Automatic Audio Captioning (AAC) is the task that aims to describe an audio signal using natural language. AAC systems take as input an audio signal and output a free-form text sentence, called a caption. Evaluating such systems is not trivial, since there are many ways to express the same idea. For this reason, several complementary metrics, such as BLEU, CIDEr, SPICE and SPIDEr, are used to compare a single automatic caption to one or several captions of reference, produced by a human annotator. Nevertheless, an automatic system can produce several caption candidates, either using some randomness in the sentence generation process, or by considering the various competing hypothesized captions during decoding with beam-search, for instance. If we consider an end-user of an AAC system, presenting several captions instead of a single one seems relevant to provide some diversity, similarly to information retrieval systems. In this work, we explore the possibility to consider several predicted captions in the evaluation process instead of one. For this purpose, we propose SPIDEr-max, a metric that takes the maximum SPIDEr value among the scores of several caption candidates. To advocate for our metric, we report experiments on Clotho v2.1 and AudioCaps, with a transformed-based system. On AudioCaps for example, this system reached a SPIDEr-max value (with 5 candidates) close to the SPIDEr human score of reference.
Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training multilingual models on English-only resources and transferring them to low-resource languages. However, its effect is limited by the gap between embedding clusters of different languages. To address this issue, we propose Embedding-Push, Attention-Pull, and Robust targets to transfer English embeddings to virtual multilingual embeddings without semantic loss, thereby improving cross-lingual transferability. Experimental results on mBERT and XLM-R demonstrate that our method significantly outperforms previous works on the zero-shot cross-lingual text classification task and can obtain a better multilingual alignment.
Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due to the quadratic complexity of the Transformer, a down-sampling step is essential for its adoption in Speech Translation. Instead, in this research, we propose to ease the complexity by using a Perceiver encoder to map the speech inputs to a fixed-length latent representation. Furthermore, we introduce a novel way of training Perceivers, with Dynamic Latent Access (DLA), unlocking larger latent spaces without any additional computational overhead. Speech-to-Text Perceivers with DLA can match the performance of a Transformer baseline across three language pairs in MuST-C. Finally, a DLA-trained model is easily adaptable to DLA at inference, and can be flexibly deployed with various computational budgets, without significant drops in translation quality.
People may be puzzled by the fact that voice over recordings data sets exist in addition to Text-to-Speech (TTS), Synthesis system advancements, albeit this is not the case. The goal of this study is to explain the relevance of TTS as well as the data preparation procedures. TTS relies heavily on recorded data since it can have a substantial influence on the outcomes of TTS modules. Furthermore, whether the domain is specialized or general, appropriate data should be developed to address all predicted language variants and domains. Different recording methodologies, taking into account quality and behavior, may also be advantageous in the development of the module. In light of the lack of Arabic language in present synthesizing systems, numerous variables that impact the flow of recorded utterances are being considered in order to manipulate an Arabic TTS module. In this study, two viewpoints will be discussed: linguistics and the creation of high-quality recordings for TTS. The purpose of this work is to offer light on how ground-truth utterances may influence the evolution of speech systems in terms of naturalness, intelligibility, and understanding. Well provide voice actor specs as well as data specs that will assist both voice actors and voice coaches in the studio as well as the annotators who will be evaluating the audios.
Machine generation of Arithmetic Word Problems (AWPs) is challenging as they express quantities and mathematical relationships and need to be consistent. ML-solvers require a large annotated training set of consistent problems with language variations. Exploiting domain-knowledge is needed for consistency checking whereas LSTM-based approaches are good for producing text with language variations. Combining these we propose a system, OLGA, to generate consistent word problems of TC (Transfer-Case) type, involving object transfers among agents. Though we provide a dataset of consistent 2-agent TC-problems for training, only about 36% of the outputs of an LSTM-based generator are found consistent. We use an extension of TC-Ontology, proposed by us previously, to determine the consistency of problems. Among the remaining 64%, about 40% have minor errors which we repair using the same ontology. To check consistency and for the repair process, we construct an instance-specific representation (ABox) of an auto-generated problem. We use a sentence classifier and BERT models for this task. The training set for these LMs is problem-texts where sentence-parts are annotated with ontology class-names. As three-agent problems are longer, the percentage of consistent problems generated by an LSTM-based approach drops further. Hence, we propose an ontology-based method that extends consistent 2-agent problems into consistent 3-agent problems. Overall, our approach generates a large number of consistent TC-type AWPs involving 2 or 3 agents. As ABox has all the information of a problem, any annotations can also be generated. Adopting the proposed approach to generate other types of AWPs is interesting future work.
