Shervin Malmasi

Sudipta Kar, Giuseppe Castellucci, Simone Filice et al. · amazon-science

Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires having the training data for all tasks available at the same time. As systems usually evolve over time, (e.g., to support new functionalities), adding a new task to an existing MTL model usually requires retraining the model from scratch on all the tasks and this can be time-consuming and computationally expensive. Moreover, in some scenarios, the data used to train the original training may be no longer available, for example, due to storage or privacy concerns. In this paper, we approach the problem of incrementally expanding MTL models' capability to solve new tasks over time by distilling the knowledge of an already trained model on n tasks into a new one for solving n+1 tasks. To avoid catastrophic forgetting, we propose to exploit unlabeled data from the same distributions of the old tasks. Our experiments on publicly available benchmarks show that such a technique dramatically benefits the distillation by preserving the already acquired knowledge (i.e., preventing up to 20% performance drops on old tasks) while obtaining good performance on the incrementally added tasks. Further, we also show that our approach is beneficial in practical settings by using data from a leading voice assistant.

Zhiyu Chen, Jason Choi, Besnik Fetahu et al. · amazon-science

Customers interacting with product search engines are increasingly formulating information-seeking queries. Frequently Asked Question (FAQ) retrieval aims to retrieve common question-answer pairs for a user query with question intent. Integrating FAQ retrieval in product search can not only empower users to make more informed purchase decisions, but also enhance user retention through efficient post-purchase support. Determining when an FAQ entry can satisfy a user's information need within product search, without disrupting their shopping experience, represents an important challenge. We propose an intent-aware FAQ retrieval system consisting of (1) an intent classifier that predicts when a user's information need can be answered by an FAQ; (2) a reformulation model that rewrites a query into a natural question. Offline evaluation demonstrates that our approach improves Hit@1 by 13% on retrieving ground-truth FAQs, while reducing latency by 95% compared to baseline systems. These improvements are further validated by real user feedback, where 71% of displayed FAQs on top of product search results received explicit positive user feedback. Overall, our findings show promising directions for integrating FAQ retrieval into product search at scale.

Shervin Malmasi, Anjie Fang, Besnik Fetahu et al.

We present MultiCoNER, a large multilingual dataset for Named Entity Recognition that covers 3 domains (Wiki sentences, questions, and search queries) across 11 languages, as well as multilingual and code-mixing subsets. This dataset is designed to represent contemporary challenges in NER, including low-context scenarios (short and uncased text), syntactically complex entities like movie titles, and long-tail entity distributions. The 26M token dataset is compiled from public resources using techniques such as heuristic-based sentence sampling, template extraction and slotting, and machine translation. We applied two NER models on our dataset: a baseline XLM-RoBERTa model, and a state-of-the-art GEMNET model that leverages gazetteers. The baseline achieves moderate performance (macro-F1=54%), highlighting the difficulty of our data. GEMNET, which uses gazetteers, improvement significantly (average improvement of macro-F1=+30%). MultiCoNER poses challenges even for large pre-trained language models, and we believe that it can help further research in building robust NER systems. MultiCoNER is publicly available at https://registry.opendata.aws/multiconer/ and we hope that this resource will help advance research in various aspects of NER.

Besnik Fetahu, Pedro Faustini, Giuseppe Castellucci et al. · amazon-science

The adoption of voice assistants like Alexa or Siri has grown rapidly, allowing users to instantly access information via voice search. Query suggestion is a standard feature of screen-based search experiences, allowing users to explore additional topics. However, this is not trivial to implement in voice-based settings. To enable this, we tackle the novel task of suggesting questions with compact and natural voice hints to allow users to ask follow-up questions. We define the task, ground it in syntactic theory and outline linguistic desiderata for spoken hints. We propose baselines and an approach using sequence-to-sequence Transformers to generate spoken hints from a list of questions. Using a new dataset of 6681 input questions and human written hints, we evaluated the models with automatic metrics and human evaluation. Results show that a naive approach of concatenating suggested questions creates poor voice hints. Our approach, which applies a linguistically-motivated pretraining task was strongly preferred by humans for producing the most natural hints.

Zhiyu Chen, Jie Zhao, Anjie Fang et al.

Conversational Question Answering (CQA) aims to answer questions contained within dialogues, which are not easily interpretable without context. Developing a model to rewrite conversational questions into self-contained ones is an emerging solution in industry settings as it allows using existing single-turn QA systems to avoid training a CQA model from scratch. Previous work trains rewriting models using human rewrites as supervision. However, such objectives are disconnected with QA models and therefore more human-like rewrites do not guarantee better QA performance. In this paper we propose using QA feedback to supervise the rewriting model with reinforcement learning. Experiments show that our approach can effectively improve QA performance over baselines for both extractive and retrieval QA. Furthermore, human evaluation shows that our method can generate more accurate and detailed rewrites when compared to human annotations.

