It is a challenging and practical research problem to obtain effective compression of lengthy product titles for E-commerce. This is particularly important as more and more users browse mobile E-commerce apps and more merchants make the original product titles redundant and lengthy for Search Engine Optimization. Traditional text summarization approaches often require a large amount of preprocessing costs and do not capture the important issue of conversion rate in E-commerce. This paper proposes a novel multi-task learning approach for improving product title compression with user search log data. In particular, a pointer network-based sequence-to-sequence approach is utilized for title compression with an attentive mechanism as an extractive method and an attentive encoder-decoder approach is utilized for generating user search queries. The encoding parameters (i.e., semantic embedding of original titles) are shared among the two tasks and the attention distributions are jointly optimized. An extensive set of experiments with both human annotated data and online deployment demonstrate the advantage of the proposed research for both compression qualities and online business values.
The representation of sentences is a very important task. It can be used as a way to exchange data inter-applications. One main characteristic, that a notation must have, is a minimal size and a representative form. This can reduce the transfer time, and hopefully the processing time as well. Usually, sentence representation is associated to the processed language. The grammar of this language affects how we represent the sentence. To avoid language-dependent notations, we have to come up with a new representation which don't use words, but their meanings. This can be done using a lexicon like wordnet, instead of words we use their synsets. As for syntactic relations, they have to be universal as much as possible. Our new notation is called STON "SenTences Object Notation", which somehow has similarities to JSON. It is meant to be minimal, representative and language-independent syntactic representation. Also, we want it to be readable and easy to be created. This simplifies developing simple automatic generators and creating test banks manually. Its benefit is to be used as a medium between different parts of applications like: text summarization, language translation, etc. The notation is based on 4 languages: Arabic, English, Franch and Japanese; and there are some cases where these languages don't agree on one representation. Also, given the diversity of grammatical structure of different world languages, this annotation may fail for some languages which allows more future improvements.
Text summarization condenses a text to a shorter version while retaining the important informations. Abstractive summarization is a recent development that generates new phrases, rather than simply copying or rephrasing sentences within the original text. Recently neural sequence-to-sequence models have achieved good results in the field of abstractive summarization, which opens new possibilities and applications for industrial purposes. However, most practitioners observe that these models still use large parts of the original text in the output summaries, making them often similar to extractive frameworks. To address this drawback, we first introduce a new metric to measure how much of a summary is extracted from the input text. Secondly, we present a novel method, that relies on a diversity factor in computing the neural network loss, to improve the diversity of the summaries generated by any neural abstractive model implementing beam search. Finally, we show that this method not only makes the system less extractive, but also improves the overall rouge score of state-of-the-art methods by at least 2 points.
Text summarization is an interesting area for researchers to develop new techniques to provide human like summaries for vast amounts of information. Summarization techniques tend to focus on providing accurate representation of content, and often the tone of the content is ignored. Tone of the content sets a baseline for how a reader perceives the content. As such being able to generate summary with tone that is appropriate for the reader is important. In our work we implement Maximal Marginal Relevance [MMR] based multi-document text summarization and propose a naive model to change tone of the summarization by setting a bias to specific set of words and restricting other words in the summarization output. This bias towards a specified set of words produces a summary whose tone is same as tone of specified words.
Text Summarization has been an extensively studied problem. Traditional approaches to text summarization rely heavily on feature engineering. In contrast to this, we propose a fully data-driven approach using feedforward neural networks for single document summarization. We train and evaluate the model on standard DUC 2002 dataset which shows results comparable to the state of the art models. The proposed model is scalable and is able to produce the summary of arbitrarily sized documents by breaking the original document into fixed sized parts and then feeding it recursively to the network.
Automatic abstractive text summarization is an important and challenging research topic of natural language processing. Among many widely used languages, the Chinese language has a special property that a Chinese character contains rich information comparable to a word. Existing Chinese text summarization methods, either adopt totally character-based or word-based representations, fail to fully exploit the information carried by both representations. To accurately capture the essence of articles, we propose a hybrid word-character approach (HWC) which preserves the advantages of both word-based and character-based representations. We evaluate the advantage of the proposed HWC approach by applying it to two existing methods, and discover that it generates state-of-the-art performance with a margin of 24 ROUGE points on a widely used dataset LCSTS. In addition, we find an issue contained in the LCSTS dataset and offer a script to remove overlapping pairs (a summary and a short text) to create a clean dataset for the community. The proposed HWC approach also generates the best performance on the new, clean LCSTS dataset.
