João Magalhães

Diogo Tavares, Pedro Azevedo, David Semedo et al.

Dialogue systems need to deal with the unpredictability of user intents to track dialogue state and the heterogeneity of slots to understand user preferences. In this paper we investigate the hypothesis that solving these challenges as one unified model will allow the transfer of parameter support data across the different tasks. The proposed principled model is based on a Transformer encoder, trained on multiple tasks, and leveraged by a rich input that conditions the model on the target inferences. Conditioning the Transformer encoder on multiple target inferences over the same corpus, i.e., intent and multiple slot types, allows learning richer language interactions than a single-task model would be able to. In fact, experimental results demonstrate that conditioning the model on an increasing number of dialogue inference tasks leads to improved results: on the MultiWOZ dataset, the joint intent and slot detection can be improved by 3.2\% by conditioning on intent, 10.8\% by conditioning on slot and 14.4\% by conditioning on both intent and slots. Moreover, on real conversations with Farfetch costumers, the proposed conditioned BERT can achieve high joint-goal and intent detection performance throughout a dialogue.

Afonso Simplício, Gonçalo Vinagre, Miguel Moura Ramos et al.

Despite rapid progress in open large language models (LLMs), European Portuguese (pt-PT) remains underrepresented in both training data and native evaluation, with machine-translated benchmarks likely missing the variant's linguistic and cultural nuances. We introduce AMALIA, a fully open LLM that prioritizes pt-PT by using more high-quality pt-PT data during both the mid- and post-training stages. To evaluate pt-PT more faithfully, we release a suite of pt-PT benchmarks that includes translated standard tasks and four new datasets targeting pt-PT generation, linguistic competence, and pt-PT/pt-BR bias. Experiments show that AMALIA matches strong baselines on translated benchmarks while substantially improving performance on pt-PT-specific evaluations, supporting the case for targeted training and native benchmarking for European Portuguese.

Frederico Vicente, Rafael Ferreira, David Semedo et al.

Introducing curiosities in a conversation is a way to teach something new to the person in a pleasant and enjoyable way. Enriching dialogues with contextualized curiosities can improve the users' perception of a dialog system and their overall user experience. In this paper, we introduce a set of curated curiosities, targeting dialogues in the cooking and DIY domains. In particular, we use real human-agent conversations collected in the context of the Amazon Alexa TaskBot challenge, a multimodal and multi-turn conversational setting. According to an A/B test with over 1000 conversations, curiosities not only increase user engagement, but provide an average relative rating improvement of 9.7%.

Rafael Ferreira, David Semedo, João Magalhães

Predicting the success of Conversational Task Assistants (CTA) can be critical to understand user behavior and act accordingly. In this paper, we propose TB-Rater, a Transformer model which combines conversational-flow features with user behavior features for predicting user ratings in a CTA scenario. In particular, we use real human-agent conversations and ratings collected in the Alexa TaskBot challenge, a novel multimodal and multi-turn conversational context. Our results show the advantages of modeling both the conversational-flow and behavioral aspects of the conversation in a single model for offline rating prediction. Additionally, an analysis of the CTA-specific behavioral features brings insights into this setting and can be used to bootstrap future systems.

Diogo Glória-Silva, David Semedo, João Magalhães

Guiding users through complex procedural plans is an inherently multimodal task in which having visually illustrated plan steps is crucial to deliver an effective plan guidance. However, existing works on plan-following language models (LMs) often are not capable of multimodal input and output. In this work, we present MM-PlanLLM, the first multimodal LLM designed to assist users in executing instructional tasks by leveraging both textual plans and visual information. Specifically, we bring cross-modality through two key tasks: Conversational Video Moment Retrieval, where the model retrieves relevant step-video segments based on user queries, and Visually-Informed Step Generation, where the model generates the next step in a plan, conditioned on an image of the user's current progress. MM-PlanLLM is trained using a novel multitask-multistage approach, designed to gradually expose the model to multimodal instructional-plans semantic layers, achieving strong performance on both multimodal and textual dialogue in a plan-grounded setting. Furthermore, we show that the model delivers cross-modal temporal and plan-structure representations aligned between textual plan steps and instructional video moments.

Rafael Ferreira, Diogo Tavares, Diogo Silva et al.