Besnik Fetahu, Zhiyu Chen, Sudipta Kar et al.

We present MULTICONER V2, a dataset for fine-grained Named Entity Recognition covering 33 entity classes across 12 languages, in both monolingual and multilingual settings. This dataset aims to tackle the following practical challenges in NER: (i) effective handling of fine-grained classes that include complex entities like movie titles, and (ii) performance degradation due to noise generated from typing mistakes or OCR errors. The dataset is compiled from open resources like Wikipedia and Wikidata, and is publicly available. Evaluation based on the XLM-RoBERTa baseline highlights the unique challenges posed by MULTICONER V2: (i) the fine-grained taxonomy is challenging, where the scores are low with macro-F1=0.63 (across all languages), and (ii) the corruption strategy significantly impairs performance, with entity corruption resulting in 9% lower performance relative to non-entity corruptions across all languages. This highlights the greater impact of entity noise in contrast to context noise.

Besnik Fetahu, Zhiyu Chen, Oleg Rokhlenko et al.

E-commerce product catalogs contain billions of items. Most products have lengthy titles, as sellers pack them with product attributes to improve retrieval, and highlight key product aspects. This results in a gap between such unnatural products titles, and how customers refer to them. It also limits how e-commerce stores can use these seller-provided titles for recommendation, QA, or review summarization. Inspired by recent work on instruction-tuned LLMs, we present InstructPTS, a controllable approach for the task of Product Title Summarization (PTS). Trained using a novel instruction fine-tuning strategy, our approach is able to summarize product titles according to various criteria (e.g. number of words in a summary, inclusion of specific phrases, etc.). Extensive evaluation on a real-world e-commerce catalog shows that compared to simple fine-tuning of LLMs, our proposed approach can generate more accurate product name summaries, with an improvement of over 14 and 8 BLEU and ROUGE points, respectively.

Saar Kuzi, Shervin Malmasi

Consumers on a shopping mission often leverage both product search and information seeking systems, such as web search engines and Question Answering (QA) systems, in an iterative process to improve their understanding of available products and reach a purchase decision. While product search is useful for shoppers to find the actual products meeting their requirements in the catalog, information seeking systems can be utilized to answer any questions they may have to refine those requirements. The recent success of Large Language Models (LLMs) has opened up an opportunity to bridge the gap between the two tasks to help customers achieve their goals quickly and effectively by integrating conversational QA within product search. In this paper, we propose to recommend users Question-Answer (Q&A) pairs that are relevant to their product search and can help them make a purchase decision. We discuss the different aspects of the problem including the requirements and characteristics of the Q&A pairs, their generation, and the optimization of the Q&A recommendation task. We highlight the challenges, open problems, and suggested solutions to encourage future research in this emerging area.

Yilun Zhu, Yuan Zhuang, Nikhita Vedula et al.

Many applications of LLM-based text regression require predicting a full conditional distribution rather than a single point value. We study distributional regression under empirical-quantile supervision, where each input is paired with multiple observed quantile outcomes, and the target distribution is represented by a dense grid of quantiles. We address two key limitations of current approaches: the lack of local grounding for distribution estimates, and the reliance on shared representations that create an indirect bottleneck between inputs and quantile outputs. In this paper, we introduce Quantile Token Regression, which, to our knowledge, is the first work to insert dedicated quantile tokens into the input sequence, enabling direct input-output pathways for each quantile through self-attention. We further augment these quantile tokens with retrieval, incorporating semantically similar neighbor instances and their empirical distributions to ground predictions with local evidence from similar instances. We also provide the first theoretical analysis of loss functions for quantile regression, clarifying which distributional objectives each optimizes. Experiments on the Inside Airbnb and StackSample benchmark datasets with LLMs ranging from 1.7B to 14B parameters show that quantile tokens with neighbors consistently outperform baselines (~4 points lower MAPE and 2x narrower prediction intervals), with especially large gains on smaller and more challenging datasets where quantile tokens produce substantially sharper and more accurate distributions.

Kalle Kujanpää, Yuying Zhu, Kristina Klinkner et al.

We investigate machine learning approaches for optimizing real-time staffing decisions in semi-automated warehouse sortation systems. Operational decision-making can be supported at different levels of abstraction, with different trade-offs. We evaluate two approaches, each in a matching simulation environment. First, we train custom Transformer-based policies using offline reinforcement learning on detailed historical state representations, achieving a 2.4% throughput improvement over historical baselines in learned simulators. In high-volume warehouse operations, improvements of this size translate to significant savings. Second, we explore LLMs operating on abstracted, human-readable state descriptions. These are a natural fit for decisions that warehouse managers make using high-level operational summaries. We systematically compare prompting techniques, automatic prompt optimization, and fine-tuning strategies. While prompting alone proves insufficient, supervised fine-tuning combined with Direct Preference Optimization on simulator-generated preferences achieves performance that matches or slightly exceeds historical baselines in a hand-crafted simulator. Our findings demonstrate that both approaches offer viable paths toward AI-assisted operational decision-making. Offline RL excels with task-specific architectures. LLMs support human-readable inputs and can be combined with an iterative feedback loop that can incorporate manager preferences.

