Papers with Amazon
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) (N18-2)
Copied to clipboard
| Challenge: | NAACL HLT 2018 is the biggest NAAPL conference to date . this year's conference highlights the vibrancy and vitality of the field . |
| Approach: | a new review form and an opportunity for authors to review the reviewers were introduced at this year's conference . the test-of-time awards are named in memory of Aravind Joshi, who died this year . |
| Outcome: | the biggest NAACL conference to date features a new review form and the Test-of-Time awards . the industrial track features papers that focus on scalable, interpretable, reliable and customer facing methods for industrial applications . |
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) (N18-1)
Copied to clipboard
| Challenge: | NAACL HLT 2018 is the biggest NAAPL conference to date . this year's conference highlights the vibrancy and vitality of the field . |
| Approach: | a new review form and an opportunity for authors to review the reviewers were introduced at this year's conference . the test-of-time awards are named in memory of Aravind Joshi, who died this year . |
| Outcome: | the biggest NAACL conference to date features a new review form and the Test-of-Time awards . the industrial track features papers that focus on scalable, interpretable, reliable and customer facing methods for industrial applications . |
Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER) (D19-66)
Copied to clipboard
| Challenge: | a workshop on fact extraction and verification is being held at EMNLP 2019 . |
| Approach: | the authors propose a workshop to promote research in joint Fact Extraction and VERification . they received 25 submissions, five of which were system descriptions . |
| Outcome: | the proposed workshop promotes research in joint Fact Extraction and VERification (FEVER) the updated leaderboard will be presented at the second workshop. |
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) (N19-1)
Copied to clipboard
| Challenge: | 2019 Program Co-Chairs have managed the largest number of submissions at any NAACL to date . submissions in 2019 almost doubled from the previous year . |
| Approach: | NAACL's 2019 Program Co-Chairs have managed the largest number of submissions to date . 2019 will see a diversity committee, a careers in NLP panel and a panel on diversity . |
| Outcome: | The 2019 Program Co-Chairs have managed the largest number of submissions at any NAACL to date. |
Towards Opinion Summarization of Customer Reviews (P18-3)
Copied to clipboard
| Challenge: | Existing methods to summarize text are limited to small, homogeneous datasets . authors outline future directions to solve these problems . |
| Approach: | They propose to use neural networks to generate summaries of user-generated travel reviews . they aim to take into account shifting opinions over time and address these issues . |
| Outcome: | The proposed method will make it easier for users of review sites to make more informed decisions. |
Pay-Per-Request Deployment of Neural Network Models Using Serverless Architectures (N18-5)
Copied to clipboard
| Challenge: | Using Amazon’s Lambda service for feedforward evaluation and DynamoDB for word embeddings, we demonstrate a serverless deployment of neural networks for NLP applications. |
| Approach: | They propose a pay-per-request pricing model for neural network deployment in NLP applications using Amazon’s Lambda service for feedforward evaluation and DynamoDB for storing word embeddings. |
| Outcome: | The proposed architecture is scalable and inexpensive. |
Multilingual Continual Learning using Attention Distillation (2025.coling-industry)
Copied to clipboard
| Challenge: | Existing models for Query-product relevance classification are not accurate across multiple languages. |
| Approach: | They propose a multilingual continual learning framework that adds adapters for each new language and incorporates a fusion layer above language-specific adapters. |
| Outcome: | The proposed approach reduces trainable parameters by 80% while outperforming SOTA CL methods on proprietary and external datasets. |
Ask-and-Verify: Span Candidate Generation and Verification for Attribute Value Extraction (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing reading comprehension models can over-generate attribute values which hinders precision. |
| Approach: | They propose a product attribute value extraction task that captures key factual information from product descriptions and a new end-to-end pipeline framework called Ask-and-Verify. |