In this report, we describe the vision, challenges, and scientific contributions of the Task Wizard team, TWIZ, in the Alexa Prize TaskBot Challenge 2022. Our vision, is to build TWIZ bot as an helpful, multimodal, knowledgeable, and engaging assistant that can guide users towards the successful completion of complex manual tasks. To achieve this, we focus our efforts on three main research questions: (1) Humanly-Shaped Conversations, by providing information in a knowledgeable way; (2) Multimodal Stimulus, making use of various modalities including voice, images, and videos; and (3) Zero-shot Conversational Flows, to improve the robustness of the interaction to unseen scenarios. TWIZ is an assistant capable of supporting a wide range of tasks, with several innovative features such as creative cooking, video navigation through voice, and the robust TWIZ-LLM, a Large Language Model trained for dialoguing about complex manual tasks. Given ratings and feedback provided by users, we observed that TWIZ bot is an effective and robust system, capable of guiding users through tasks while providing several multimodal stimuli.

Rafael Ferreira, David Semedo, João Magalhães

Following complex instructions in conversational assistants can be quite daunting due to the shorter attention and memory spans when compared to reading the same instructions. Hence, when conversational assistants walk users through the steps of complex tasks, there is a need to structure the task into manageable pieces of information of the right length and complexity. In this paper, we tackle the recipes domain and convert reading structured instructions into conversational structured ones. We annotated the structure of instructions according to a conversational scenario, which provided insights into what is expected in this setting. To computationally model the conversational step's characteristics, we tested various Transformer-based architectures, showing that a token-based approach delivers the best results. A further user study showed that users tend to favor steps of manageable complexity and length, and that the proposed methodology can improve the original web-based instructional text. Specifically, 86% of the evaluated tasks were improved from a conversational suitability point of view.

João Coelho, Bruno Martins, João Magalhães et al.

This study investigates the existence of positional biases in Transformer-based models for text representation learning, particularly in the context of web document retrieval. We build on previous research that demonstrated loss of information in the middle of input sequences for causal language models, extending it to the domain of representation learning. We examine positional biases at various stages of training for an encoder-decoder model, including language model pre-training, contrastive pre-training, and contrastive fine-tuning. Experiments with the MS-MARCO document collection reveal that after contrastive pre-training the model already generates embeddings that better capture early contents of the input, with fine-tuning further aggravating this effect.

Diogo Glória-Silva, Rafael Ferreira, Diogo Tavares et al.

Training Large Language Models (LLMs) to follow user instructions has been shown to supply the LLM with ample capacity to converse fluently while being aligned with humans. Yet, it is not completely clear how an LLM can lead a plan-grounded conversation in mixed-initiative settings where instructions flow in both directions of the conversation, i.e. both the LLM and the user provide instructions to one another. In this paper, we tackle a dual goal mixed-initiative conversational setting where the LLM not only grounds the conversation on an arbitrary plan but also seeks to satisfy both a procedural plan and user instructions. The LLM is then responsible for guiding the user through the plan and, at the same time, adapting to new circumstances, answering questions, and activating safety guardrails when needed. We propose a novel LLM that grounds the dialogue on a procedural plan, can take the dialogue initiative, and enforces guardrails on the system's behavior, while also improving the LLM's responses to unexpected user behavior. Experiments in controlled settings and with real users show that the best-performing model, which we call PlanLLM, achieves a 2.1x improvement over a strong baseline. Moreover, experiments also show good generalization to unseen domains.

João Daniel Silva, Joao Magalhaes, Devis Tuia et al.

Methods based on Contrastive Language-Image Pre-training (CLIP) are nowadays extensively used in support of vision-and-language tasks involving remote sensing data, such as cross-modal retrieval. The adaptation of CLIP to this specific domain has relied on model fine-tuning with the standard contrastive objective, using existing human-labeled image-caption datasets, or using synthetic data corresponding to image-caption pairs derived from other annotations over remote sensing images (e.g., object classes). The use of different pre-training mechanisms has received less attention, and only a few exceptions have considered multilingual inputs. This work proposes a novel vision-and-language model for the remote sensing domain, exploring the fine-tuning of a multilingual CLIP model and testing the use of a self-supervised method based on aligning local and global representations from individual input images, together with the standard CLIP objective. Model training relied on assembling pre-existing datasets of remote sensing images paired with English captions, followed by the use of automated machine translation into nine additional languages. We show that translated data is indeed helpful, e.g. improving performance also on English. Our resulting model, which we named Remote Sensing Multilingual CLIP (RS-M-CLIP), obtains state-of-the-art results in a variety of vision-and-language tasks, including cross-modal and multilingual image-text retrieval, or zero-shot image classification.