Shadi Sartipi, John Wu, Sina Ghotbi et al.

Detecting product price outliers is important for retail and e-commerce stores as erroneous or unexpectedly high prices adversely affect competitiveness, revenue, and consumer trust. Classical techniques offer simple thresholds while ignoring the rich semantic relationships among product attributes. We propose an agentic Large Language Model (LLM) framework that treats outlier price flagging as a reasoning task grounded in related product detection and comparison. The system processes the prices of target products in three stages: (i) relevance classification selects price-relevant similar products using product descriptions and attributes; (ii) relative utility assessment evaluates the target product against each similar product along price influencing dimensions (e.g., brand, size, features); (iii) reasoning-based decision aggregates these justifications into an explainable price outlier judgment. The framework attains over 75% agreement with human auditors on a test dataset, and outperforms zero-shot and retrieval based LLM techniques. Ablation studies show the sensitivity of the method to key hyper-parameters and testify on its flexibility to be applied to cases with different accuracy requirement and auditor agreements.

Zhuoer Wang, Marcus Collins, Nikhita Vedula et al.

Methods to generate text from structured data have advanced significantly in recent years, primarily due to fine-tuning of pre-trained language models on large datasets. However, such models can fail to produce output faithful to the input data, particularly on out-of-domain data. Sufficient annotated data is often not available for specific domains, leading us to seek an unsupervised approach to improve the faithfulness of output text. Since the problem is fundamentally one of consistency between the representations of the structured data and text, we evaluate the effectiveness of cycle training in this work. Cycle training uses two models which are inverses of each other: one that generates text from structured data, and one which generates the structured data from natural language text. We show that cycle training, when initialized with a small amount of supervised data (100 samples in our case), achieves nearly the same performance as fully supervised approaches for the data-to-text generation task on the WebNLG, E2E, WTQ, and WSQL datasets. We perform extensive empirical analysis with automated evaluation metrics and a newly designed human evaluation schema to reveal different cycle training strategies' effectiveness of reducing various types of generation errors. Our code is publicly available at https://github.com/Edillower/CycleNLG.

Ning Liu, Chuanneng Sun, Kristina Klinkner et al.

Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practical settings, training data consists of multiple rollouts per prompt, inducing rich preference structure that pairwise DPO fails to exploit. Collapsing such data into independent pairs discards transitivity, introduces redundant or conflicting supervision, and can lead to unstable optimization. We propose Graph Direct Preference Optimization (GraphDPO), a principled generalization of DPO that operates over directed acyclic preference graphs induced by rollout rankings. GraphDPO encodes dominance relations as edges and optimizes a graph-structured Plackett--Luce-inspired objective that aggregates supervision over graph neighborhoods, enforcing transitivity while recovering standard DPO as a special case. To handle discrete or sparse signals, we introduce an equivalence-class construction where responses with identical preferences form graph layers, and intra-layer edges contribute zero loss, preventing spurious gradients. Despite leveraging full graph structure, GraphDPO maintains linear per-prompt complexity via efficient log-sum-exp aggregation. We further incorporate optional ground-truth anchoring by inserting verified solutions as dominant nodes and applying an annealed schedule that stabilizes early training while gradually relaxing oracle supervision. Experiments on reasoning and program synthesis tasks demonstrate superior performance, suggesting that graph-structured preference modeling is a scalable and robust alternative to pairwise and listwise alignment objectives.

Yilun Zhu, Nikhita Vedula, Shervin Malmasi

Entity search, i.e., finding the most similar entities to a query entity, faces unique challenges in e-commerce, where product similarity varies across categories and contexts. Traditional embedding-based approaches often struggle to capture nuanced context-specific attribute relevance. In this paper, we present a two-stage approach combining Large Language Model (LLM)-driven attribute graph construction with graph-aware LLM ranking. In the offline stage, we extract structured product attributes from unstructured text, and construct a reusable attribute graph with category-aware schemas. In the online stage, we rank retrieved candidates by reasoning over this structured representation rather than raw text, reducing per-product token usage by 57% while improving ranking precision. Experiments show that our approach outperforms multiple baselines under zero-shot scenarios, achieving a over 5% improvement in average precision without requiring training data, generalizes robustly across diverse product categories, and shows immense potential for real-world deployment.

Theodore Glavas, Nikhita Vedula, Dushyanta Dhyani et al.

Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context. While standard autoregressive decoding is slow due to its sequential nature, the independence between output sequences offers an opportunity for parallelism. We present Hyper-Parallel Decoding, a novel decoding algorithm that accelerates offline decoding by leveraging both shared memory and computation across batches. HPD enables out-of-order token generation through position ID manipulation, significantly improving efficiency. Experiments on AVE show that attribute-value pairs are conditionally independent, enabling us to parallelize value generation within each prompt. By further stacking multiple documents within a single prompt, we can decode in parallel up to 96 tokens per prompt. HPD works with all LLMs, and reduces both inference costs and total inference time by up to 13.8X without compromising output quality, potentially saving hundreds of thousands of dollars on industry AVE tasks. Although designed for attribute extraction, HPD makes no assumptions unique to the AVE domain and can in theory be applied to other scenarios with independent output structures.

Parth Patwa, Simone Filice, Zhiyu Chen et al. · amazon-science

Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. In-Context Learning (ICL) typically achieves better accuracy than the 0-shot setting, but it pays in terms of efficiency, due to the longer input prompt. In this paper, we propose a strategy to make LLMs as efficient as 0-shot text classifiers, while getting comparable or better accuracy than ICL. Our solution targets the low resource setting, i.e., when only 4 examples per class are available. Using a single LLM and few-shot real data we perform a sequence of generation, filtering and Parameter-Efficient Fine-Tuning steps to create a robust and efficient classifier. Experimental results show that our approach leads to competitive results on multiple text classification datasets.

Nikhita Vedula, Oleg Rokhlenko, Shervin Malmasi

Digital assistants have become ubiquitous in e-commerce applications, following the recent advancements in Information Retrieval (IR), Natural Language Processing (NLP) and Generative Artificial Intelligence (AI). However, customers are often unsure or unaware of how to effectively converse with these assistants to meet their shopping needs. In this work, we emphasize the importance of providing customers a fast, easy to use, and natural way to interact with conversational shopping assistants. We propose a framework that employs Large Language Models (LLMs) to automatically generate contextual, useful, answerable, fluent and diverse questions about products, via in-context learning and supervised fine-tuning. Recommending these questions to customers as helpful suggestions or hints to both start and continue a conversation can result in a smoother and faster shopping experience with reduced conversation overhead and friction. We perform extensive offline evaluations, and discuss in detail about potential customer impact, and the type, length and latency of our generated product questions if incorporated into a real-world shopping assistant.

Xiangci Li, Zhiyu Chen, Jason Ingyu Choi et al.

The goal of conversational product search (CPS) is to develop an intelligent, chat-based shopping assistant that can directly interact with customers to understand shopping intents, ask clarification questions, and find relevant products. However, training such assistants is hindered mainly due to the lack of reliable and large-scale datasets. Prior human-annotated CPS datasets are extremely small in size and lack integration with real-world product search systems. We propose a novel approach, TRACER, which leverages large language models (LLMs) to generate realistic and natural conversations for different shopping domains. TRACER's novelty lies in grounding the generation to dialogue plans, which are product search trajectories predicted from a decision tree model, that guarantees relevant product discovery in the shortest number of search conditions. We also release the first target-oriented CPS dataset Wizard of Shopping (WoS), containing highly natural and coherent conversations (3.6k) from three shopping domains. Finally, we demonstrate the quality and effectiveness of WoS via human evaluations and downstream tasks.

Zhiyu Chen, Jason Choi, Besnik Fetahu et al.

In e-commerce, high consideration search missions typically require careful and elaborate decision making, and involve a substantial research investment from customers. We consider the task of identifying High Consideration (HC) queries. Identifying such queries enables e-commerce sites to better serve user needs using targeted experiences such as curated QA widgets that help users reach purchase decisions. We explore the task by proposing an Engagement-based Query Ranking (EQR) approach, focusing on query ranking to indicate potential engagement levels with query-related shopping knowledge content during product search. Unlike previous studies on predicting trends, EQR prioritizes query-level features related to customer behavior, finance, and catalog information rather than popularity signals. We introduce an accurate and scalable method for EQR and present experimental results demonstrating its effectiveness. Offline experiments show strong ranking performance. Human evaluation shows a precision of 96% for HC queries identified by our model. The model was commercially deployed, and shown to outperform human-selected queries in terms of downstream customer impact, as measured through engagement.

Kaustubh D. Dhole, Nikhita Vedula, Saar Kuzi et al. · amazon-science

In Recommender Systems, users often seek the best products through indirect, vague, or under-specified queries, such as "best shoes for trail running". Such queries, also referred to as implicit superlative queries, pose a significant challenge for standard retrieval and ranking systems as they lack an explicit mention of attributes and require identifying and reasoning over complex factors. We investigate how Large Language Models (LLMs) can generate implicit attributes for ranking as well as reason over them to improve product recommendations for such queries. As a first step, we propose a novel four-point schema for annotating the best product candidates for superlative queries called SUPERB, paired with LLM-based product annotations. We then empirically evaluate several existing retrieval and ranking approaches on our new dataset, providing insights and discussing their integration into real-world e-commerce production systems.

