Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)

MathPrompter: Mathematical Reasoning using Large Language Models (2023.acl-industry)

Challenge:	Unclaimed embodiment extraction is performed manually and little research has been conducted on its automation.
Approach:	They propose a task of unclaimed embodiment extraction and a dataset for the task . they use a natural language inference task to extract unclaimed inventions .
Outcome:	The proposed task requires performing natural language inference on patent specifications.

Copied to clipboard

Shima Imani, Liang Du, Harsh Shrivastava

Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems (2023.acl-industry)

Challenge:	Recent advances in natural language processing (NLP) can be attributed to massive scaling of Large Language Models (LLMs).
Approach:	They propose a technique that improves performance of Large Language Models (LLMs) on arithmetic problems along with increased reliance in the predictions.
Outcome:	The proposed technique improves performance on arithmetic problems and increases confidence in the output results.

Copied to clipboard

Mohammad Kachuee, Sungjin Lee

pNLP-Mixer: an Efficient all-MLP Architecture for Language (2023.acl-industry)

Challenge:	Recent self-learning methods based on user satisfaction metrics and contextual bandits have shown promising results to enable consistent improvements in conversational AI systems.
Approach:	They propose a meta-gradient learning approach that adjusts constraint violation penalty terms adaptively through a user-defined meta objective that encourages balanced constraint satisfaction across domains.
Outcome:	The proposed framework supports fine-grained exploration targets for individual domains via user-defined constraints.

Copied to clipboard

Francesco Fusco, Damian Pascual, Peter Staar, Diego Antognini

Extracting Text Representations for Terms and Phrases in Technical Domains (2023.acl-industry)

Challenge:	large pre-trained language models are impractical for on-device applications due to their size and inference cost.
Approach:	They propose an embedding-free MLP-Mixer model for on-device NLP that achieves high weight-efficiency thanks to a novel projection layer.
Outcome:	The proposed model beats state-of-the-art of tiny models by 97.8% on two datasets . it beats mBERT on MTOP and multiATIS, while using 170x less parameters .

Copied to clipboard

Francesco Fusco, Diego Antognini

CocaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval (2023.acl-industry)

Challenge:	Large pre-trained language models are extensively used in modern NLP systems.
Approach:	They propose an unsupervised approach to encoding using character-based models and pre-trained sentence encoders to reconstruct large pre-trained embedding matrices.
Outcome:	The proposed approach matches the quality of sentence encoders in technical domains and is 5 times smaller and up to 10 times faster on high-end GPUs.

Copied to clipboard

Jiapeng Wang, Chengyu Wang, Xiaodan Wang, Jun Huang, Lianwen Jin

KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerce (2023.acl-industry)

Challenge:	Existing methods for text-image retrieval are limited to edge devices and real-time situations due to the substantial indexing and inference time.
Approach:	They propose a fully-Connected knowledge interaction graph technique for cross-modal pre-training distillation.
Outcome:	The proposed method achieves SOTA performances on the widely-used Flickr30K and MSCOCO benchmarks under the lightweight setting.

Copied to clipboard

Qinjin Jia, Yang Liu, Daoping Wu, Shaoyuan Xu, Huidong Liu, Jinmiao Fu, Roland Vollgraf, Bryan Wang

Domain-specific transformer models for query translation (2023.acl-industry)

Challenge:	Various visionlanguage pre-training (VLP) models learn cross-modal alignment from large-scale well-aligned image-text datasets without leveraging external knowledge.
Approach:	They propose a knowledge-guided fashion-domain language-image pre-training framework that learns fine-grained representations in e-commerce domain and utilizes external knowledge to improve the pre-train efficiency.
Outcome:	The proposed framework outperforms state-of-the-art models on Amazon and Fashion-Gen datasets by large margins.

Copied to clipboard

Mandar Kulkarni, Nikesh Garera, Anusua Trivedi

Label efficient semi-supervised conversational intent classification (2023.acl-industry)

Challenge:	In domains such as Grocery, users prefer to buy certain brands of products . a large non-English speaking population makes it difficult to translate code-mix queries .
Approach:	They propose a model to preserve/correct Grocery brand names while translating context words . they propose to use a dataset of popular Groceries brand names to train the model .
Outcome:	The proposed model preserves/corrects Grocery brand names while translating context words . it is tested with a large non-English speaking population and is deployed in production .

Copied to clipboard

Mandar Kulkarni, Kyung Kim, Nikesh Garera, Anusua Trivedi

Responsible & Trustworthy NLP

Challenge:	A conversational chatbot can answer pre-purchase questions and post-purchase queries to provide a seamless shopping experience.
Approach:	They propose a semi-supervised learning approach for label-efficient intent classification using a small labeled corpus and large unlabeled query data to train a transformer model.
Outcome:	The proposed approach significantly improves over the baseline, even with a limited labeled set.

xPQA: Cross-Lingual Product Question Answering in 12 Languages (2023.acl-industry)

Copied to clipboard

Xiaoyu Shen, Akari Asai, Bill Byrne, Adria De Gispert

Multilinguality

Challenge:	Existing work on product question answering systems focuses mainly on English, but in practice there is need to support multiple customer languages while leveraging product information available in English.
Approach:	They present a large-scale annotated cross-lingual PQA dataset in 12 languages and evaluate three approaches to generating a natural-sounding non-English answer.
Outcome:	The proposed dataset supports crosslingual product question answering (PQA) systems that provide answers to customers’ questions as they shop for products.

Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection (2023.acl-industry)

Copied to clipboard

Beizhe Hu, Qiang Sheng, Juan Cao, Yongchun Zhu, Danding Wang, Zhengjia Wang, Zhiwei Jin

Reasoning

Challenge:	Existing work on fake news detection does not consider the temporal shift issue caused by the rapidly-evolving nature of news data.
Approach:	They propose a framework to forecast temporal patterns of news data and guide detector to fast adapt to future distributions.
Outcome:	The proposed framework forecasts temporal distribution patterns and guides detector to fast adapt to future distribution.

AVEN-GR: Attribute Value Extraction and Normalization using product GRaphs (2023.acl-industry)

Copied to clipboard

Thomas Ricatte, Donato Crisostomi

GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model (2023.acl-industry)

Challenge:	Query Attribute Understanding (QAU) is a sub-component of QU that involves extracting named attributes from user queries.
Approach:	They propose a novel end-to-end approach that solves Named Entity Recognition and Entity Linking for QAU . they propose utilizing product graphs to enhance the representation of query entities .
Outcome:	The proposed approach solves Named Entity Recognition and Entity Linking and enables open-world reasoning for QAU.

Copied to clipboard

Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Shu Zhao, Peng Zhang, Jie Tang

FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph (2023.acl-industry)

Challenge:	Existing knowledge distillation frameworks for language models are limited by memory and the use of complex distillation methods on larger-scale PLMs.
Approach:	They propose a general knowledge distillation framework that supports distillation on larger-scale PLMs using various distillation methods.
Outcome:	The proposed framework can support distillation on larger-scale PLMs and 25 mainstream methods on 8 NVIDIA A100 (40GB) GPUs.

Copied to clipboard

Xiaodan Wang, Chengyu Wang, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, Ming Gao

Entity Contrastive Learning in a Large-Scale Virtual Assistant System (2023.acl-industry)

Challenge:	Recent advances in visual-language pre-trained (VLP) models have greatly improved cross-modal retrieval performance . however, the fine-grained interactions between objects from different modalities are far from well-established . e-commerce domain lacks sufficient training data and fine-granular cross-modulal knowledge .
Approach:	They propose a visual-language pre-trained (VLP) image-text retrieval model that integrates cross-modal knowledge into the model to improve performance.
Outcome:	The proposed model improves performance on e-commerce image-text retrieval task by a large margin.

Copied to clipboard

Jonathan Rubin, Jason Crowley, George Leung, Morteza Ziyadi, Maria Minakova

Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce Catalog (2023.acl-industry)

Challenge:	Named Entity Recognition (NER) tasks are a well-studied and fundamental task within Natural Language Understanding (NLU).
Approach:	They propose to incorporate entity contrastive learning into a virtual assistant system to improve NER models by clustering similar inputs closer together in a learned representation space.
Outcome:	The proposed model improves against a production baseline system that does not use contrastive learning.

Copied to clipboard

Kewei Cheng, Xian Li, Zhengyang Wang, Chenwei Zhang, Binxuan Huang, Yifan Ethan Xu, Xin Luna Dong, Yizhou Sun

Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs (2023.acl-industry)

Challenge:	Existing methods for analyzing textual attributes in product catalogs are not effective on structured tabular data since they are trained on free-form natural language texts.
Approach:	They propose a model to handle error detection over tabular data following a pre-training paradigm.
Outcome:	The proposed model improves on a real-world Amazon Product Catalog table by 16% over state-of-the-art methods and by 11% on PR AUC over attribute value validation task.

Copied to clipboard

Abishek Komma, Nagesh Panyam Chandrasekarasastry, Timothy Leffel, Anuj Goyal, Angeliki Metallinou, Spyros Matsoukas, Aram Galstyan

Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial Reports (2023.acl-industry)

Challenge:	Existing methods to dialog quality estimation focus on evaluating individual turns or collecting dialog-level quality measurements from end users immediately following an interaction.
Approach:	They propose a dialog-level annotation workflow called Dialog Quality Annotation . they propose to annotate dialogs for attributes such as goal completion and user sentiment .
Outcome:	The proposed model outperforms existing methods for dialog quality estimation . it shows that high-quality human-annotated data is important for dialog-quality evaluation .

Copied to clipboard

Chuang Liu, Junzhuo Li, Deyi Xiong

KoSBI: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Applications (2023.acl-industry)

Challenge:	Existing conversational question answering datasets are usually constructed from unstructured texts in English.
Approach:	They propose a Chinese tabular conversational question answering dataset based on financial reports . they select 2,463 tables and manually generate 2,463, conversations with 35,494 QA pairs .
Outcome:	The proposed dataset is based on Chinese financial reports extracted from listed companies in the past 30 years.

Copied to clipboard

Hwaran Lee, Seokhee Hong, Joonsuk Park, Takyoung Kim, Gunhee Kim, Jung-woo Ha

Improving Knowledge Production Efficiency With Question Answering on Conversation (2023.acl-industry)

Challenge:	Existing research and resources are not readily applicable in South Korea due to the differences in language and culture, both of which significantly affect the biases and targeted demographic groups.
Approach:	They propose a social bias dataset of 34k pairs of contexts and sentences in Korean covering 72 demographic groups in 15 categories.
Outcome:	The proposed dataset reduces social biases by 16.47%p on average for HyperClova (30B and 82B), and GPT-3.

