Spain

Online customer reviews are of growing importance for many businesses in the hospitality industry, particularly restaurants and hotels. Managerial responses to such reviews provide businesses with the opportunity to influence the public discourse and to attain improved ratings over time. However, responding to each and every review is a time-consuming endeavour. Therefore, we investigate automatic generation of review responses in the hospitality domain for two languages, English and German. 

We apply an existing system, originally proposed for review response generation for smartphone apps. This approach employs an extended neural network sequence-to-sequence architecture and performs well in the original domain. However, as shown through our experiments, when applied to a new domain, such as hospitality, performance drops considerably. Therefore, we analyse potential causes for the differences in performance and provide evidence to suggest that review response generation in the hospitality domain is a more challenging task and thus requires further study and additional domain adaptation techniques.

COLING 2020

Benchmarking Automated Review Response Generation for the Hospitality Domain

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

technical paper

We tackle tag-based query refinement as a mobile-friendly alternative to standard facet search. We approach the inference challenge with reinforcement learning, and propose a deep contextual bandit that can be efficiently scaled in a multi-tenant SaaS scenario.

Blending Search and Discovery: Tag-Based Query Refinement with Contextual Reinforcement Learning

Information retrieval chatbots are widely used as assistants, to help users formulate their requirements about the products they want to purchase and navigate to the set of items that satisfies their requirements in the best way. The work of the modern chatbots is based mostly on the deep learning theory behind the knowledge model that can improve the performance of the system. In our work, we are developing a concept-based knowledge model that encapsulates objects and their common descriptions. The leveraging of the concept-based knowledge model allows the system to refine the initial users’ requests and lead them to the set of objects with the maximal variability of parameters that matters less to them. Introducing the additional textual characteristics allows users to formulate their initial query as a phrase in natural language, rather than as some standard request in the form of, “Attribute - value”.

On a Chatbot Navigating a User through a Concept-Based Knowledge Model

Product matching, i.e., being able to infer the product being sold for a merchant-created offer, is crucial for any e-commerce marketplace, enabling product-based navigation, price comparisons, product reviews, etc. This problem proves a challenging task, mostly due to the extent of product catalog, data heterogeneity, missing product representants, and varying levels of data quality. Moreover, new products are being introduced every day, making it difficult to cast the problem as a classification task. 
In this work, we apply BERT-based models in a similarity learning setup to solve the product matching problem. We provide a thorough ablation study, showing the impact of architecture and training objective choices. Application of transformer-based architectures and proper sampling techniques significantly boosts performance for a range of e-commerce domains, allowing for production deployment.

BERT-based similarity learning for product matching

Many e-commerce services provide customer review systems. Previous laboratory studies have indicated that the ratings recorded by these systems differ from the actual evaluations of the users, owing to the influence of historical ratings in the system. Some studies have proposed using real-world datasets to model rating prediction. Herein, we propose an aspect-similarity-aware historical influence model for rating prediction using natural language processing techniques. In general, each user provides a rating considering different aspects. Thus, it can be assumed that historical ratings provided considering similar aspects to those of later ones will influence evaluations of users more. By focusing on the review-topic similarities, we show that our method predicts ratings more accurately than the previous historical-inference-aware model. In addition, we examine whether our model can predict ``intrinsic rating,'' which is given if users were not influenced by historical ratings. We performed an intrinsic rating prediction task, and showed that our model achieved improved performance. Our method can be useful to debias user ratings collected by customer review systems. The debiased ratings help users to make decision properly and systems to provide helpful recommendations. This might improve the user experience of e-commerce services.

Aspect-Similarity-Aware Historical Influence Modeling for Rating Prediction

E-commerce sites include advertising slogans along with information regarding items. Slogans can attract viewers' attention to increase sales or visits by emphasizing advantages of items. The aim of this study is to generate a slogan from a description of an item. To generate a slogan, we apply an encoder-decoder model which has shown effectiveness in many kinds of natural language generation tasks, such as abstractive summarization. However, slogan generation task has three characteristics that distinguish it from other natural language generation tasks: distinctiveness, topic emphasis, and style difference. To handle these three characteristics, we propose a compressed representation-based reconstruction model with refer-attention and conversion layers. The results of experiments with automatic and human evaluations indicate that our method achieves higher performance than conventional methods.