| Outcome: | The proposed framework outperforms existing models by up to 3.1% F1 absolute improvement points while scaling to thousands of attributes. |
Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce (N19-2)
Copied to clipboard
| Challenge: | Existing methods for short product title generation only consider textual information from long titles . MM-GAN incorporates image information and attribute tags from product, as well as textual info from original long titles. |
| Approach: | They propose a multi-modal generative adversarial network for short product title generation in E-commerce . they incorporate image information and attribute tags from product, as well as textual information from original long titles . |
| Outcome: | The proposed model outperforms state-of-the-art methods on a large-scale E-commerce dataset. |
Deep Metric Learning to Hierarchically Rank - An Application in Product Retrieval (2023.emnlp-industry)
Copied to clipboard
Kee Kiat Koo, Ashutosh Joshi, Nishaanth Reddy, Karim Bouyarmane, Ismail Tutar, Vaclav Petricek, Changhe Yuan
| Challenge: | e-commerce search engines use customer behavior signals to augment lexical matching and improve search relevance. |
| Approach: | They propose a method to identify duplicate and near-duplicate products across stores . they use Hierarchical Ranked Multi Similarity Loss to learn hierarchical metric space . |
| Outcome: | The proposed model outperforms baselines in terms of catalog coverage and precision of the mappings. |
Rationale-Guided Distillation for E-Commerce Relevance Classification: Bridging Large Language Models and Lightweight Cross-Encoders (2025.coling-industry)
Copied to clipboard
| Challenge: | Large-scale e-commerce search systems typically follow a multi-step process to retrieve relevant products for a given query. |
| Approach: | They propose a distillation approach that uses "rationales" generated by Large Language Models to guide smaller cross-encoder models. |
| Outcome: | The proposed model achieves ROC-AUC improvements of 1.4% on 9 multilingual e-commerce datasets, 2.4% on 3 ESCI datasets and 6% on GLUE datasets while being 50 times faster per sample. |
EasyTurk: A User-Friendly Interface for High-Quality Linguistic Annotation with Amazon Mechanical Turk (2021.eacl-demos)
Copied to clipboard
| Challenge: | Amazon Mechanical Turk (AMT) is one of the most popular crowd-sourcing platforms, allowing researchers from all over the world to create linguistic datasets quickly and at a relatively low cost. |
| Approach: | They propose to improve the potential of Amazon Mechanical Turk by adding some new features to the tool. |
| Outcome: | The proposed tool improves the performance of Amazon Mechanical Turk by adding new features. |
Are the Tools up to the Task? an Evaluation of Commercial Dialog Tools in Developing Conversational Enterprise-grade Dialog Systems (N19-2)
Copied to clipboard
| Challenge: | Existing toolsets are incomplete in meeting the goal of building effective dialog systems, authors say . |
| Approach: | They compare dialog tools available from a number of companies to determine their strengths and weaknesses . they provide quantitative and qualitative results in three main areas: natural language understanding, dialog, and text generation . |
| Outcome: | The toolsets are incomplete, but they are compared to other tools to determine their strengths and weaknesses. |
Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributes (2023.acl-industry)
Copied to clipboard
| Challenge: | E-commerce websites often don’t label or mislabel attributes of products . |
| Approach: | They propose a multi-modal product attribute generation system that extracts product attributes from the product pages of eCommerce stores by using both text and images. |
| Outcome: | The proposed model improves the recall@90P accuracy by 10.16% and 6.9 from the state-of-the-art models. |
IPL: Leveraging Multimodal Large Language Models for Intelligent Product Listing (2024.emnlp-industry)
Copied to clipboard
Kang Chen, Qing Zhang, Chengbao Lian, Yixin Ji, Xuwei Liu, Shuguang Han, Guoqiang Wu, Fei Huang, Jufeng Chen
| Challenge: | Unlike professional Business-to-Consumer (B2C) e-commerce platforms, consumer-to consumer (C2C), is mainly targeting individual sellers. |
| Approach: | They develop an intelligent product listing tool that generates product descriptions using various product attributes such as category, brand, color, condition, etc. |
| Outcome: | The proposed tool outperforms the base model in domain-specific tasks while producing less hallucination. |
Generative Models for Product Attribute Extraction (2023.emnlp-industry)