Copied to clipboard

Changlin Yang, Siye Liu, Sen Hu, Wangshu Zhang, Teng Xu, Jing Zheng

Mitigating the Burden of Redundant Datasets via Batch-Wise Unique Samples and Frequency-Aware Losses (2023.acl-industry)

Challenge:	Existing researches on conversation-based QA focus on document-based tasks . current researche focuses on document based tasks, but there is a lack of researche on conversation based qa .
Approach:	They propose a multi-span extraction model on conversation-based QA and introduce continual pre-training and multi-task learning schemes to further improve model performance.
Outcome:	The proposed model outperforms baseline on two Chinese datasets and will be released for research purposes.

Copied to clipboard

Donato Crisostomi, Andrea Caciolai, Alessandro Pedrani, Kay Rottmann, Alessandro Manzotti, Enrico Palumbo, Davide Bernardi

The economic trade-offs of large language models: A case study (2023.acl-industry)

Challenge:	Existing solutions to train deep learning models on redundant datasets are difficult to implement in industrial settings.
Approach:	They propose a method to eliminate duplicates at the batch level without altering the data distribution observed by the model.
Outcome:	The proposed approach reduces training times on models on redundant datasets by up to 87% and 46% on average, with a drop in model performance of 0.2% relative at worst.

Copied to clipboard

Kristen Howell, Gwen Christian, Pavel Fomitchov, Gitit Kehat, Julianne Marzulla, Leanne Rolston, Jadin Tredup, Ilana Zimmerman, Ethan Selfridge, Joseph Bradley

Application-Agnostic Language Modeling for On-Device ASR (2023.acl-industry)

Challenge:	Large Language Models (LLMs) are a natural fit for contact-based customer service, but their efficacy must be balanced with the cost of training and serving them.
Approach:	They propose a cost framework for evaluating an NLP model’s utility for the enterprise as a function of the usefulness of the responses that they generate.
Outcome:	The proposed model can be used to help human agents handle complex customer service calls and can be modified to improve their performance.

Copied to clipboard

Markus Nussbaum-thom, Lyan Verwimp, Youssef Oualil

Building Accurate Low Latency ASR for Streaming Voice Search in E-commerce (2023.acl-industry)

Challenge:	On-device automatic speech recognition systems face several challenges compared to server-based systems.
Approach:	They propose to use a feed-forward language model to build a single application-agnostic model . they propose to reduce disk size by half while maintaining speed and accuracy of original model a .
Outcome:	The proposed architecture reduces disk size by half while maintaining speed and accuracy of the original model.

Copied to clipboard

Abhinav Goyal, Nikesh Garera

PLAtE: A Large-scale Dataset for List Page Web Extraction (2023.acl-industry)

Challenge:	Recent years have witnessed the popularity of end-to-end ASR models, which have demonstrated higher accuracy compared to traditional pipelines with separate acoustic, pronunciation, and language models.
Approach:	They build accurate LSTM, attention and CTC based streaming ASR models for large-scale Hinglish voice search.
Outcome:	The proposed model achieves a word error rate (WER) of 3.69% without EOS and 4.78% with EOS, with 1300 ms (46.64%) reduction in latency.

Copied to clipboard

Aidan San, Yuan Zhuang, Jan Bakus, Colin Lockard, David Ciemiewicz, Sandeep Atluri, Kevin Small, Yangfeng Ji, Heba Elfardy

Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference Speed (2023.acl-industry)

Challenge:	Existing methods for web extraction are limited by the limited number of available large-scale datasets.
Approach:	They introduce a dataset that focuses on shopping data and a list page web extraction task.
Outcome:	The proposed dataset is the first large-scale list page web extraction dataset . it contains 52,898 items and 156,014 attributes, making it the first dataset based on this task .

Copied to clipboard

Bingyan Liu, Weifeng Lin, Zhongjie Duan, Chengyu Wang, Wu Ziheng, Zhang Zipeng, Kui Jia, Lianwen Jin, Cen Chen, Jun Huang

Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributes (2023.acl-industry)

Challenge:	Text-to-Image Synthesis (TIS) aims to generate images based on textual inputs . but, current diffusion-based models lack entity knowledge and low inference speed .
Approach:	They propose a framework for training and deploying latent diffusion models with rich entity knowledge injected and optimized networks.
Outcome:	The proposed framework improves image quality and inference speed and can be used in industrial applications.

Copied to clipboard

Anant Khandelwal, Happy Mittal, Shreyas Kulkarni, Deepak Gupta

Consistent Text Categorization using Data Augmentation in e-Commerce (2023.acl-industry)

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.

Copied to clipboard

Noa Avigdor, Guy Horowitz, Ariel Raviv, Stav Yanovsky Daye

An efficient method for Natural Language Querying on Structured Data (2023.acl-industry)

Challenge:	Upon closer inspection, we found inconsistencies in the labeling of similar items.
Approach:	They propose to improve an existing product categorization model that takes a product title as input and outputs the most suitable category out of thousands of available candidates.
Outcome:	The proposed model is based on a product title and outputs the most suitable category out of thousands of available candidates.

