Personalization of search results has gained increasing attention in the past few years, also thanks to the development of Neural Networks-based approaches for Information Retrieval. Recent works have proposed to build user models at query time by leveraging the Attention mechanism, which allows weighing the contribution of the user-related information w.r.t. the current query.This approach allows giving more importance to the user’s interests related to the current search performed by the user.In this paper, we discuss some shortcomings of the Attention mechanism when employed for personalization and introduce a novel Attention variant, the Denoising Attention, to solve them.Denoising Attention adopts a robust normalization scheme and introduces a filtering mechanism to better discern among the user-related data those helpful for personalization.Experimental evaluation shows improvements in MAP, MRR, and NDCG above 15% w.r.t. other Attention variants at the state-of-the-art.

Fact-checking using evidences is the preferred way to tackle the issue of misinformation in the society. The democratization of information through social media has accelerated the spread of information, allowing misinformation to reach and influence a vast audience. The significant impact of these falsehoods on society and public opinion underscores the need for automated approaches to identify and combat this phenomenon.This paper is describes the participation of team IKR3-UNIMIB in AVeriTeC (Automated Verification of Textual Claims) 2024 shared task. We proposed a methods to retrieve evidence in the question and answer format and predict the veracity of a claim. As part of the AVeriTeC shared task, our method combines similarity-based ColBERT re-ranker with traditional keyword search using BM25. Additionally, a recent promising approach, Chain of RAG (CoRAG) is introduced to generate question and answer pairs (QAs) to evaluate performance on this specific dataset. We explore whether generating questions from claims or answers produces more effective QA pairs for veracity prediction. Additionally, we try to generate questions from the claim rather than from evidence (opposite the AVeriTeC dataset paper) to generate effective QA pairs for veracity prediction. Our method achieved an AVeriTeC Score of 0.18 (more than baseline) on the test dataset, demonstrating its potential in automated fact-checking.

The fine-tuning paradigm has been widely adopted to train neural models tailored for specific tasks. However, the recent upsurge of Large Language Models (LLMs), characterized by billions of parameters, has introduced profound computational challenges to the fine-tuning process. This has fueled intensive research on Parameter-Efficient Fine-Tuning (PEFT) techniques, usually involving the training of a selective subset of the original model parameters. One of the most used approaches is Adapters, which add trainable lightweight layers to the existing pretrained weights. Within this context, we propose AdaKron, an Adapter-based fine-tuning with the Kronecker product. In particular, we leverage the Kronecker product to combine the output of two small networks, resulting in a final vector whose dimension is the product of the dimensions of the individual outputs, allowing us to train only 0.55% of the model’s original parameters. We evaluate AdaKron performing a series of experiments on the General Language Understanding Evaluation (GLUE) benchmark, achieving results in the same ballpark as recent state-of-the-art PEFT methods, despite training fewer parameters.

This paper describes our contribution to the Answer Localization track of the MedVidQA 2022 Shared Task. We propose two answer localization approaches that use only textual information extracted from the video. In particular, our approaches exploit the text extracted from the video’s transcripts along with the text displayed in the video’s frames to create a set of features. Having created a set of features that represents a video’s textual information, we employ four different models to measure the similarity between a video’s segment and a corresponding question. Then, we employ two different methods to obtain the start and end times of the identified answer. One of them is based on a random forest regressor, whereas the other one uses an unsupervised peak detection model to detect the answer’s start time. Our findings suggest that for this task, leveraging only text-related features (transmitted either verbally or visually) and using a small amount of training data, lead to significant improvements over the benchmark Video Span Localization model that is based on deep neural networks.

We present a new gold-standard dataset and a benchmark for the Research Theme Identification task, a sub-task of the Scholarly Knowledge Graph Generation shared task, at the 3rd Workshop on Scholarly Document Processing. The objective of the shared task was to label given research papers with research themes from a total of 36 themes. The benchmark was compiled using data drawn from the largest overall assessment of university research output ever undertaken globally (the Research Excellence Framework - 2014). We provide a performance comparison of a transformer-based ensemble, which obtains multiple predictions for a research paper, given its multiple textual fields (e.g. title, abstract, reference), with traditional machine learning models. The ensemble involves enriching the initial data with additional information from open-access digital libraries and Argumentative Zoning techniques (CITATION). It uses a weighted sum aggregation for the multiple predictions to obtain a final single prediction for the given research paper. Both data and the ensemble are publicly available on https://www.kaggle.com/competitions/sdp2022-scholarly-knowledge-graph-generation/data?select=task1_test_no_label.csv and https://github.com/ProjectDoSSIER/sdp2022, respectively.

With the advent of contextualized embeddings, attention towards neural ranking approaches for Information Retrieval increased considerably. However, two aspects have remained largely neglected: i) queries usually consist of few keywords only, which increases ambiguity and makes their contextualization harder, and ii) performing neural ranking on non-English documents is still cumbersome due to shortage of labeled datasets. In this paper we present SIR (Sense-enhanced Information Retrieval) to mitigate both problems by leveraging word sense information. At the core of our approach lies a novel multilingual query expansion mechanism based on Word Sense Disambiguation that provides sense definitions as additional semantic information for the query. Importantly, we use senses as a bridge across languages, thus allowing our model to perform considerably better than its supervised and unsupervised alternatives across French, German, Italian and Spanish languages on several CLEF benchmarks, while being trained on English Robust04 data only. We release SIR at https://github.com/SapienzaNLP/sir.