Copied to clipboard
| Challenge: | generative models are used for product attribute extraction, a new field in information extraction and e-commerce. |
| Approach: | They analyze generative models for product attribute extraction and demonstrate their utility . they perform experiments on Amazon and MAVE product attribute datasets . |
| Outcome: | The proposed model can generate implicit attribute values, which state-of-the-art models are unable to extract. |
From Disjoint Sets to Parallel Data to Train Seq2Seq Models for Sentiment Transfer (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for sentiment transfer have relied on unsupervised methods due to lack of parallel corpora. |
| Approach: | They propose a method for creating parallel data to train Seq2Seq neural networks for sentiment transfer. |
| Outcome: | The proposed method outperforms existing unsupervised methods in sentiment transfer tasks. |
Multi-source Multi-domain Sentiment Analysis with BERT-based Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Sentiment analysis is a widely studied task in natural language processing. |
| Approach: | They propose to improve BERT-based models for sentiment analysis on italian corpora and evaluate their performance on the basis of eight corpors. |
| Outcome: | The proposed model is evaluated over eight sentiment analysis corpora from different domains and sources on the prediction of positive, negative and neutral classes. |
A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on product search tasks, but ignore potential risks. |
| Approach: | They propose a data generation pipeline that leverages webpage content and interactive elements to create diverse, functionality-grounded user queries. |
| Outcome: | The proposed framework assesses the performance and safety of web agents under dynamic, real-world e-commerce environments. |
“Alexa in the wild” – Collecting Unconstrained Conversations with a Modern Voice Assistant in a Public Environment (2020.lrec-1)
Copied to clipboard
| Challenge: | Currently, many studies on human-machine interactions focus on private usage, short pre-defined tasks or specific domains. |
| Approach: | They propose to collect 40 hours of device directed utterances during a science exhibition in germany and extract transcripts of both visitors requests and Alexa answers. |
| Outcome: | The proposed dataset provides an unconstrained, unscripted public interaction with a voice assistant during a science exhibition in germany. |
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach (P18-1)
Copied to clipboard
| Challenge: | Existing studies for sentiment-to-sentiment "translation" only change the underlying sentiment and fail to keep the semantic content. |
| Approach: | They propose a cycled reinforcement learning method that combines neutralization module and emotionalization module. |
| Outcome: | The proposed method outperforms state-of-the-art systems on Yelp and Amazon review datasets. |
Efficient Few-Shot Fine-Tuning for Opinion Summarization (2022.findings-naacl)
Copied to clipboard
| Challenge: | Abstractive summarization models are typically pre-trained on large amounts of generic texts . large annotated datasets of reviews paired with reference summaries are not available . |
| Approach: | They propose a few-shot method which uses adapters to store in-domain knowledge . they pre-train adapters on unannotated customer reviews and fine-tune them on annotated datasets . |
| Outcome: | The proposed method can store in-domain knowledge and improves on large annotated reviews . it improves coherence and redundancies on the Amazon and Yelp datasets . |
Aggregating Crowd of LLMs for Cost-Effective Data Annotation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have shown promise for automated data annotation, yet reliance on expensive commercial models like GPT-4 limits accessibility. |
| Approach: | They propose to build a crowd of LLMs which aggregates annotations from multiple sLLMs using label aggregation algorithms. |
| Outcome: | The proposed approach outperforms individual sLLMs and human crowd labels yields superior results compared to either method alone. |
Combining Deep Learning and Topic Modeling for Review Understanding in Context-Aware Recommendation (N18-1)
Copied to clipboard
| Challenge: | Existing models for user reviews are limited by data sparsity and lack of data. |
| Approach: | They propose to integrate LSTM and Topic Modeling to extract review information for recommender systems by utilizing user reviews. |