Yilun Zhu, Nikhita Vedula, Shervin Malmasi

Search queries with superlatives (e.g., best, most popular) require comparing candidates across multiple dimensions, demanding linguistic understanding and domain knowledge. We show that LLMs can uncover latent intent behind these expressions in e-commerce queries through a framework that extracts structured interpretations or hints. Our approach decomposes queries into attribute-value hints generated concurrently with retrieval, enabling efficient integration into the ranking pipeline. Our method improves search performanc eby 10.9 points in MAP and ranking by 5.9 points in MRR over baselines. Since direct LLM-based reranking faces prohibitive latency, we develop an efficient approach transferring superlative interpretations to lightweight models. Our findings provide insights into how superlative semantics can be represented and transferred between models, advancing linguistic interpretation in retrieval systems while addressing practical deployment constraints.

Lütfi Kerem Senel, Besnik Fetahu, Davis Yoshida et al.

Recommender systems are widely used to suggest engaging content, and Large Language Models (LLMs) have given rise to generative recommenders. Such systems can directly generate items, including for open-set tasks like question suggestion. While the world knowledge of LLMs enable good recommendations, improving the generated content through user feedback is challenging as continuously fine-tuning LLMs is prohibitively expensive. We present a training-free approach for optimizing generative recommenders by connecting user feedback loops to LLM-based optimizers. We propose a generative explore-exploit method that can not only exploit generated items with known high engagement, but also actively explore and discover hidden population preferences to improve recommendation quality. We evaluate our approach on question generation in two domains (e-commerce and general knowledge), and model user feedback with Click Through Rate (CTR). Experiments show our LLM-based explore-exploit approach can iteratively improve recommendations, and consistently increase CTR. Ablation analysis shows that generative exploration is key to learning user preferences, avoiding the pitfalls of greedy exploit-only approaches. A human evaluation strongly supports our quantitative findings.

Nikhita Vedula, Giuseppe Castellucci, Eugene Agichtein et al. · amazon-science

Conversational Task Assistants (CTAs) guide users in performing a multitude of activities, such as making recipes. However, ensuring that interactions remain engaging, interesting, and enjoyable for CTA users is not trivial, especially for time-consuming or challenging tasks. Grounded in psychological theories of human interest, we propose to engage users with contextual and interesting statements or facts during interactions with a multi-modal CTA, to reduce fatigue and task abandonment before a task is complete. To operationalize this idea, we train a high-performing classifier (82% F1-score) to automatically identify relevant and interesting facts for users. We use it to create an annotated dataset of task-specific interesting facts for the domain of cooking. Finally, we design and validate a dialogue policy to incorporate the identified relevant and interesting facts into a conversation, to improve user engagement and task completion. Live testing on a leading multi-modal voice assistant shows that 66% of the presented facts were received positively, leading to a 40% gain in the user satisfaction rating, and a 37% increase in conversation length. These findings emphasize that strategically incorporating interesting facts into the CTA experience can promote real-world user participation for guided task interactions.

Besnik Fetahu, Nachshon Cohen, Elad Haramaty et al.

Voice assistants have become ubiquitous in smart devices allowing users to instantly access information via voice questions. While extensive research has been conducted in question answering for voice search, little attention has been paid on how to enable proactive recommendations from a voice assistant to its users. This is a highly challenging problem that often leads to user friction, mainly due to recommendations provided to the users at the wrong time. We focus on the domain of e-commerce, namely in identifying Shopping Product Questions (SPQs), where the user asking a product-related question may have an underlying shopping need. Identifying a user's shopping need allows voice assistants to enhance shopping experience by determining when to provide recommendations, such as product or deal recommendations, or proactive shopping actions recommendation. Identifying SPQs is a challenging problem and cannot be done from question text alone, and thus requires to infer latent user behavior patterns inferred from user's past shopping history. We propose features that capture the user's latent shopping behavior from their purchase history, and combine them using a novel Mixture-of-Experts (MoE) model. Our evaluation shows that the proposed approach is able to identify SPQs with a high score of F1=0.91. Furthermore, based on an online evaluation with real voice assistant users, we identify SPQs in real-time and recommend shopping actions to users to add the queried product into their shopping list. We demonstrate that we are able to accurately identify SPQs, as indicated by the significantly higher rate of added products to users' shopping lists when being prompted after SPQs vs random PQs.

Besnik Fetahu, Tejas Mehta, Qun Song et al.