Crafting adversarial examples has become an important technique to evaluate the robustness of deep neural networks (DNNs). However, most existing works focus on attacking the image classification problem since its input space is continuous and output space is finite. In this paper, we study the much more challenging problem of crafting adversarial examples for sequence-to-sequence (seq2seq) models, whose inputs are discrete text strings and outputs have an almost infinite number of possibilities. To address the challenges caused by the discrete input space, we propose a projected gradient method combined with group lasso and gradient regularization. To handle the almost infinite output space, we design some novel loss functions to conduct non-overlapping attack and targeted keyword attack. We apply our algorithm to machine translation and text summarization tasks, and verify the effectiveness of the proposed algorithm: by changing less than 3 words, we can make seq2seq model to produce desired outputs with high success rates. On the other hand, we recognize that, compared with the well-evaluated CNN-based classifiers, seq2seq models are intrinsically more robust to adversarial attacks.
In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE directly maximizing the conditional likelihood, the bridge extends the point-wise ground truth to a bridge distribution conditioned on it, and the generator is optimized to minimize their KL-divergence. Three different GBNs, namely uniform GBN, language-model GBN and coaching GBN, are proposed to penalize confidence, enhance language smoothness and relieve learning burden. Experiments conducted on two recognized sequence prediction tasks (machine translation and abstractive text summarization) show that our proposed GBNs can yield significant improvements over strong baselines. Furthermore, by analyzing samples drawn from different bridges, expected influences on the generator are verified.
Automatic text summarization, the automated process of shortening a text while reserving the main ideas of the document(s), is a critical research area in natural language processing. The aim of this literature review is to survey the recent work on neural-based models in automatic text summarization. We examine in detail ten state-of-the-art neural-based summarizers: five abstractive models and five extractive models. In addition, we discuss the related techniques that can be applied to the summarization tasks and present promising paths for future research in neural-based summarization.
Many Natural Language Processing and Computational Linguistics applications involves the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation. However, there has been a serious problem haunting these applications for decades, that is, how to automatically and accurately assess quality of these applications. In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation: how to pinpoint content differences of two text passages (especially for large pas-sages such as articles and books). Our idea is intuitive and very different from existing approaches. We treat one text passage as a small knowledge base, and ask it a large number of questions to exhaustively identify all content points in it. By comparing the correctly answered questions from two text passages, we will be able to compare their content precisely. The experiment using 2007 DUC summarization corpus clearly shows promising results.
Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when extracting sentences. As an effort towards extracting coherent summaries, we propose a neural coherence model to capture the cross-sentence semantic and syntactic coherence patterns. The proposed neural coherence model obviates the need for feature engineering and can be trained in an end-to-end fashion using unlabeled data. Empirical results show that the proposed neural coherence model can efficiently capture the cross-sentence coherence patterns. Using the combined output of the neural coherence model and ROUGE package as the reward, we design a reinforcement learning method to train a proposed neural extractive summarizer which is named Reinforced Neural Extractive Summarization (RNES) model. The RNES model learns to optimize coherence and informative importance of the summary simultaneously. Experimental results show that the proposed RNES outperforms existing baselines and achieves state-of-the-art performance in term of ROUGE on CNN/Daily Mail dataset. The qualitative evaluation indicates that summaries produced by RNES are more coherent and readable.
Data-driven approaches to sequence-to-sequence modelling have been successfully applied to short text summarization of news articles. Such models are typically trained on input-summary pairs consisting of only a single or a few sentences, partially due to limited availability of multi-sentence training data. Here, we propose to use scientific articles as a new milestone for text summarization: large-scale training data come almost for free with two types of high-quality summaries at different levels - the title and the abstract. We generate two novel multi-sentence summarization datasets from scientific articles and test the suitability of a wide range of existing extractive and abstractive neural network-based summarization approaches. Our analysis demonstrates that scientific papers are suitable for data-driven text summarization. Our results could serve as valuable benchmarks for scaling sequence-to-sequence models to very long sequences.
Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in semantics. In such cases, when generating summaries, the model selects semantically unrelated words with respect to the source content as the most probable output. The problem can be attributed to heuristically constructed training data, where summaries can be unrelated to the source content, thus containing semantically unrelated words and spurious word correspondence. In this paper, we propose a regularization approach for the sequence-to-sequence model and make use of what the model has learned to regularize the learning objective to alleviate the effect of the problem. In addition, we propose a practical human evaluation method to address the problem that the existing automatic evaluation method does not evaluate the semantic consistency with the source content properly. Experimental results demonstrate the effectiveness of the proposed approach, which outperforms almost all the existing models. Especially, the proposed approach improves the semantic consistency by 4\% in terms of human evaluation.
Most of the current abstractive text summarization models are based on the sequence-to-sequence model (Seq2Seq). The source content of social media is long and noisy, so it is difficult for Seq2Seq to learn an accurate semantic representation. Compared with the source content, the annotated summary is short and well written. Moreover, it shares the same meaning as the source content. In this work, we supervise the learning of the representation of the source content with that of the summary. In implementation, we regard a summary autoencoder as an assistant supervisor of Seq2Seq. Following previous work, we evaluate our model on a popular Chinese social media dataset. Experimental results show that our model achieves the state-of-the-art performances on the benchmark dataset.