Copied to clipboard

Hanoz Bhathena, Aviral Joshi, Prateek Singh

Boosting Transformers and Language Models for Clinical Prediction in Immunotherapy (2023.acl-industry)

Challenge:	a new approach to NLQ on structured data is based on text-to-SQL type semantic parsing . domain classification, domain classification and domain classification are the main tasks . semantic parsed queries are less common when information is in structured form .
Approach:	They propose an efficient and reliable approach to natural language Querying on databases . they use domain classification, domain classification and slot/entity extraction to query a DB .
Outcome:	The proposed approach simplifies the NLQ on structured data problem to the following "bread and butter" tasks.

Copied to clipboard

Zekai Chen, Mariann Micsinai Balan, Kevin Brown

EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only (2023.acl-industry)

Challenge:	Current machine learning approaches to predict clinical outcomes are limited to tabular data and are not applicable to clinical prediction.
Approach:	They investigate the potential of transformers to improve clinical prediction compared to conventional machine learning approaches and address the challenge of few-shot learning in predicting rare disease areas.
Outcome:	The proposed model improves the accuracy of baseline models and language models under few-shot regimes and shows that it is more accurate than previous models.

Copied to clipboard

Kamer Yüksel, Ahmet Gunduz, Mohamed Al-badrashiny, Hassan Sawaf

Machine Translation

Challenge:	EvolveMT is a method for the efficient combination of multiple machine translation engines.
Approach:	They propose a method that selects the output from one engine for each segment and uses online learning techniques to predict the most appropriate system for each translation request.
Outcome:	The proposed method achieves similar translation accuracy at a lower cost than selecting the best translation of each segment from all translations using an MT quality estimator.

A Static Evaluation of Code Completion by Large Language Models (2023.acl-industry)

Copied to clipboard

Hantian Ding, Varun Kumar, Yuchen Tian, Zijian Wang, Rob Kwiatkowski, Xiaopeng Li, Murali Krishna Ramanathan, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta

Programming Languages in NLP

Challenge:	Large language models trained on code have shown great potential to increase productivity of software developers.
Approach:	They propose a static evaluation framework to quantify static errors in Python code completions by leveraging Abstract Syntax Trees.
Outcome:	The proposed framework is more efficient and applicable to code in the wild.

Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational Systems (2023.acl-industry)

Copied to clipboard

Sarthak Ahuja, Mohammad Kachuee, Fatemeh Sheikholeslami, Weiqing Liu, Jaeyoung Do

MobileNMT: Enabling Translation in 15MB and 30ms (2023.acl-industry)

Challenge:	Off-Policy reinforcement learning has been used to improve conversational AIs, but in large-scale commercial environments it is challenging to balance between policy improvements and experience continuity.
Approach:	They propose to curate and leverage regression incident reports to validate, safe-guard, and improve policies prior to the online deployment.
Outcome:	The proposed method validates, safe-guards, and improves policies prior to the online deployment.

Copied to clipboard

Ye Lin, Xiaohui Wang, Zhexi Zhang, Mingxuan Wang, Tong Xiao, Jingbo Zhu

Multilinguality

Challenge:	Existing work on NMT models is limited in storage, memory, computation and power consumption.
Approach:	They propose a mobile machine translation system that can translate in 15MB and 30ms on devices.
Outcome:	The proposed system can translate in 15MB and 30ms on mobile devices.

Multi-doc Hybrid Summarization via Salient Representation Learning (2023.acl-industry)

Copied to clipboard

Min Xiao

Summarization

Challenge:	Multi-document summarization is gaining more and more attention . extractive multi-doc approaches intend to directly extract key facts from multiple sources .
Approach:	They propose a multi-document hybrid summarization approach that generates a human-readable summary and extracts corresponding key evidences based on multi-doc inputs.
Outcome:	The proposed method generates a human-readable summary and extracts key evidences based on multi-doc inputs.

SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy Labels (2023.acl-industry)

Copied to clipboard

Zhenting Qi, Xiaoyu Tan, Chao Qu, Yinghui Xu, Yuan Qi

Responsible & Trustworthy NLP

Challenge:	Existing noise-handling methods could not improve performance of BERT on noisy datasets . existing methods could only improve performance on noisy data, authors say .
Approach:	They propose a fine-tuning framework for BERT-based text classifiers that combats label noises without access to clean data for training or validation.
Outcome:	The proposed framework achieves superior performance on multiple text classification benchmarks.

Chemical Language Understanding Benchmark (2023.acl-industry)

Copied to clipboard

Yunsoo Kim, Hyuk Ko, Jane Lee, Hyun Young Heo, Jinyoung Yang, Sungsoo Lee, Kyu-hwang Lee

HyperT5: Towards Compute-Efficient Korean Language Modeling (2023.acl-industry)

Challenge:	CLUB datasets are used to facilitate NLP research in the chemical industry.
Approach:	They introduce a benchmark dataset called CLUB to facilitate NLP research in the chemical industry.
Outcome:	The CLUB datasets are a new benchmark dataset for NLP in the chemical industry.

Copied to clipboard

Dongju Park, Soonwon Ka, Kang Min Yoo, Gichang Lee, Jaewook Kang

Semantic Ambiguity Detection in Sentence Classification using Task-Specific Embeddings (2023.acl-industry)

Challenge:	Pretraining and fine-tuning language models is a common practice in NLP, but deploying general-purpose language models without the abundant computation or data resources is proving difficult.
Approach:	They propose a sequence-to-sequence language model architecture that can be more practical and compute-efficient than the decoder-oriented approach.
Outcome:	The proposed language model outperforms competing models in Korean benchmarks and is more efficient in low-resource settings.

