to be included in the extraction. A sentence-deployed attention mechanism in the abstractor ensures the final summary emphasizes the desired content. Additionally, the encoder is adaptable, supporting both Transformer- and BERT-based configurations. In a series of experiments assessed with ROUGE metrics and two human evaluations, ESCA outperformed eight state-of-the-art models on the CNN/DailyMail and NYT50 benchmark datasets.

arXiv:2004.09739

Neural Abstractive Summarization with Structural Attention

Attentional, RNN-based encoder-decoder architectures have achieved impressive performance on abstractive summarization of news articles. However, these methods fail to account for long term dependencies within the sentences of a document. This problem is exacerbated in multi-document summarization tasks such as summarizing the popular opinion in threads present in community question answering (CQA) websites such as Yahoo! Answers and Quora. These threads contain answers which often overlap or contradict each other. In this work, we present a hierarchical encoder based on structural attention to model such inter-sentence and inter-document dependencies. We set the popular pointer-generator architecture and some of the architectures derived from it as our baselines and show that they fail to generate good summaries in a multi-document setting. We further illustrate that our proposed model achieves significant improvement over the baselines in both single and multi-document summarization settings -- in the former setting, it beats the best baseline by 1.31 and 7.8 ROUGE-1 points on CNN and CQA datasets, respectively; in the latter setting, the performance is further improved by 1.6 ROUGE-1 points on the CQA dataset.