E-commerce customers frequently seek detailed product information for purchase decisions, commonly contacting sellers directly with extended queries. This manual response requirement imposes additional costs and disrupts buyer's shopping experience with response time fluctuations ranging from hours to days. We seek to automate buyer inquiries to sellers in a leading e-commerce store using a domain-specific federated Question Answering (QA) system. The main challenge is adapting current QA systems, designed for single questions, to address detailed customer queries. We address this with a low-latency, sequence-to-sequence approach, MESSAGE-TO-QUESTION ( M2Q ). It reformulates buyer messages into succinct questions by identifying and extracting the most salient information from a message. Evaluation against baselines shows that M2Q yields relative increases of 757% in question understanding, and 1,746% in answering rate from the federated QA system. Live deployment shows that automatic answering saves sellers from manually responding to millions of messages per year, and also accelerates customer purchase decisions by eliminating the need for buyers to wait for a reply

Lingbo Mo, Besnik Fetahu, Oleg Rokhlenko et al.

Yes/No or polar questions represent one of the main linguistic question categories. They consist of a main interrogative clause, for which the answer is binary (assertion or negation). Polar questions and answers (PQA) represent a valuable knowledge resource present in many community and other curated QA sources, such as forums or e-commerce applications. Using answers to polar questions alone in other contexts is not trivial. Answers are contextualized, and presume that the interrogative question clause and any shared knowledge between the asker and answerer are provided. We address the problem of controllable rewriting of answers to polar questions into decontextualized and succinct factual statements. We propose a Transformer sequence to sequence model that utilizes soft-constraints to ensure controllable rewriting, such that the output statement is semantically equivalent to its PQA input. Evaluation on three separate PQA datasets as measured through automated and human evaluation metrics show that our proposed approach achieves the best performance when compared to existing baselines.

Pedro Faustini, Zhiyu Chen, Besnik Fetahu et al.

Spoken Question Answering (QA) is a key feature of voice assistants, usually backed by multiple QA systems. Users ask questions via spontaneous speech which can contain disfluencies, errors, and informal syntax or phrasing. This is a major challenge in QA, causing unanswered questions or irrelevant answers, and leading to bad user experiences. We analyze failed QA requests to identify core challenges: lexical gaps, proposition types, complex syntactic structure, and high specificity. We propose a Semantic Question Reformulation (SURF) model offering three linguistically-grounded operations (repair, syntactic reshaping, generalization) to rewrite questions to facilitate answering. Offline evaluation on 1M unanswered questions from a leading voice assistant shows that SURF significantly improves answer rates: up to 24% of previously unanswered questions obtain relevant answers (75%). Live deployment shows positive impact for millions of customers with unanswered questions; explicit relevance feedback shows high user satisfaction.

Besnik Fetahu, Sudipta Kar, Zhiyu Chen et al.

We present the findings of SemEval-2023 Task 2 on Fine-grained Multilingual Named Entity Recognition (MultiCoNER 2). Divided into 13 tracks, the task focused on methods to identify complex fine-grained named entities (like WRITTENWORK, VEHICLE, MUSICALGRP) across 12 languages, in both monolingual and multilingual scenarios, as well as noisy settings. The task used the MultiCoNER V2 dataset, composed of 2.2 million instances in Bangla, Chinese, English, Farsi, French, German, Hindi, Italian., Portuguese, Spanish, Swedish, and Ukrainian. MultiCoNER 2 was one of the most popular tasks of SemEval-2023. It attracted 842 submissions from 47 teams, and 34 teams submitted system papers. Results showed that complex entity types such as media titles and product names were the most challenging. Methods fusing external knowledge into transformer models achieved the best performance, and the largest gains were on the Creative Work and Group classes, which are still challenging even with external knowledge. Some fine-grained classes proved to be more challenging than others, such as SCIENTIST, ARTWORK, and PRIVATECORP. We also observed that noisy data has a significant impact on model performance, with an average drop of 10% on the noisy subset. The task highlights the need for future research on improving NER robustness on noisy data containing complex entities.

Gustavo Henrique Paetzold, Shervin Malmasi, Marcos Zampieri

In this paper we revisit the problem of automatically identifying hate speech in posts from social media. We approach the task using a system based on minimalistic compositional Recurrent Neural Networks (RNN). We tested our approach on the SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter (HatEval) shared task dataset. The dataset made available by the HatEval organizers contained English and Spanish posts retrieved from Twitter annotated with respect to the presence of hateful content and its target. In this paper we present the results obtained by our system in comparison to the other entries in the shared task. Our system achieved competitive performance ranking 7th in sub-task A out of 62 systems in the English track.

Marcos Zampieri, Shervin Malmasi, Preslav Nakov et al.

We present the results and the main findings of SemEval-2019 Task 6 on Identifying and Categorizing Offensive Language in Social Media (OffensEval). The task was based on a new dataset, the Offensive Language Identification Dataset (OLID), which contains over 14,000 English tweets. It featured three sub-tasks. In sub-task A, the goal was to discriminate between offensive and non-offensive posts. In sub-task B, the focus was on the type of offensive content in the post. Finally, in sub-task C, systems had to detect the target of the offensive posts. OffensEval attracted a large number of participants and it was one of the most popular tasks in SemEval-2019. In total, about 800 teams signed up to participate in the task, and 115 of them submitted results, which we present and analyze in this report.