Copied to clipboard

Jong Myoung Kim, Young-jun Lee, Sangkeun Jung, Ho-jin Choi

Reliable and Interpretable Drift Detection in Streams of Short Texts (2023.acl-industry)

Challenge:	ambiguity is a major obstacle to providing services based on sentence classification . authors use similarity in a semantic space to detect ambiguities in training data and scenarios .
Approach:	They use similarity in a semantic space to detect ambiguities in service scenarios and training data.
Outcome:	The proposed approach can detect ambiguities and debug services.

Copied to clipboard

Ella Rabinovich, Matan Vetzler, Samuel Ackerman, Ateret Anaby Tavor

Sharing Encoder Representations across Languages, Domains and Tasks in Large-Scale Spoken Language Understanding (2023.acl-industry)

Challenge:	Data drift is a key factor leading to model performance degradation over time.
Approach:	They propose a framework for reliable model-agnostic change-point detection and interpretation in large task-oriented dialog systems.
Outcome:	The proposed framework is effective in multiple customer deployments.

Copied to clipboard

Jonathan Hueser, Judith Gaspers, Thomas Gueudre, Chandana Prakash, Jin Cao, Daniil Sorokin, Quynh Do, Nicolas Anastassacos, Tobias Falke, Turan Gojayev

Annotating Research Infrastructure in Scientific Papers: An NLP-driven Approach (2023.acl-industry)

Challenge:	Larger encoders can improve accuracy for spoken language understanding (SLU) but are difficult to use given the inference latency constraints of online systems.
Approach:	They propose to use a larger 170M parameter BERT encoder that shares representations across languages, domains and tasks for SLU.
Outcome:	The proposed encoders achieve state-of-the-art performance on numerous NLP tasks.

Copied to clipboard

Seyed Amin Tabatabaei, Georgios Cheirmpos, Marius Doornenbal, Alberto Zigoni, Veronique Moore, Georgios Tsatsaronis

Structured Data in NLP

Challenge:	a pipeline is used to identify, extract and link research infrastructure used in scientific publications.
Approach:	They propose a natural language processing pipeline for the identification, extraction and linking of Research Infrastructure (RI) used in scientific publications.
Outcome:	The proposed pipeline can be used to identify, extract and link research infrastructure used in scientific publications.

Event-Centric Query Expansion in Web Search (2023.acl-industry)

Copied to clipboard

Yanan Zhang, Weijie Cui, Yangfan Zhang, Xiaoling Bai, Zhe Zhang, Jin Ma, Xiang Chen, Tianhua Zhou

Transferable and Efficient: Unifying Dynamic Multi-Domain Product Categorization (2023.acl-industry)

Challenge:	Existing studies rely on long-term search log mining to improve search experience . EQE system is a novel event retrieval framework that can select the best expansion from a significant amount of potential events quickly and accurately.
Approach:	They propose a QE system that uses a four-stage event retrieval framework . they collect news headlines and then refine a dual-tower semantic model to serve as an encoder .
Outcome:	The proposed system can select the best expansion from a significant amount of potential events quickly and accurately.

Copied to clipboard

Shansan Gong, Zelin Zhou, Shuo Wang, Fengjiao Chen, Xiujie Song, Xuezhi Cao, Yunsen Xian, Kenny Zhu

DISCOSQA: A Knowledge Base Question Answering System for Space Debris based on Program Induction (2023.acl-industry)

Challenge:	e-commerce platforms are encountering increasingly complex product categorization scenarios . multiple business domains correspond to different category taxonomies, with different depths and distinct literal expressions of category names.
Approach:	They propose a taxonomy-agnostic framework that calculates semantic relatedness between product titles and category names in the vector space.
Outcome:	The proposed framework outperforms strong baselineson three dynamic multi-domain product categorization tasks.

Copied to clipboard

Paul Darm, Antonio Valerio Miceli Barone, Shay B. Cohen, Annalisa Riccardi

BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting (2023.acl-industry)

Challenge:	a system that can answer complex natural language queries is developed for the European Space Agency . space debris are uncontrolled artificial objects left in orbit during normal operations or due to malfunctions .
Approach:	They propose a query-based system that can answer queries in natural language . it generates a program sketch from a natural language question and executes it against the database .
Outcome:	The proposed system can answer queries in natural language based on a natural language question generated by a query program . the system reduces overfitting and shortcut learning even with limited training data, the authors say .

Copied to clipboard

Wei Zhu, Peng Wang, Yuan Ni, Guotong Xie, Xiaoling Wang

K-pop and fake facts: from texts to smart alerting for maritime security (2023.acl-industry)

Challenge:	Recent years have witnessed the rise of many pre-trained language models (PLMs) such as GPT (Radford et al., 2019) and XLNet (Yang e.t al, 2019).
Approach:	They propose a framework which consists of two off-the-shelf methods for improving PLMs’ early exiting.
Outcome:	The proposed method can reduce the average latency of pre-trained language models and work with other inference speed-up methods like model pruning.

