Merchants selling products on the Web often ask their customers to review the products that they have purchased and the associated services. As e-commerce is becoming more and more popular, the number of customer reviews that a product receives grows rapidly. For a popular product, the number of reviews can be in hundreds or even thousands. This makes it difficult for a potential customer to read them to make an informed decision on whether to purchase the product. It also makes it difficult for the manufacturer of the product to keep track and to manage customer opinions. For the manufacturer, there are additional difficulties because many merchant sites may sell the same product and the manufacturer normally produces many kinds of products. In this research, we aim to mine and to summarize all the customer reviews of a product. This summarization task is different from traditional text summarization because we only mine the features of the product on which the customers have expressed their opinions and whether the opinions are positive or negative. We do not summarize the reviews by selecting a subset or rewrite some of the original sentences from the reviews to capture the main points as in the classic text summarization. Our task is performed in three steps: (1) mining product features that have been commented on by customers; (2) identifying opinion sentences in each review and deciding whether each opinion sentence is positive or negative; (3) summarizing the results. This paper proposes several novel techniques to perform these tasks. Our experimental results using reviews of a number of products sold online demonstrate the effectiveness of the techniques.

/pdf/mining-and-summarizing-customer-reviews-3kfih6aknk.pdf

Mining and summarizing customer reviews

We describe a method for the automatic acquisition of the hyponymy lexical relation from unrestricted text. Two goals motivate the approach: (i) avoidance of the need for pre-encoded knowledge and (ii) applicability across a wide range of text. We identify a set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest. We describe a method for discovering these patterns and suggest that other lexical relations will also be acquirable in this way. A subset of the acquisition algorithm is implemented and the results are used to augment and critique the structure of a large hand-built thesaurus. Extensions and applications to areas such as information retrieval are suggested.

/pdf/automatic-acquisition-of-hyponyms-from-large-text-corpora-58zjcml7pl.pdf

Automatic acquisition of hyponyms from large text corpora

Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text). However, these models have two shortcomings: they are liable to reproduce factual details inaccurately, and they tend to repeat themselves. In this work we propose a novel architecture that augments the standard sequence-to-sequence attentional model in two orthogonal ways. First, we use a hybrid pointer-generator network that can copy words from the source text via pointing, which aids accurate reproduction of information, while retaining the ability to produce novel words through the generator. Second, we use coverage to keep track of what has been summarized, which discourages repetition. We apply our model to the CNN / Daily Mail summarization task, outperforming the current abstractive state-of-the-art by at least 2 ROUGE points.

/pdf/get-to-the-point-summarization-with-pointer-generator-5bzdk0pv8y.pdf

Get To The Point: Summarization with Pointer-Generator Networks

An intelligent electronic appliance preferably includes a user interface, data input and/or output port, and an intelligent processor. A preferred embodiment comprises a set top box for interacting with broadband media streams, with an adaptive user interface, content-based media processing and/or media metadata processing, and telecommunications integration. An adaptive user interface models the user, by observation, feedback, and/or explicit input, and presents a user interface and/or executes functions based on the user model. A content-based media processing system analyzes media content, for example audio and video, to understand the content, for example to generate content-descriptive metadata. A media metadata processing system operates on locally or remotely generated metadata to process the media in accordance with the metadata, which may be, for example, an electronic program guide, MPEG 7 data, and/or automatically generated format. A set top box preferably includes digital trick play effects, and incorporated digital rights management features.

Intelligent electronic appliance system and method

We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS). Extractive TS relies on the concept of sentence salience to identify the most important sentences in a document or set of documents. Salience is typically defined in terms of the presence of particular important words or in terms of similarity to a centroid pseudo-sentence. We consider a new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph representation of sentences. In this model, a connectivity matrix based on intra-sentence cosine similarity is used as the adjacency matrix of the graph representation of sentences. Our system, based on LexRank ranked in first place in more than one task in the recent DUC 2004 evaluation. In this paper we present a detailed analysis of our approach and apply it to a larger data set including data from earlier DUC evaluations. We discuss several methods to compute centrality using the similarity graph. The results show that degree-based methods (including LexRank) outperform both centroid-based methods and other systems participating in DUC in most of the cases. Furthermore, the LexRank with threshold method outperforms the other degree-based techniques including continuous LexRank. We also show that our approach is quite insensitive to the noise in the data that may result from an imperfect topical clustering of documents.

/pdf/lexrank-graph-based-lexical-centrality-as-salience-in-text-10aso8e2ok.pdf

LexRank: graph-based lexical centrality as salience in text summarization

●● ● ● ● To summarize is to reduce in complexity, and hence in length, while retaining some of the essential qualities of the original. This paper focusses on document extracts, a particular kind of computed document summary. Document extracts consisting of roughly 20% of the original cart be as informative as the full text of a document, which suggests that even shorter extracts may be useful indicative summmies. The trends in our results are in agreement with those of Edmundson who used a subjectively weighted combination of features as opposed to training the feature weights using a corpus.

/pdf/a-trainable-document-summarizer-1gv5gedbk6.pdf

A trainable document summarizer

We present an implementation of a part-of-speech tagger based on a hidden Markov model. The methodology enables robust and accurate tagging with few resource requirements. Only a lexicon and some unlabeled training text are required. Accuracy exceeds 96%. We describe implementation strategies and optimizations which result in high-speed operation. Three applications for tagging are described: phrase recognition; word sense disambiguation; and grammatical function assignment.

A Practical Part-of-Speech Tagger

A computerized method for retrieving documents from a text corpus in response to a user-supplied natural language input string, e.g., a question. An input string is accepted and analyzed to detect phrases therein. A series of queries based on the detected phrases is automatically constructed through a sequence of successive broadening and narrowing operations designed to generate an optimal query or queries. The queries of the series are executed to retrieve documents, which are then ranked and made available for output to the user, a storage device, or further processing. In another aspect the method is implemented in the context of a larger two-phase method, of which the first phase comprises the method of the invention and the second phase of the method comprises answer extraction.

Method for computerized information retrieval using shallow linguistic analysis

Robust part-of-speech tagging using a hidden Markov model

The paper describes an algorithm that employs English and French text taggers to associate noun phrases in an aligned bilingual corpus. The taggers provide part-of-speech categories which are used by finite-state recognizers to extract simple noun phrases for both languages. Noun phrases are then mapped to each other using an iterative re-estimation algorithm that bears similarities to the Baum-Welch algorithm which is used for training the taggers. The algorithm provides an alternative to other approaches for finding word correspondences, with the advantage that linguistic structure is incorporated. Improvements to the basic algorithm are described, which enable context to be accounted for when constructing the noun phrase mappings.

Julian M. Kupiec

Papers

A trainable document summarizer

A Practical Part-of-Speech Tagger

Method for computerized information retrieval using shallow linguistic analysis

Robust part-of-speech tagging using a hidden Markov model

An algorithm for finding noun phrase correspondences in bilingual corpora