| Outcome: | The proposed model outperforms existing models on Amazon review dataset and shows better ability on making topic clustering than traditional topic model based method. |
Product Description and QA Assisted Self-Supervised Opinion Summarization (2024.findings-naacl)
Copied to clipboard
Tejpalsingh Siledar, Rupasai Rangaraju, Sankara Muddu, Suman Banerjee, Amey Patil, Sudhanshu Singh, Muthusamy Chelliah, Nikesh Garera, Swaprava Nath, Pushpak Bhattacharyya
| Challenge: | Existing methods to generate opinion summarization without supervised training data are limited due to the lack of additional sources. |
| Approach: | They propose a synthetic dataset creation strategy that leverages reviews and additional sources to generate a pseudo-summary. |
| Outcome: | The proposed approach achieves 14.5% improvement in ROUGE-1 F1 over existing models. |
Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer (N18-1)
Copied to clipboard
| Challenge: | Previous work using adversarial methods has struggled to produce high-quality outputs. |
| Approach: | They propose a method that transforms a sentence to alter a specific attribute while preserving its attribute-independent content. |
| Outcome: | The proposed method generates grammatical and appropriate responses on 22% more inputs than the best previous system, averaged over three attribute transfer datasets. |
Multi-Domain Targeted Sentiment Analysis (2022.naacl-main)
Copied to clipboard
| Challenge: | Targeted Sentiment Analysis (TSA) is a task for generating insights from consumer reviews. |
| Approach: | They propose a multi-domain TSA system that augments a given training set with diverse weak labels from assorted domains and augments it with Yelp reviews. |
| Outcome: | The proposed model outperforms manual methods on three evaluation datasets across different domains and shows that it performs well. |
Opinion Summarization by Weak-Supervision from Mix-structured Data (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for opinion summarization of multiple reviews lack reference summaries . OAs and ISs are often mismatched between review input and summary . |
| Approach: | They propose a method to generate mixed-structured synthetic training data for opinion summarization. |
| Outcome: | The proposed method outperforms existing methods on Yelp, Amazon and RottenTomatos datasets. |
Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models’ Memories (2023.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models demonstrate excellent abilities to understand texts in the generic domain while struggling in a specific domain. |
| Approach: | They propose to decouple the feed-forward networks of the Transformer architecture into two parts to maintain old-domain knowledge and a mixture-of-adapters gate to inject domain-specific knowledge in parallel. |
| Outcome: | The proposed method achieves superior performance on in-domain, out-of-domain and knowledge-intensive tasks. |
Few-Shot Learning for Opinion Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that abstractive summarization models fail to capture their essential properties due to the high cost of summary production. |
| Approach: | They propose a few-shot framework for abstractive opinion summarization that bootstraps the output of an unsupervised model. |
| Outcome: | The proposed framework outperforms extractive and abstractive methods on Amazon and Yelp datasets. |
Rethinking Style Transformer with Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model (2022.emnlp-main)
Copied to clipboard
Hojun Cho, Dohee Kim, Seungwoo Ryu, ChaeHun Park, Hyungjong Noh, Jeong-in Hwang, Minseok Choi, Edward Choi, Jaegul Choo
| Challenge: | Existing methods to train text style transfer models with adversarial loss degrade fluency compared to other metrics. |
| Approach: | They propose a method which leverages a pretrained language model to improve fluency by restructuring the discriminator and the model itself. |
| Outcome: | The proposed model achieves state-of-the-art on three public benchmarks and achieved state-outperformance on the overall metrics. |
Unsupervised Opinion Summarization as Copycat-Review Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work on opinion summarization has focused on extracting fragments from reviews, but we use novel sentences to generate abstractive summaries. |
| Approach: | They propose an abstractive summarizer which does not use summaries in training and is trained end-to-end on a large collection of reviews. |
| Outcome: | The proposed model produces fluent and coherent summaries reflecting consensus opinions on Amazon and Yelp reviews. |