Copied to clipboard

Maxime Prieur, Souhir Gahbiche, Guillaume Gadek, Sylvain Gatepaille, Kilian Vasnier, Valerian Justine

Knowledge Representation

Challenge:	Maritime security requires full-time monitoring of the situation based on technical data but also from OSINT-like inputs.
Approach:	They propose a system that extracts data from sensors and texts to feed a Knowledge Base . the system can be used to detect malicious actors using AIS and pseudo-newspapers .
Outcome:	The proposed system ingests data from sensors and texts and feeds a Knowledge Base . it performs coherence checks between extracted facts and the extracted data .

Evaluating Embedding APIs for Information Retrieval (2023.acl-industry)

Copied to clipboard

Ehsan Kamalloo, Xinyu Zhang, Odunayo Ogundepo, Nandan Thakur, David Alfonso-hermelo, Mehdi Rezagholizadeh, Jimmy Lin

Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform (2023.acl-industry)

Challenge:	a growing number of language models are limiting their access to the community . we evaluate existing APIs for domain generalization and multilingual retrieval .
Approach:	They evaluate semantic embedding APIs in retrieval scenarios to assess their capabilities . they use BEIR and MIRACL to re-rank BM25 results using the APIs .
Outcome:	The proposed model is based on semantic embedding APIs that build vector representations of a given text.

Copied to clipboard

Mateusz Wójcik, Witold Kościukiewicz, Mateusz Baran, Tomasz Kajdanowicz, Adam Gonczarek

Text Classification

Challenge:	Recent methods with stochastic gradient learning struggle in streaming data setups and are restricted to specific domains.
Approach:	They propose a fully differentiable architecture that enables the training of high-performance classifiers when examples from each class are presented separately.
Outcome:	The proposed architecture achieves SOTA results without a memory buffer and clearly outperforms the reference methods.

Regression-Free Model Updates for Spoken Language Understanding (2023.acl-industry)

Copied to clipboard

Andrea Caciolai, Verena Weber, Tobias Falke, Alessandro Pedrani, Davide Bernardi

Reducing cohort bias in natural language understanding systems with targeted self-training scheme (2023.acl-industry)

Challenge:	Recent work has proposed methods for minimizing regressions caused by model updates . focus is on spoken language understanding models, which are unexplored .
Approach:	They propose a focal distillation technique to reduce regressions in goal-oriented dialog systems . they also evaluate its effectiveness for key language understanding tasks .
Outcome:	The proposed technique outperforms naive supervised training in mislabeled data and label expansion settings.

Copied to clipboard

Dieu-thu Le, Gabriela Hernandez, Bei Chen, Melanie Bradford

Content Moderation for Evolving Policies using Binary Question Answering (2023.acl-industry)

Challenge:	In deep learning models, it is hard to capture all the variations of the language that different users can use.
Approach:	They propose a framework that uses four active learning strategies to identify important samples coming from new users and a self training phase where a teacher model is trained from the first phase to expand the training data with relevant cohort utterances.
Outcome:	The proposed framework reduces the bias related to new customers in a digital voice assistant system by using two phases: a fixing phase and a self training phase.

Copied to clipboard

Sankha Subhra Mullick, Mohan Bhambhani, Suhit Sinha, Akshat Mathur, Somya Gupta, Jidnya Shah

Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)

Challenge:	Social media platforms use content moderation to safeguard users from abuse, harassment, malicious attacks, spam, etc.
Approach:	They propose to model content moderation as a binary question answering problem where questions validate loosely coupled themes constituting a policy.
Outcome:	The proposed model improves recall at 95% precision on two proprietary datasets of social media posts and comments respectively annotated under curated Hate Speech and Commercial Spam policies.

Copied to clipboard

Tianqi Wang, Lei Chen, Xiaodan Zhu, Younghun Lee, Jing Gao

Towards Building a Robust Toxicity Predictor (2023.acl-industry)

Challenge:	Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision.
Approach:	They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible.
Outcome:	The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task.

Copied to clipboard

Dmitriy Bespalov, Sourav Bhabesh, Yi Xiang, Liutong Zhou, Yanjun Qi

Robustness in NLP

Challenge:	Recent studies have focused on robustness of toxicity language predictors, but this is problematic for real-world toxicity detection.
Approach:	They propose a novel adversarial attack that exploits greedy search strategies to fool toxic text classifiers.
Outcome:	The proposed attack can detect weaker toxicity language detectors even against unseen attacks.

AI Coach Assist: An Automated Approach for Call Recommendation in Contact Centers for Agent Coaching (2023.acl-industry)

Copied to clipboard

Md Tahmid Rahman Laskar, Cheng Chen, Xue-yong Fu, Mahsa Azizi, Shashi Bhushan, Simon Corston-oliver

Unified Contextual Query Rewriting (2023.acl-industry)

Challenge:	In recent years, the utilization of Artificial Intelligence (AI) in the contact center industry is on the rise.
Approach:	They present a transformer-based pairwise sentence classification model that analyzes call transcripts to determine which calls are most relevant for coaching purposes.
Outcome:	The proposed model can determine which calls are most relevant for coaching purposes based on quality assurance queries/questions asked by managers or supervisors .

Copied to clipboard

Yingxue Zhou, Jie Hao, Mukund Rungta, Yang Liu, Eunah Cho, Xing Fan, Yanbin Lu, Vishal Vasudevan, Kellen Gillespie, Zeynab Raeesy

Paraphrasing

Challenge:	Large-scale conversational AI agents such as Alexa, Siri, and Google Assistant are becoming increasingly popular in real-world applications to assist users in daily life.
Approach:	They propose a unified contextual query rewriting model that unifies QR for friction reduction and contextual carryover . they leverage the text-to-text unified framework which uses independent tasks with weighted loss to account for task importance .
Outcome:	The proposed model reduces friction and contextual carryover by using multiple auxiliary tasks.