Residual minimization is a widely used technique for solving Partial Differential Equations in variational form. It minimizes the dual norm of the residual, which naturally yields a saddle-point (min-max) problem over the so-called trial and test spaces. Such min-max problem is highly non-linear, and traditional methods often employ different mixed formulations to approximate it. Alternatively, it is possible to address the above saddle-point problem by employing Adversarial Neural Networks: one network approximates the global trial minimum, while another network seeks the test maximizer. However, this approach is numerically unstable due to a lack of continuity of the text maximizers with respect to the trial functions as we approach the exact solution. To overcome this, we reformulate the residual minimization as an equivalent minimization of a Ritz functional fed by optimal test functions computed from another Ritz functional minimization. The resulting Deep Double Ritz Method combines two Neural Networks for approximating the trial and optimal test functions. Numerical results on several 1D diffusion and convection problems support the robustness of our method up to the approximability and trainability capacity of the networks and the optimizer.
Contextualizing language technologies beyond a single language kindled embracing multiple modalities and languages. Individually, each of these directions undoubtedly proliferated into several NLP tasks. Despite this momentum, most of the multimodal research is primarily centered around English and multilingual research is primarily centered around contexts from text modality. Challenging this conventional setup, researchers studied the unification of multilingual and multimodal (MultiX) streams. The main goal of this work is to catalogue and characterize these works by charting out the categories of tasks, datasets and methods to address MultiX scenarios. To this end, we review the languages studied, gold or silver data with parallel annotations, and understand how these modalities and languages interact in modeling. We present an account of the modeling approaches along with their strengths and weaknesses to better understand what scenarios they can be used reliably. Following this, we present the high-level trends in the overall paradigm of the field. Finally, we conclude by presenting a road map of challenges and promising research directions.
NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model. While existing model debugging methods have shown promise, their prototype-level implementations provide limited practical utility. Thus, we propose XMD: the first open-source, end-to-end framework for explanation-based model debugging. Given task- or instance-level explanations, users can flexibly provide various forms of feedback via an intuitive, web-based UI. After receiving user feedback, XMD automatically updates the model in real time, by regularizing the model so that its explanations align with the user feedback. The new model can then be easily deployed into real-world applications via Hugging Face. Using XMD, we can improve the model's OOD performance on text classification tasks by up to 18%.
This position paper proposes a conceptual framework for the design of Natural Language Generation (NLG) systems that follow efficient and effective production strategies in order to achieve complex communicative goals. In this general framework, efficiency is characterised as the parsimonious regulation of production and comprehension costs while effectiveness is measured with respect to task-oriented and contextually grounded communicative goals. We provide concrete suggestions for the estimation of goals, costs, and utility via modern statistical methods, demonstrating applications of our framework to the classic pragmatic task of visually grounded referential games and to abstractive text summarisation, two popular generation tasks with real-world applications. In sum, we advocate for the development of NLG systems that learn to make pragmatic production decisions from experience, by reasoning about goals, costs, and utility in a human-like way.
Explainable question answering systems should produce not only accurate answers but also rationales that justify their reasoning and allow humans to check their work. But what sorts of rationales are useful and how can we train systems to produce them? We propose a new style of rationale for open-book question answering, called \emph{markup-and-mask}, which combines aspects of extractive and free-text explanations. In the markup phase, the passage is augmented with free-text markup that enables each sentence to stand on its own outside the discourse context. In the masking phase, a sub-span of the marked-up passage is selected. To train a system to produce markup-and-mask rationales without annotations, we leverage in-context learning. Specifically, we generate silver annotated data by sending a series of prompts to a frozen pretrained language model, which acts as a teacher. We then fine-tune a smaller student model by training on the subset of rationales that led to correct answers. The student is "honest" in the sense that it is a pipeline: the rationale acts as a bottleneck between the passage and the answer, while the "untrusted" teacher operates under no such constraints. Thus, we offer a new way to build trustworthy pipeline systems from a combination of end-task annotations and frozen pretrained language models.