There have been many studies on neural headline generation models trained with a lot of (article, headline) pairs. However, there are few situations for putting such models into practical use in the real world since news articles typically already have corresponding headlines. In this paper, we describe a practical use case of neural headline generation in a news aggregator, where dozens of professional editors constantly select important news articles and manually create their headlines, which are much shorter than the original headlines. Specifically, we show how to deploy our model to an editing support tool and report the results of comparing the behavior of the editors before and after the release.

A Case Study on Neural Headline Generation for Editing Support

Spell correction is a must-have feature for any modern search engine in applications such as web or e-commerce search. Typical spell correction solutions used in production systems consist of large indexed lookup tables based on a global model trained across many users over a large scale web corpus or a query log. For search over personal corpora, such as email, this global solution is not sufficient, as it ignores the user's personal lexicon. Without personalization, global spelling fails to correct tail queries drawn from a user's own, often idiosyncratic, lexicon. Personalization using existing algorithms is difficult due to resource constraints and unavailability of sufficient data to build per-user models. In this work, we propose a simple and effective personalized spell correction solution that augments existing global solutions for search over private corpora. Our event driven spell correction candidate generation method is specifically designed with personalization as the key construct. Our novel spell correction and query completion algorithms do not require complex model training and is highly efficient. The proposed solution has shown over 30% click-through rate gain on affected queries when evaluated against a range of strong commercial personal search baselines - Google's Gmail, Drive, and Calendar search production systems.

https://dl.acm.org/doi/pdf/10.1145/3308558.3313706

Personalized Online Spell Correction for Personal Search

In this article, we make use of sequence-to-sequence (seq2seq) models for spelling correction in the agglutinative Turkish language. In the baseline system, misspelled and target words are split into their letters and the letter sequences are fed into the seq2seq model. We prefer letters as the unit of the model due to the agglutinative nature of Turkish, which results in an impractical dictionary size when words are used as a dictionary unit. In order to improve the baseline performance, we incorporate right and left context of the misspelled words. All context words are represented with their first three consonants in the context-dependent model. We train the seq2seq models using a large text corpus collected automatically from the Internet. The corpus contains approximately 4 million sentences. We randomly introduce substitution, deletion, and insertion spelling errors to the words in the corpus. We test the performance of the proposed context-dependent seq2seq model using synthetic and realistic test sets. The synthetic test set is constructed similar to the training set. The realistic test set contains human-made misspellings from Twitter messages. In the experiments, we observed that the proposed context-dependent model performs significantly better than the baseline system. Its correction accuracy reaches 94% on the synthetic dataset. Additionally, the proposed method provides 2.1% absolute improvement over a state-of-the-art Turkish spelling correction system on the Twitter test set.

Context-Dependent Sequence-to-Sequence Turkish Spelling Correction

Performance of any word processor, search engine, social media relies heavily on the spell-checkers, grammar checkers etc. Spell-checkers are the language tools which break down the text to check the spelling errors. It cautions the user if there is any unintentional misspelling occurred in the text. In the area of spell-checking, we still lack an exhaustive study that covers aspects like strengths, limitations, handled errors, performance along with the evaluation parameters. In literature, spell-checkers for different languages are available and each one possesses similar characteristics however, have a different design. This study follows the guidelines of systematic literature review and applies it to the field of spell-checking. The steps of the systematic review are employed on 130 selected articles published in leading journals, premier conferences and workshops in the field of spell-checking of different inflectional languages. These steps include framing of the research questions, selection of research articles, inclusion/exclusion criteria and the extraction of the relevant information from the selected research articles. The literature about spell-checking is divided into key sub-areas according to the languages. Each sub-area is then described based on the technique being used. In this study, various articles are analyzed on certain criteria to reach the conclusion. This article suggests how the techniques from the other domains like morphology, part-of-speech, chunking, stemming, hash-table etc. can be used in development of spell-checkers. It also highlights the major challenges faced by researchers along with the future area of research in the field of spell-checking.

Systematic review of spell-checkers for highly inflectional languages

We present a novel language adaptable spell checking system that detects spelling errors and suggests context-sensitive corrections in real-time. We show that our system can be extended to new languages with minimal language-specific processing. Available literature majorly discusses spell checkers for English but there are no publicly available systems that can be extended to work for other languages out of the box. Most of the systems do not work in real-time. We explain the process of generating a language's word dictionary and n-gram probability dictionaries using Wikipedia-articles data and manually curated video subtitles. We present the results of generating a list of suggestions for a misspelled word. We also propose three approaches to create noisy channel datasets of real-world typographic errors. Finally, we show the effectiveness of language adaptability of our proposed system by extending it to 24 languages.

/pdf/a-context-sensitive-real-time-spell-checker-with-language-bn8e57jija.pdf

A Context-Sensitive Real-Time Spell Checker with Language Adaptability

Spelling correction is a well-known task in Natural Language Processing (NLP). Automatic spelling correction is important for many NLP applications like web search engines, text summarization, sentiment analysis etc. Most approaches use parallel data of noisy and correct word mappings from different sources as training data for automatic spelling correction. Indic languages are resource-scarce and do not have such parallel data due to low volume of queries and non-existence of such prior implementations. In this paper, we show how to build an automatic spelling corrector for resource-scarce languages. We propose a sequence-to-sequence deep learning model which trains end-to-end. We perform experiments on synthetic datasets created for Indic languages, Hindi and Telugu, by incorporating the spelling mistakes committed at character level. A comparative evaluation shows that our model is competitive with the existing spell checking and correction techniques for Indic languages.

/pdf/automatic-spelling-correction-for-resource-scarce-languages-37sjes3ff4.pdf

Pravallika Etoori

Papers

Automatic Spelling Correction for Resource-Scarce Languages using Deep Learning