Context-Aware Query Rewriting for Improving Users’ Search Experience on E-commerce Websites (2023.acl-industry)

Copied to clipboard

Simiao Zuo, Qingyu Yin, Haoming Jiang, Shaohui Xi, Bing Yin, Chao Zhang, Tuo Zhao

Text Generation

Challenge:	Existing query rewriting models ignore user history behaviors and consider only the instant search query, which is often a short string offering limited information about the true shopping intent.
Approach:	They propose an end-to-end context-aware query rewriting model that takes search context into account and builds a session graph using the history search queries and their contained words.
Outcome:	The proposed model outperforms state-of-the-art models under various metrics.

Federated Learning of Gboard Language Models with Differential Privacy (2023.acl-industry)

Copied to clipboard

Zheng Xu, Yanxiang Zhang, Galen Andrew, Christopher Choquette, Peter Kairouz, Brendan Mcmahan, Jesse Rosenstock, Yuanbo Zhang

RadLing: Towards Efficient Radiology Report Understanding (2023.acl-industry)

Challenge:	Using federated learning and differential privacy, we train and deploy language models with federation and DP in Google Keyboard.
Approach:	They train and deploy language models with federated learning and differential privacy in Google Keyboard .
Outcome:	The proposed algorithm achieves meaningfully formal DP guarantees without uniform sampling of clients.

Copied to clipboard

Rikhiya Ghosh, Oladimeji Farri, Sanjeev Kumar Karn, Manuela Danu, Ramya Vunikili, Larisa Micu

Predicting Customer Satisfaction with Soft Labels for Ordinal Classification (2023.acl-industry)

Challenge:	a few pre-trained language models have produced comparable results in fine-tuning tasks in radiology domain.
Approach:	They propose a continuously pretrained language model with ELECTRA-small architecture that can compete with state-of-the-art results in radiology domain.
Outcome:	The proposed model can compete with state-of-the-art models for fine tuning tasks in radiology domain.

Copied to clipboard

Etienne Manderscheid, Matthias Lee

Text Classification

Challenge:	a typical call center only responds to 8% of customers with a customer satisfaction survey . a predictive algorithm that infers CSAT on the 1-5 scale is needed to minimize this data sparsity and response bias.
Approach:	They propose an algorithm that infers CSAT on 1-5 scale on inbound calls to the call center . they reframe the problem into a binary class and map it back to five classes .
Outcome:	The proposed model is able to support keycustomer workflows with high accuracy overmillions of calls a month.

Accurate Training of Web-based Question Answering Systems with Feedback from Ranked Users (2023.acl-industry)

Copied to clipboard

Liang Wang, Ivano Lauriola, Alessandro Moschitti

SPM: A Split-Parsing Method for Joint Multi-Intent Detection and Slot Filling (2023.acl-industry)

Challenge:	Recent work shows that large-scale annotated datasets are essential for training state-of-the-art Question Answering (QA) models.
Approach:	They use large-scale annotated datasets to train question answering models . they use feedback data collected from deployed QA systems to provide cheaper supervision .
Outcome:	The proposed model improves on the large scale annotated datasets from QA systems . the proposed model can be easily supervised on large-scale unlabeled web data .

Copied to clipboard

Sheng Jiang, Su Zhu, Ruisheng Cao, Qingliang Miao, Kai Yu

Semantic Parsing

Challenge:	Existing studies focus on utterances with a single intent, but lack the ability to assign slots to each corresponding intent.
Approach:	They propose a split-parsing method for joint intent detection and slot filling . they split an input sentence into multiple sub-sentences which contain a single-intent .
Outcome:	The proposed method improves on three multi-intent datasets on multi-tasks.

NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER Tasks (2023.acl-industry)

Copied to clipboard

Xinpeng Zhang, Ming Tan, Jingfan Zhang, Wei Zhu

Search Query Spell Correction with Weak Supervision in E-commerce (2023.acl-industry)

Challenge:	Existing models for general NER tasks require entities to be generated in a predefined order, causing error propagation and inefficient decoding.
Approach:	They propose a non-autoregressive generation framework for general NER tasks that generates entities as a set instead of a sequence, avoiding error propagation and inefficient decoding.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark NER datasets and two of our proprietary NER tasks.

Copied to clipboard

Vishal Kakkar, Chinmay Sharma, Madhura Pande, Surender Kumar

“Let’s not Quote out of Context”: Unified Vision-Language Pretraining for Context Assisted Image Captioning (2023.acl-industry)

Challenge:	Misspelled search queries can lead to empty or irrelevant products . only 29% of the population in india is proficient in english .
Approach:	They propose to group spell errors into error classes and then leverage a Transformer model for contextual spell correction.
Outcome:	The proposed model improves on tough spell mistakes without human intervention without human input.