Marcos Zampieri, Shervin Malmasi, Preslav Nakov et al.

As offensive content has become pervasive in social media, there has been much research in identifying potentially offensive messages. However, previous work on this topic did not consider the problem as a whole, but rather focused on detecting very specific types of offensive content, e.g., hate speech, cyberbulling, or cyber-aggression. In contrast, here we target several different kinds of offensive content. In particular, we model the task hierarchically, identifying the type and the target of offensive messages in social media. For this purpose, we complied the Offensive Language Identification Dataset (OLID), a new dataset with tweets annotated for offensive content using a fine-grained three-layer annotation scheme, which we make publicly available. We discuss the main similarities and differences between OLID and pre-existing datasets for hate speech identification, aggression detection, and similar tasks. We further experiment with and we compare the performance of different machine learning models on OLID.

Fernando Benites, Shervin Malmasi, Marcos Zampieri

We present methods for the automatic classification of patent applications using an annotated dataset provided by the organizers of the ALTA 2018 shared task - Classifying Patent Applications. The goal of the task is to use computational methods to categorize patent applications according to a coarse-grained taxonomy of eight classes based on the International Patent Classification (IPC). We tested a variety of approaches for this task and the best results, 0.778 micro-averaged F1-Score, were achieved by SVM ensembles using a combination of words and characters as features. Our team, BMZ, was ranked first among 14 teams in the competition.

Liviu P. Dinu, Alina Maria Ciobanu, Marcos Zampieri et al.

In this paper we present ensemble-based systems for dialect and language variety identification using the datasets made available by the organizers of the VarDial Evaluation Campaign 2018. We present a system developed to discriminate between Flemish and Dutch in subtitles and a system trained to discriminate between four Arabic dialects: Egyptian, Levantine, Gulf, North African, and Modern Standard Arabic in speech broadcasts. Finally, we compare the performance of these two systems with the other systems submitted to the Discriminating between Dutch and Flemish in Subtitles (DFS) and the Arabic Dialect Identification (ADI) shared tasks at VarDial 2018.

Alina Maria Ciobanu, Shervin Malmasi, Liviu P. Dinu

In this paper we present the GDI_classification entry to the second German Dialect Identification (GDI) shared task organized within the scope of the VarDial Evaluation Campaign 2018. We present a system based on SVM classifier ensembles trained on characters and words. The system was trained on a collection of speech transcripts of five Swiss-German dialects provided by the organizers. The transcripts included in the dataset contained speakers from Basel, Bern, Lucerne, and Zurich. Our entry in the challenge reached 62.03% F1-score and was ranked third out of eight teams.

Alina Maria Ciobanu, Marcos Zampieri, Shervin Malmasi et al.

In this paper we present a system based on SVM ensembles trained on characters and words to discriminate between five similar languages of the Indo-Aryan family: Hindi, Braj Bhasha, Awadhi, Bhojpuri, and Magahi. We investigate the performance of individual features and combine the output of single classifiers to maximize performance. The system competed in the Indo-Aryan Language Identification (ILI) shared task organized within the VarDial Evaluation Campaign 2018. Our best entry in the competition, named ILIdentification, scored 88:95% F1 score and it was ranked 3rd out of 8 teams.

Iria del Río, Marcos Zampieri, Shervin Malmasi

In this paper we present NLI-PT, the first Portuguese dataset compiled for Native Language Identification (NLI), the task of identifying an author's first language based on their second language writing. The dataset includes 1,868 student essays written by learners of European Portuguese, native speakers of the following L1s: Chinese, English, Spanish, German, Russian, French, Japanese, Italian, Dutch, Tetum, Arabic, Polish, Korean, Romanian, and Swedish. NLI-PT includes the original student text and four different types of annotation: POS, fine-grained POS, constituency parses, and dependency parses. NLI-PT can be used not only in NLI but also in research on several topics in the field of Second Language Acquisition and educational NLP. We discuss possible applications of this dataset and present the results obtained for the first lexical baseline system for Portuguese NLI.

Seid Muhie Yimam, Chris Biemann, Shervin Malmasi et al.

We report the findings of the second Complex Word Identification (CWI) shared task organized as part of the BEA workshop co-located with NAACL-HLT'2018. The second CWI shared task featured multilingual and multi-genre datasets divided into four tracks: English monolingual, German monolingual, Spanish monolingual, and a multilingual track with a French test set, and two tasks: binary classification and probabilistic classification. A total of 12 teams submitted their results in different task/track combinations and 11 of them wrote system description papers that are referred to in this report and appear in the BEA workshop proceedings.