Rafael Ferreira, David Semedo, João Magalhães

Conversational systems must be robust to user interactions that naturally exhibit diverse conversational traits. Capturing and simulating these diverse traits coherently and efficiently presents a complex challenge. This paper introduces Multi-Trait Adaptive Decoding (mTAD), a method that generates diverse user profiles at decoding-time by sampling from various trait-specific Language Models (LMs). mTAD provides an adaptive and scalable approach to user simulation, enabling the creation of multiple user profiles without the need for additional fine-tuning. By analyzing real-world dialogues from the Conversational Task Assistant (CTA) domain, we identify key conversational traits and developed a framework to generate profile-aware dialogues that enhance conversational diversity. Experimental results validate the effectiveness of our approach in modeling single-traits using specialized LMs, which can capture less common patterns, even in out-of-domain tasks. Furthermore, the results demonstrate that mTAD is a robust and flexible framework for combining diverse user simulators.

Artur Horal, Daniel Pina, Henrique Paz et al.

This paper presents the vision, scientific contributions, and technical details of RedTWIZ: an adaptive and diverse multi-turn red teaming framework, to audit the robustness of Large Language Models (LLMs) in AI-assisted software development. Our work is driven by three major research streams: (1) robust and systematic assessment of LLM conversational jailbreaks; (2) a diverse generative multi-turn attack suite, supporting compositional, realistic and goal-oriented jailbreak conversational strategies; and (3) a hierarchical attack planner, which adaptively plans, serializes, and triggers attacks tailored to specific LLM's vulnerabilities. Together, these contributions form a unified framework -- combining assessment, attack generation, and strategic planning -- to comprehensively evaluate and expose weaknesses in LLMs' robustness. Extensive evaluation is conducted to systematically assess and analyze the performance of the overall system and each component. Experimental results demonstrate that our multi-turn adversarial attack strategies can successfully lead state-of-the-art LLMs to produce unsafe generations, highlighting the pressing need for more research into enhancing LLM's robustness.

Gonçalo Marcelino, David Semedo, André Mourão et al.

Creating a cohesive, high-quality, relevant, media story is a challenge that news media editors face on a daily basis. This challenge is aggravated by the flood of highly relevant information that is constantly pouring onto the newsroom. To assist news media editors in this daunting task, this paper proposes a framework to organize news content into cohesive, high-quality, relevant visual storylines. First, we formalize, in a nonsubjective manner, the concept of visual story transition. Leveraging it, we propose four graph-based methods of storyline creation, aiming for global story cohesiveness. These were created and implemented to take full advantage of existing graph algorithms, ensuring their correctness and good computational performance. They leverage a strong ensemble-based estimator which was trained to predict story transition quality based on both the semantic and visual features present in the pair of images under scrutiny. A user study covered a total of 28 curated stories about sports and cultural events. Experiments showed that (i) visual transitions in storylines can be learned with a quality above 90%, and (ii) the proposed graph methods can produce cohesive storylines with quality in the range of 88% to 96%.

Mariana Leite, Rafael Ferreira, David Semedo et al.

The conversational search paradigm introduces a step change over the traditional search paradigm by allowing users to interact with search agents in a multi-turn and natural fashion. The conversation flows naturally and is usually centered around a target field of knowledge. In this work, we propose a knowledge-driven answer generation approach for open-domain conversational search, where a conversation-wide entities' knowledge graph is used to bias search-answer generation. First, a conversation-specific knowledge graph is extracted from the top passages retrieved with a Transformer-based re-ranker. The entities knowledge-graph is then used to bias a search-answer generator Transformer towards information rich and concise answers. This conversation specific bias is computed by identifying the most relevant passages according to the most salient entities of that particular conversation. Experiments show that the proposed approach successfully exploits entities knowledge along the conversation, and outperforms a set of baselines on the search-answer generation task.