Copied to clipboard

Abisek Rajakumar Kalarani, Pushpak Bhattacharyya, Niyati Chhaya, Sumit Shekhar

Visual Data in NLP

Challenge:	Large enterprises have several teams to create their content for the purpose of marketing, campaigning, or even maintaining a brand presence.
Approach:	They propose a new unified Vision-Language (VL) model with a focus on context-assisted image captioning where the caption is generated based on both the image and its context.
Outcome:	The proposed model achieves state-of-the-art with an improvement of up to 8.34 CIDEr score on the benchmark news image captioning datasets.

What, When, and How to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue (2023.acl-industry)

Copied to clipboard

Deuksin Kwon, Sunwoo Lee, Ki Hyun Kim, Seojin Lee, Taeyoon Kim, Eric Davis

CUPID: Curriculum Learning Based Real-Time Prediction using Distillation (2023.acl-industry)

Challenge:	a personalized dialogue system can generate user-customized responses based on long-term memory about the user's persona.
Approach:	They propose a method for building a personalized open-domain dialogue system . they combine weighted dataset blending and negative persona information augmentation methods .
Outcome:	The proposed method balances dialogue fluency and tendency to ground while introducing a response-type label to improve controllability and explainability of the grounded responses.

Copied to clipboard

Arindam Bhattacharya, Ankith Ms, Ankit Gandhi, Vijay Huddar, Atul Saroop, Rahul Bhagat

Answering Unanswered Questions through Semantic Reformulations in Spoken QA (2023.acl-industry)

Challenge:	Relevance in E-commerce Product Search is crucial for providing customers with accurate results that match their query intent.
Approach:	They propose a curriculum learning based real-time relevance prediction using distillation . they propose e-commerce search systems that use transformers to predict relevance .
Outcome:	The proposed model improves on english and Arabic in a bi-lingual relevance prediction task while maintaining low evaluation latency on CPUs.

Copied to clipboard

Pedro Faustini, Zhiyu Chen, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi

Exploring Zero and Few-shot Techniques for Intent Classification (2023.acl-industry)

Challenge:	Question Answering (QA) is a longstanding NLP task, and voice assistants like Alexa have made Spoken QA ubiquitous.
Approach:	They propose a model that uses linguistically-grounded operations to rewrite questions to facilitate answering.
Outcome:	The proposed model improves answer rates on 1M unanswered questions from a leading voice assistant.

Copied to clipboard

Soham Parikh, Mitul Tiwari, Prashil Tumbade, Quaizar Vohra

Responsible & Trustworthy NLP

Challenge:	Intent classification is the primary natural language understanding task for a virtual agent or a chatbot.
Approach:	They propose four different approaches to zero-shot intent classification with low-resource constraints . they use domain adaptation, data augmentation, and parametric fine-tuning to achieve this .
Outcome:	The proposed approaches perform well in low-resource settings for zero/few-shot intent classification . the proposed methods remove or substantially reduce the work to provide intent-utterances .

Referring to Screen Texts with Voice Assistants (2023.acl-industry)

Copied to clipboard

Shruti Bhargava, Anand Dhoot, Ing-marie Jonsson, Hoang Long Nguyen, Alkesh Patel, Hong Yu, Vincent Renkens

Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product Search (2023.acl-industry)

Challenge:	a new approach to voice assistants is limited in their ability to understand context of the user.
Approach:	They propose a general purpose model that allows users to refer to phone numbers, addresses, email addresses, urls, and dates on their phone screens.
Outcome:	The proposed model is lightweight, offering flexibility, better interpretability and efficient run time memory.

Copied to clipboard

Zhiyu Chen, Jason Choi, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi

KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models (2023.acl-industry)

Challenge:	Frequently Asked Question (FAQ) retrieval aims at retrieving question-answer pairs for a given user query.
Approach:	They propose to use an intent classifier to predict whether a query is looking for an FAQ and a reformulation model to rewrite the query into a natural question to improve retrieval performance.
Outcome:	The proposed method improves 12% on Hit@1 on retrieving ground-truth FAQs while reducing latency by 95% compared to baseline systems.

Copied to clipboard

Zhiwei Jia, Pradyumna Narayana, Arjun Akula, Garima Pruthi, Hao Su, Sugato Basu, Varun Jampani

Weakly supervised hierarchical multi-task classification of customer questions (2023.acl-industry)

Challenge:	Image ad understanding is a crucial task with wide real-world applications, but is under-explored in the machine learning community due to the lack of foundational vision-language models (VLMs) .
Approach:	They propose a simple feature adaptation strategy to fuse multimodal information for image ads and further empower it with knowledge of real-world entities.
Outcome:	The proposed strategy fuses multimodal information for image ads and empowers it with knowledge of real-world entities.

Copied to clipboard

Jitenkumar Rana, Promod Yenigalla, Chetan Aggarwal, Sandeep Sricharan Mukku, Manan Soni, Rashmi Patange

Low-Resource NLP

Challenge:	Identifying granular and actionable topics from customer questions helps improve the overall customer experience.
Approach:	They propose a weakly supervised Hierarchical Multi-task Classification Framework to identify granular topics from customer questions . a clustering based taxonomy creation and data labeling module is used to create taxonomies and labelled data with minimal supervision.
Outcome:	The proposed model achieves 13% better accuracy over single-task classification frameworks . it can adapt to constantly evolving taxonomy without need of re-training .

Automated Digitization of Unstructured Medical Prescriptions (2023.acl-industry)

Copied to clipboard

Megha Sharma, Tushar Vatsal, Srujana Merugu, Aruna Rajan