We report a series of experiments with different semantic models on top of various statistical models for extractive text summarization. Though statistical models may better capture word co-occurrences and distribution around the text, they fail to detect the context and the sense of sentences /words as a whole. Semantic models help us gain better insight into the context of sentences. We show that how tuning weights between different models can help us achieve significant results on various benchmarks. Learning pre-trained vectors used in semantic models further, on given corpus, can give addition spike in performance. Using weighing techniques in between different statistical models too further refines our result. For Statistical models, we have used TF/IDF, TextRAnk, Jaccard/Cosine Similarities. For Semantic Models, we have used WordNet-based Model and proposed two models based on Glove Vectors and Facebook's InferSent. We tested our approach on DUC 2004 dataset, generating 100-word summaries. We have discussed the system, algorithms, analysis and also proposed and tested possible improvements. ROUGE scores were used to compare to other summarizers.
The recent advance in neural network architecture and training algorithms have shown the effectiveness of representation learning. The neural network-based models generate better representation than the traditional ones. They have the ability to automatically learn the distributed representation for sentences and documents. To this end, we proposed a novel model that addresses several issues that are not adequately modeled by the previously proposed models, such as the memory problem and incorporating the knowledge of document structure. Our model uses a hierarchical structured self-attention mechanism to create the sentence and document embeddings. This architecture mirrors the hierarchical structure of the document and in turn enables us to obtain better feature representation. The attention mechanism provides extra source of information to guide the summary extraction. The new model treated the summarization task as a classification problem in which the model computes the respective probabilities of sentence-summary membership. The model predictions are broken up by several features such as information content, salience, novelty and positional representation. The proposed model was evaluated on two well-known datasets, the CNN / Daily Mail, and DUC 2002. The experimental results show that our model outperforms the current extractive state-of-the-art by a considerable margin.
Neural abstractive summarization models have led to promising results in summarizing relatively short documents. We propose the first model for abstractive summarization of single, longer-form documents (e.g., research papers). Our approach consists of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary. Empirical results on two large-scale datasets of scientific papers show that our model significantly outperforms state-of-the-art models.
In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide state-of-the-art performance in a wide variety of tasks such as machine translation, headline generation, text summarization, speech to text conversion, and image caption generation. The underlying framework for all these models is usually a deep neural network comprising an encoder and a decoder. Although simple encoder-decoder models produce competitive results, many researchers have proposed additional improvements over these sequence-to-sequence models, e.g., using an attention-based model over the input, pointer-generation models, and self-attention models. However, such seq2seq models suffer from two common problems: 1) exposure bias and 2) inconsistency between train/test measurement. Recently, a completely novel point of view has emerged in addressing these two problems in seq2seq models, leveraging methods from reinforcement learning (RL). In this survey, we consider seq2seq problems from the RL point of view and provide a formulation combining the power of RL methods in decision-making with sequence-to-sequence models that enable remembering long-term memories. We present some of the most recent frameworks that combine concepts from RL and deep neural networks and explain how these two areas could benefit from each other in solving complex seq2seq tasks. Our work aims to provide insights into some of the problems that inherently arise with current approaches and how we can address them with better RL models. We also provide the source code for implementing most of the RL models discussed in this paper to support the complex task of abstractive text summarization.
Teaching large classes remains a great challenge, primarily because it is difficult to attend to all the student needs in a timely manner. Automatic text summarization systems can be leveraged to summarize the student feedback, submitted immediately after each lecture, but it is left to be discovered what makes a good summary for student responses. In this work we explore a new methodology that effectively extracts summary phrases from the student responses. Each phrase is tagged with the number of students who raise the issue. The phrases are evaluated along two dimensions: with respect to text content, they should be informative and well-formed, measured by the ROUGE metric; additionally, they shall attend to the most pressing student needs, measured by a newly proposed metric. This work is enabled by a phrase-based annotation and highlighting scheme, which is new to the summarization task. The phrase-based framework allows us to summarize the student responses into a set of bullet points and present to the instructor promptly.
Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall summary. We use a novel sentence-level policy gradient method to bridge the non-differentiable computation between these two neural networks in a hierarchical way, while maintaining language fluency. Empirically, we achieve the new state-of-the-art on all metrics (including human evaluation) on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores. Moreover, by first operating at the sentence-level and then the word-level, we enable parallel decoding of our neural generative model that results in substantially faster (10-20x) inference speed as well as 4x faster training convergence than previous long-paragraph encoder-decoder models. We also demonstrate the generalization of our model on the test-only DUC-2002 dataset, where we achieve higher scores than a state-of-the-art model.