Rafael Ferreira, David Semedo, Joao Magalhaes

The use of conversational assistants to search for information is becoming increasingly more popular among the general public, pushing the research towards more advanced and sophisticated techniques. In the last few years, in particular, the interest in conversational search is increasing, not only because of the generalization of conversational assistants but also because conversational search is a step forward in allowing a more natural interaction with the system. In this work, the focus is on exploring the context present of the conversation via the historical utterances and respective embeddings with the aim of developing a conversational search system that helps people search for information in a natural way. In particular, this system must be able to understand the context where the question is posed, tracking the current state of the conversation and detecting mentions to previous questions and answers. We achieve this by using a context-tracking component based on neural query-rewriting models. Another crucial aspect of the system is to provide the most relevant answers given the question and the conversational history. To achieve this objective, we used a Transformer-based re-ranking method and expanded this architecture to use the conversational context. The results obtained with the system developed showed the advantages of using the context present in the natural language utterances and in the neural embeddings generated throughout the conversation.

Rafael Ferreira, Mariana Leite, David Semedo et al.

Open-domain conversational search assistants aim at answering user questions about open topics in a conversational manner. In this paper we show how the Transformer architecture achieves state-of-the-art results in key IR tasks, leveraging the creation of conversational assistants that engage in open-domain conversational search with single, yet informative, answers. In particular, we propose an open-domain abstractive conversational search agent pipeline to address two major challenges: first, conversation context-aware search and second, abstractive search-answers generation. To address the first challenge, the conversation context is modeled with a query rewriting method that unfolds the context of the conversation up to a specific moment to search for the correct answers. These answers are then passed to a Transformer-based re-ranker to further improve retrieval performance. The second challenge, is tackled with recent Abstractive Transformer architectures to generate a digest of the top most relevant passages. Experiments show that Transformers deliver a solid performance across all tasks in conversational search, outperforming the best TREC CAsT 2019 baseline.

Gonçalo Marcelino, David Semedo, André Mourão et al.

Media editors in the newsroom are constantly pressed to provide a "like-being there" coverage of live events. Social media provides a disorganised collection of images and videos that media professionals need to grasp before publishing their latest news updated. Automated news visual storyline editing with social media content can be very challenging, as it not only entails the task of finding the right content but also making sure that news content evolves coherently over time. To tackle these issues, this paper proposes a benchmark for assessing social media visual storylines. The SocialStories benchmark, comprised by total of 40 curated stories covering sports and cultural events, provides the experimental setup and introduces novel quantitative metrics to perform a rigorous evaluation of visual storytelling with social media data.

Flávio Martins, João Magalhães, Jamie Callan

Newsworthy events are broadcast through multiple mediums and prompt the crowds to produce comments on social media. In this paper, we propose to leverage on this behavioral dynamics to estimate the most relevant time periods for an event (i.e., query). Recent advances have shown how to improve the estimation of the temporal relevance of such topics. In this approach, we build on two major novelties. First, we mine temporal evidences from hundreds of external sources into topic-based external collections to improve the robustness of the detection of relevant time periods. Second, we propose a formal retrieval model that generalizes the use of the temporal dimension across different aspects of the retrieval process. In particular, we show that temporal evidence of external collections can be used to (i) infer a topic's temporal relevance, (ii) select the query expansion terms, and (iii) re-rank the final results for improved precision. Experiments with TREC Microblog collections show that the proposed time-aware retrieval model makes an effective and extensive use of the temporal dimension to improve search results over the most recent temporal models. Interestingly, we observe a strong correlation between precision and the temporal distribution of retrieved and relevant documents.

David Semedo, João Magalhães

Multimedia information have strong temporal correlations that shape the way modalities co-occur over time. In this paper we study the dynamic nature of multimedia and social-media information, where the temporal dimension emerges as a strong source of evidence for learning the temporal correlations across visual and textual modalities. So far, cross-media retrieval models, explored the correlations between different modalities (e.g. text and image) to learn a common subspace, in which semantically similar instances lie in the same neighbourhood. Building on such knowledge, we propose a novel temporal cross-media neural architecture, that departs from standard cross-media methods, by explicitly accounting for the temporal dimension through temporal subspace learning. The model is softly-constrained with temporal and inter-modality constraints that guide the new subspace learning task by favouring temporal correlations between semantically similar and temporally close instances. Experiments on three distinct datasets show that accounting for time turns out to be important for cross-media retrieval. Namely, the proposed method outperforms a set of baselines on the task of temporal cross-media retrieval, demonstrating its effectiveness for performing temporal subspace learning.