Decode with Template: Content Preserving Sentiment Transfer (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to transfer sentiments for text use only explicit sentiments and templates to remove them from input sentences. |
| Approach: | They propose a method to transfer sentiments from input sentences to output sentences using templates. |
| Outcome: | The proposed model significantly outperforms state-of-the-art models in content preservation. |
Prompted Opinion Summarization with GPT-3.5 (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent years have seen several shifts in summarization research, including extractive models. |
| Approach: | They propose a pipeline method for applying GPT-3.5 to summarize user reviews . they propose three new metrics targeting faithfulness, factuality, and genericity . |
| Outcome: | The proposed methods perform well in opinion summarization, the authors show . they also show that standard evaluation metrics do not reflect this performance . |
YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews (2021.emnlp-main)
Copied to clipboard
| Challenge: | YASO contains 2,215 English sentences from dozens of review domains, annotated with target terms and their sentiment. |
| Approach: | They propose a new TSA evaluation dataset of open-domain user reviews in English . YASO contains 2,215 English sentences annotated with target terms and their sentiment . |
| Outcome: | The proposed dataset verifies the reliability of the annotations and explores the characteristics of the collected data. |
Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals (2022.emnlp-main)
Copied to clipboard
| Challenge: | a recent study found that finetuned language models rely on spurious patterns in training data . this limitation limits their performance on out-of-distribution (OOD) test data. |
| Approach: | They propose a method that only requires annotation of a small fraction of training data . they add 1% manual counterfactuals to training data and generate extra counterfacts in vector space . |
| Outcome: | The proposed approach improves sentiment classification using IMDb data and other sets for OOD tests. |
Synthesize, if you do not have: Effective Synthetic Dataset Creation Strategies for Self-Supervised Opinion Summarization in E-commerce (2023.findings-emnlp)
Copied to clipboard
Tejpalsingh Siledar, Suman Banerjee, Amey Patil, Sudhanshu Singh, Muthusamy Chelliah, Nikesh Garera, Pushpak Bhattacharyya
| Challenge: | Existing approaches to generate general and aspect-specific opinion summarization are limited due to their reliance on human-specified aspects and seed words. |
| Approach: | They propose synthetic dataset creation approaches for general and aspect-specific opinion summarization . general opinion summaries struggle to generate faithful to the input reviews, they say . aspect- specific opinion summarisation models are limited due to reliance on human-specified aspects . |
| Outcome: | The proposed approach outperforms existing models on three e-commerce test sets on general and aspect-specific opinion summarization. |
Federated Meta-Learning for Emotion and Sentiment Aware Multi-modal Complaint Identification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on complaint identification are limited to text. |
| Approach: | They propose a meta-learning-based multi-modal multi-task framework for identifying complaints using emotion recognition and sentiment analysis as auxiliary tasks. |
| Outcome: | The proposed framework outperforms baselines and state-of-the-art approaches in centralized and federated meta-learning settings. |
The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation. |
| Approach: | They propose to use a dataset to investigate a new type of bias in Large Language Models for code generation, provider bias, to determine whether the model favors specific providers. |
| Outcome: | The proposed model favors services from Google and Amazon, but without explicit directives, and can modify input code to incorporate their preferred providers without user requests. |
R-Fairness: Assessing Fairness of Ranking in Subjective Data (2025.acl-long)
Copied to clipboard
| Challenge: | Subjective data, reflecting individual opinions, permeates platforms like Yelp and Amazon . despite the prevalence of such platforms, little attention has been given to fairness in their context . |
| Approach: | They propose a fairness assessment pipeline that starts with data collection phase and then iterates through rated items. |
| Outcome: | The proposed approach favors groups writing best-ranked reviews over others on collaborative rating platforms. |