Shervin Malmasi, Marcos Zampieri

In this study we approach the problem of distinguishing general profanity from hate speech in social media, something which has not been widely considered. Using a new dataset annotated specifically for this task, we employ supervised classification along with a set of features that includes n-grams, skip-grams and clustering-based word representations. We apply approaches based on single classifiers as well as more advanced ensemble classifiers and stacked generalization, achieving the best result of 80% accuracy for this 3-class classification task. Analysis of the results reveals that discriminating hate speech and profanity is not a simple task, which may require features that capture a deeper understanding of the text not always possible with surface n-grams. The variability of gold labels in the annotated data, due to differences in the subjective adjudications of the annotators, is also an issue. Other directions for future work are discussed.

Shervin Malmasi, Marcos Zampieri

In this paper we examine methods to detect hate speech in social media, while distinguishing this from general profanity. We aim to establish lexical baselines for this task by applying supervised classification methods using a recently released dataset annotated for this purpose. As features, our system uses character n-grams, word n-grams and word skip-grams. We obtain results of 78% accuracy in identifying posts across three classes. Results demonstrate that the main challenge lies in discriminating profanity and hate speech from each other. A number of directions for future work are discussed.

Octavia-Maria Sulea, Marcos Zampieri, Shervin Malmasi et al.

In this paper, we investigate the application of text classification methods to support law professionals. We present several experiments applying machine learning techniques to predict with high accuracy the ruling of the French Supreme Court and the law area to which a case belongs to. We also investigate the influence of the time period in which a ruling was made on the form of the case description and the extent to which we need to mask information in a full case ruling to automatically obtain training and test data that resembles case descriptions. We developed a mean probability ensemble system combining the output of multiple SVM classifiers. We report results of 98% average F1 score in predicting a case ruling, 96% F1 score for predicting the law area of a case, and 87.07% F1 score on estimating the date of a ruling.

Marcos Zampieri, Shervin Malmasi, Gustavo Paetzold et al.

This paper revisits the problem of complex word identification (CWI) following up the SemEval CWI shared task. We use ensemble classifiers to investigate how well computational methods can discriminate between complex and non-complex words. Furthermore, we analyze the classification performance to understand what makes lexical complexity challenging. Our findings show that most systems performed poorly on the SemEval CWI dataset, and one of the reasons for that is the way in which human annotation was performed.

Shervin Malmasi

We present the first open-set language identification experiments using one-class classification. We first highlight the shortcomings of traditional feature extraction methods and propose a hashing-based feature vectorization approach as a solution. Using a dataset of 10 languages from different writing systems, we train a One- Class Support Vector Machine using only a monolingual corpus for each language. Each model is evaluated against a test set of data from all 10 languages and we achieve an average F-score of 0.99, highlighting the effectiveness of this approach for open-set language identification.

Alina Maria Ciobanu, Marcos Zampieri, Shervin Malmasi et al.

This paper presents a computational approach to author profiling taking gender and language variety into account. We apply an ensemble system with the output of multiple linear SVM classifiers trained on character and word $n$-grams. We evaluate the system using the dataset provided by the organizers of the 2017 PAN lab on author profiling. Our approach achieved 75% average accuracy on gender identification on tweets written in four languages and 97% accuracy on language variety identification for Portuguese.

Shervin Malmasi, Mark Dras

Ensemble methods using multiple classifiers have proven to be the most successful approach for the task of Native Language Identification (NLI), achieving the current state of the art. However, a systematic examination of ensemble methods for NLI has yet to be conducted. Additionally, deeper ensemble architectures such as classifier stacking have not been closely evaluated. We present a set of experiments using three ensemble-based models, testing each with multiple configurations and algorithms. This includes a rigorous application of meta-classification models for NLI, achieving state-of-the-art results on three datasets from different languages. We also present the first use of statistical significance testing for comparing NLI systems, showing that our results are significantly better than the previous state of the art. We make available a collection of test set predictions to facilitate future statistical tests.

Cyril Goutte, Serge Léger, Shervin Malmasi et al.

We present an analysis of the performance of machine learning classifiers on discriminating between similar languages and language varieties. We carried out a number of experiments using the results of the two editions of the Discriminating between Similar Languages (DSL) shared task. We investigate the progress made between the two tasks, estimate an upper bound on possible performance using ensemble and oracle combination, and provide learning curves to help us understand which languages are more challenging. A number of difficult sentences are identified and investigated further with human annotation.

Marcos Zampieri, Shervin Malmasi, Mark Dras

This paper presents a number of experiments to model changes in a historical Portuguese corpus composed of literary texts for the purpose of temporal text classification. Algorithms were trained to classify texts with respect to their publication date taking into account lexical variation represented as word n-grams, and morphosyntactic variation represented by part-of-speech (POS) distribution. We report results of 99.8% accuracy using word unigram features with a Support Vector Machines classifier to predict the publication date of documents in time intervals of both one century and half a century. A feature analysis is performed to investigate the most informative features for this task and how they are linked to language change.