Distinctive Slogan Generation with Reconstruction

Coping with ambiguous questions has been a perennial problem in real-world dialogue systems.
Although clarification by asking questions is a common form of human interaction, it is hard to define appropriate questions to elicit more specific intents from a user.
In this work, we propose a reinforcement model to clarify ambiguous questions by suggesting refinements of the original query. We first formulate a collection partitioning problem to select a set of labels enabling us to distinguish potential unambiguous intents.
We list the chosen labels as intent phrases to the user for further confirmation. The selected label along with the original user query then serves as a refined query, for which a suitable response can more easily be identified.
The model is trained using reinforcement learning with a deep policy network. 
We evaluate our model based on real-world user clicks and demonstrate significant improvements across several different experiments.

Interactive Question Clarification in Dialogue via Reinforcement Learning

The goal of text simplification (TS) is to transform difficult text into a version that is easier to understand and more broadly accessible to a wide variety of readers. In some domains, such as healthcare, fully automated approaches cannot be used since information must be accurately preserved. Instead, semi-automated approaches can be used that assist a human writer in simplifying text faster and at a higher quality. In this paper, we examine the application of autocomplete to text simplification in the medical domain. We introduce a new parallel medical data set consisting of aligned English Wikipedia with Simple English Wikipedia sentences and examine the application of pretrained neural language models (PNLMs) on this dataset. We compare four PNLMs (BERT, RoBERTa, XLNet, and GPT-2), and show how the additional context of the sentence to be simplified can be incorporated to achieve better results (6.17% absolute improvement over the best individual model). We also introduce an ensemble model that combines the four PNLMs and outperforms the best individual model by 2.1%, resulting in an overall word prediction accuracy of 64.52%.


AutoMeTS: The Autocomplete for Medical Text Simplification.

Low-resource Machine Translation recently gained a lot of popularity, and for certain languages, it has made great strides. However, it is still difficult to track progress in other languages for which there is no publicly available evaluation data. In this paper, we introduce benchmark datasets for Arabic and its dialects. We describe our design process and motivations and analyze the datasets to understand their resulting properties. Numerous successful attempts use large monolingual corpora to augment low-resource pairs. We try to approach augmentation differently and investigate whether it is possible to improve MT models without any external sources of data. We accomplish this by bootstrapping existing parallel sentences and complement this with multilingual training to achieve strong baselines.

Datasets for Low-Resource Machine Translation of Arabic Dialects

Data scarcity is always a constraint on analyzing speech transcriptions for automatic Alzheimer’s disease (AD) detection, especially when the subjects are non-English speakers. To deal with this issue, this paper first proposes a contrastive learning method to obtain effective representations for text classification based on monolingual embeddings of BERT. Furthermore, a cross-lingual data augmentation method is designed by building autoencoders to learn the text representations
shared by both languages. Experiments on a Mandarin AD corpus show that the contrastive learning method can achieve better detection accuracy than conventional CNN-based and BERTbased methods. Our cross-lingual data augmentation method also outperforms other compared methods when using another English AD corpus for augmentation. Finally, a best detection accuracy of 81.6% is obtained by our proposed methods on the Mandarin AD corpus.

Text Classification by Contrastive Learning and Cross-lingual Data Augmentation for Alzheimer’s Disease Detection

Efficient document summarization requires evaluation measures that can not only rank a set of systems based on an average score, but also highlight which individual summary is better than another. However, despite the very active research on summarization approaches, few works have proposed new evaluation measures in the recent years. 

The standard measures relied upon for the development of summarization systems are most often ROUGE and BLEU which, despite being efficient in overall system ranking, remain lexical in nature and have a limited potential when it comes to training neural networks. 

In this work, we present HOLMS, a new hybrid evaluation measure for summarization that combines both language models pre-trained on large corpora and lexical similarity measures. Through several experiments, we show that HOLMS outperforms ROUGE and BLEU substantially in its correlation with human judgments on several extractive summarization datasets for both linguistic quality and pyramid scores. 


Benchmarking Automated Review Response Generation for the Hospitality Domain

Downloads

Next from COLING 2020

Blending Search and Discovery: Tag-Based Query Refinement with Contextual Reinforcement Learning

Similar lecture

On a Chatbot Navigating a User through a Concept-Based Knowledge Model

Benchmarking Automated Review Response Generation for the Hospitality Domain

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Blending Search and Discovery: Tag-Based Query Refinement with Contextual Reinforcement Learning

Similar lecture

On a Chatbot Navigating a User through a Concept-Based Knowledge Model

Downloads