We introduce PAELLA, a Parameter-Efficient Lightweight Language-Agnostic image captioning model designed to be both parameter and data-efficient using retrieval augmentation. The model is trained by learning a small mapping network with 34M parameters between a pre-trained visual model and a multilingual language model that is conditioned on two types of input: (i) the image itself, and (ii) a set of retrieved captions in the target language. The retrieved examples play a key role in guiding the model to generate captions across languages. Through retrieval, the model can be lightweight in terms of the number of trainable parameters, which only exist in its mapping network, and also in the amount of multilingual training data that is required. Experiments on the XM3600 dataset, featuring 36 languages, show that PAELLA can outperform or compete against some models with 3–77× more learned parameters and 35–863× more data, particularly in low-resource languages. We also find that PAELLA can be trained on only monolingual data and still show strong zero-shot abilities in other languages.

Although the International Classification of Diseases (ICD) has been adopted worldwide, manually assigning ICD codes to clinical text is time-consuming, error-prone, and expensive, motivating the development of automated approaches. This paper describes a novel approach for automated ICD coding, combining several ideas from previous related work. We specifically employ a strong Transformer-based model as a text encoder and, to handle lengthy clinical narratives, we explored either (a) adapting the base encoder model into a Longformer, or (b) dividing the text into chunks and processing each chunk independently. The representations produced by the encoder are combined with a label embedding mechanism that explores diverse ICD code synonyms. Experiments with different splits of the MIMIC-III dataset show that the proposed approach outperforms the current state-of-the-art models in ICD coding, with the label embeddings significantly contributing to the good performance. Our approach also leads to properly calibrated classification results, which can effectively inform downstream tasks such as quantification.

This study investigates the existence of positional biases in Transformer-based language 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 embedding learning. We examine positional biases at multiple stages of the training pipeline for an encoder-decoder neural retrieval model, namely 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 the beginning of the input content, with fine-tuning further aggravating this effect.

ABSTRACT: This paper describes our approach to the SemEval-2024 safe biomedical Natural Language Inference for Clinical Trials (NLI4CT) task, which concerns classifying statements about Clinical Trial Reports (CTRs). We explored the capabilities of Mistral-7B, a generalistic open-source Large Language Model (LLM). We developed a prompt for the NLI4CT task, and fine-tuning a quantized version of the model using a slightly augmented version of the training dataset. The experimental results show that this approach can produce notable results in terms of the macro F1-score, while having limitations in terms of faithfulness and consistency. All the developed code is publicly available on a GitHub repository.

Multilingual image captioning has recently been tackled by training with large-scale machine translated data, which is an expensive, noisy, and time-consuming process. Without requiring any multilingual caption data, we propose LMCap, an image-blind few-shot multilingual captioning model that works by prompting a language model with retrieved captions. Specifically, instead of following the standard encoder-decoder paradigm, given an image, LMCap first retrieves the captions of similar images using a multilingual CLIP encoder. These captions are then combined into a prompt for an XGLM decoder, in order to generate captions in the desired language. In other words, the generation model does not directly process the image, instead it processes retrieved captions. Experiments on the XM3600 dataset of geographically diverse images show that our model is competitive with fully-supervised multilingual captioning models, without requiring any supervised training on any captioning data.

Task-oriented dialogue systems need to generate appropriate responses to help fulfill users’ requests. This paper explores different strategies, namely prompting, retrieval, and fine-tuning, for task-oriented dialogue generation. Through a systematic evaluation, we aim to provide valuable insights and guidelines for researchers and practitioners working on developing efficient and effective dialogue systems for real-world applications. Evaluation is performed on the MultiWOZ and Taskmaster-2 datasets, and we test various versions of FLAN-T5, GPT-3.5, and GPT-4 models. Costs associated with running these models are analyzed, and dialogue evaluation is briefly discussed. Our findings suggest that when testing data differs from the training data, fine-tuning may decrease performance, favoring a combination of a more general language model and a prompting mechanism based on retrieved examples.

Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be effectively formulated from this new perspective. Our model, named EXTRA, benefits from using captions retrieved from the training dataset, and it can also benefit from using an external dataset without the need for retraining. Ablation studies show that retrieving a sufficient number of captions (e.g., k=5) can improve captioning quality. Our work contributes towards using pretrained V&L encoders for generative tasks, instead of standard classification tasks.

Interest in argument mining has resulted in an increasing number of argument annotated corpora. However, most focus on English texts with explicit argumentative discourse markers, such as persuasive essays or legal documents. Conversely, we report on the first extensive and consolidated Portuguese argument annotation project focused on opinion articles. We briefly describe the annotation guidelines based on a multi-layered process and analyze the manual annotations produced, highlighting the main challenges of this textual genre. We then conduct a comprehensive inter-annotator agreement analysis, including argumentative discourse units, their classes and relations, and resulting graphs. This analysis reveals that each of these aspects tackles very different kinds of challenges. We observe differences in annotator profiles, motivating our aim of producing a non-aggregated corpus containing the insights of every annotator. We note that the interpretation and identification of token-level arguments is challenging; nevertheless, tasks that focus on higher-level components of the argument structure can obtain considerable agreement. We lay down perspectives on corpus usage, exploiting its multi-faceted nature.

Templated answers are used extensively in customer support scenarios, providing an efficient way to cover a plethora of topics, with an easily maintainable collection of templates. However, the number of templates is often too high for an agent to manually search. Automatically suggesting the correct template for a given question can thus improve the service efficiency, reducing costs and leading to a better customer satisfaction. In this work, we propose a dense retrieval framework for the customer support scenario, adapting a standard in-batch negatives technique to support unpaired sampling of queries and templates. We also propose a novel loss that extends the typical query-centric similarity, exploiting other similarity relations in the training data. Experiments show that our approach achieves considerable improvements, in terms of performance and training speed, over more standard dense retrieval methods. This includes methods such as DPR, and also ablated versions of the proposed approach.

This work describes a process to extract Named Entity (NE) translations from the text available in web links (anchor texts). It translates a NE by retrieving a list of web documents in the target language, extracting the anchor texts from the links to those documents and finding the best translation from the anchor texts, using a combination of features, some of which, are specific to anchor texts. Experiments performed on a manually built corpora, suggest that over 70% of the NEs, ranging from unpopular to popular entities, can be translated correctly using sorely anchor texts. Tests on a Machine Translation task indicate that the system can be used to improve the quality of the translations of state-of-the-art statistical machine translation systems.