David Semedo, João Magalhães, Flávio Martins

In this paper we address the task of gender classification on picture sharing social media networks such as Instagram and Flickr. We aim to infer the gender of an user given only a small set of the images shared in its profile. We make the assumption that user's images contain a collection of visual elements that implicitly encode discriminative patterns that allow inferring its gender, in a language independent way. This information can then be used in personalisation and recommendation. Our main hypothesis is that semantic visual features are more adequate for discriminating high-level classes. The gender detection task is formalised as: given an user's profile, represented as a bag of images, we want to infer the gender of the user. Social media profiles can be noisy and contain confounding factors, therefore we classify bags of user-profile's images to provide a more robust prediction. Experiments using a dataset from the picture sharing social network Instagram show that the use of multiple images is key to improve detection performance. Moreover, we verify that deep semantic features are more suited for gender detection than low-level image representations. The methods proposed can infer the gender with precision scores higher than 0.825, and the best performing method achieving 0.911 precision.

Gonçalo Marcelino, Ricardo Pinto, João Magalhães

News editors need to find the photos that best illustrate a news piece and fulfill news-media quality standards, while being pressed to also find the most recent photos of live events. Recently, it became common to use social-media content in the context of news media for its unique value in terms of immediacy and quality. Consequently, the amount of images to be considered and filtered through is now too much to be handled by a person. To aid the news editor in this process, we propose a framework designed to deliver high-quality, news-press type photos to the user. The framework, composed of two parts, is based on a ranking algorithm tuned to rank professional media highly and a visual SPAM detection module designed to filter-out low-quality media. The core ranking algorithm is leveraged by aesthetic, social and deep-learning semantic features. Evaluation showed that the proposed framework is effective at finding high-quality photos (true-positive rate) achieving a retrieval MAP of 64.5% and a classification precision of 70%.

Flávio Martins, João Magalhães, Jamie Callan

In microblog retrieval, query expansion can be essential to obtain good search results due to the short size of queries and posts. Since information in microblogs is highly dynamic, an up-to-date index coupled with pseudo-relevance feedback (PRF) with an external corpus has a higher chance of retrieving more relevant documents and improving ranking. In this paper, we focus on the research question:how can we reduce the query expansion computational cost while maintaining the same retrieval precision as standard PRF? Therefore, we propose to accelerate the query expansion step of pseudo-relevance feedback. The hypothesis is that using an expansion corpus organized into verticals for expanding the query, will lead to a more efficient query expansion process and improved retrieval effectiveness. Thus, the proposed query expansion method uses a distributed search architecture and resource selection algorithms to provide an efficient query expansion process. Experiments on the TREC Microblog datasets show that the proposed approach can match or outperform standard PRF in MAP and NDCG@30, with a computational cost that is three orders of magnitude lower.

Flávio Martins, João Magalhães, Jamie Callan

In Twitter, and other microblogging services, the generation of new content by the crowd is often biased towards immediacy: what is happening now. Prompted by the propagation of commentary and information through multiple mediums, users on the Web interact with and produce new posts about newsworthy topics and give rise to trending topics. This paper proposes to leverage on the behavioral dynamics of users to estimate the most relevant time periods for a topic. Our hypothesis stems from the fact that when a real-world event occurs it usually has peak times on the Web: a higher volume of tweets, new visits and edits to related Wikipedia articles, and news published about the event. In this paper, we propose a novel time-aware ranking model that leverages on multiple sources of crowd signals. Our approach builds on two major novelties. First, a unifying approach that given query q, mines and represents temporal evidence from multiple sources of crowd signals. This allows us to predict the temporal relevance of documents for query q. Second, a principled retrieval model that integrates temporal signals in a learning to rank framework, to rank results according to the predicted temporal relevance. Evaluation on the TREC 2013 and 2014 Microblog track datasets demonstrates that the proposed model achieves a relative improvement of 13.2% over lexical retrieval models and 6.2% over a learning to rank baseline.