In text-audio retrieval (TAR) tasks, due to the heterogeneity of contents between text and audio, the semantic information contained in the text is only similar to certain frames within the audio. Yet, existing works aggregate the entire audio without considering the text, such as mean-pooling over the frames, which is likely to encode misleading audio information not described in the given text. In this paper, we present a text-aware attention pooling (TAP) module for TAR, which is essentially a scaled dot product attention for a text to attend to its most semantically similar frames. Furthermore, previous methods only conduct the softmax for every single-side retrieval, ignoring the potential cross-retrieval information. By exploring the intrinsic prior of each text-audio pair, we introduce a prior matrix revised (PMR) loss to filter the hard case with high (or low) text-to-audio but low (or high) audio-to-text similarity scores, thus achieving the dual optimal match. Experiments show that our TAP significantly outperforms various text-agnostic pooling functions. Moreover, our PMR loss also shows stable performance gains on multiple datasets.
Over the eight months since its release, ChatGPT and its underlying model, GPT3.5, have garnered massive attention, due to their potent mix of capability and accessibility. While a niche-industry of papers have emerged examining the scope of capabilities these models possess, the information fed to and extracted from these networks has been either natural language text or stylized, code-like language. Drawing inspiration from the prowess we expect a truly human-level intelligent agent to have across multiple signal modalities, in this work we examine GPT3.5's aptitude for visual tasks, where the inputs feature content provided as ASCII-art without overt distillation into a lingual summary. We conduct experiments analyzing the model's performance on image recognition tasks after various transforms typical in visual settings, trials investigating knowledge of image parts, and tasks covering image generation.
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features. This work bridges this 2D-to-3D gap for robotic manipulation by leveraging distilled feature fields to combine accurate 3D geometry with rich semantics from 2D foundation models. We present a few-shot learning method for 6-DOF grasping and placing that harnesses these strong spatial and semantic priors to achieve in-the-wild generalization to unseen objects. Using features distilled from a vision-language model, CLIP, we present a way to designate novel objects for manipulation via free-text natural language, and demonstrate its ability to generalize to unseen expressions and novel categories of objects.
The rise of large language models (LLMs) had a transformative impact on search, ushering in a new era of search engines that are capable of generating search results in natural language text, imbued with citations for supporting sources. Building generative information-seeking models demands openly accessible datasets, which currently remain lacking. In this paper, we introduce a new dataset, HAGRID (Human-in-the-loop Attributable Generative Retrieval for Information-seeking Dataset) for building end-to-end generative information-seeking models that are capable of retrieving candidate quotes and generating attributed explanations. Unlike recent efforts that focus on human evaluation of black-box proprietary search engines, we built our dataset atop the English subset of MIRACL, a publicly available information retrieval dataset. HAGRID is constructed based on human and LLM collaboration. We first automatically collect attributed explanations that follow an in-context citation style using an LLM, i.e. GPT-3.5. Next, we ask human annotators to evaluate the LLM explanations based on two criteria: informativeness and attributability. HAGRID serves as a catalyst for the development of information-seeking models with better attribution capabilities.
Public figures receive a disproportionate amount of abuse on social media, impacting their active participation in public life. Automated systems can identify abuse at scale but labelling training data is expensive, complex and potentially harmful. So, it is desirable that systems are efficient and generalisable, handling both shared and specific aspects of online abuse. We explore the dynamics of cross-group text classification in order to understand how well classifiers trained on one domain or demographic can transfer to others, with a view to building more generalisable abuse classifiers. We fine-tune language models to classify tweets targeted at public figures across DOmains (sport and politics) and DemOgraphics (women and men) using our novel DODO dataset, containing 28,000 labelled entries, split equally across four domain-demographic pairs. We find that (i) small amounts of diverse data are hugely beneficial to generalisation and model adaptation; (ii) models transfer more easily across demographics but models trained on cross-domain data are more generalisable; (iii) some groups contribute more to generalisability than others; and (iv) dataset similarity is a signal of transferability.
Legal judgment prediction is the task of predicting the outcome of court cases on a given text description of facts of cases. These tasks apply Natural Language Processing (NLP) techniques to predict legal judgment results based on facts. Recently, large-scale public datasets and NLP models have increased research in areas related to legal judgment prediction systems. For such systems to be practically helpful, they should be robust from adversarial attacks. Previous works mainly focus on making a neural legal judgement system; however, significantly less or no attention has been given to creating a robust Legal Judgement Prediction(LJP) system. We implemented adversarial attacks on early existing LJP systems and found that none of them could handle attacks. In this work, we proposed an approach for making robust LJP systems. Extensive experiments on three legal datasets show significant improvements in our approach over the state-of-the-art LJP system in handling adversarial attacks. To the best of our knowledge, we are the first to increase the robustness of early-existing LJP systems.
The Fourth Industrial Revolution, particularly Artificial Intelligence (AI), has had a profound impact on society, raising concerns about its implications and ethical considerations. The emergence of text generative AI tools like ChatGPT has further intensified concerns regarding ethics, security, privacy, and copyright. This study aims to examine the perceptions of individuals in different information flow categorizations toward AI. The results reveal key themes in participant-supplied definitions of AI and the fourth industrial revolution, emphasizing the replication of human intelligence, machine learning, automation, and the integration of digital technologies. Participants expressed concerns about job replacement, privacy invasion, and inaccurate information provided by AI. However, they also recognized the benefits of AI, such as solving complex problems and increasing convenience. Views on government involvement in shaping the fourth industrial revolution varied, with some advocating for strict regulations and others favoring support and development. The anticipated changes brought by the fourth industrial revolution include automation, potential job impacts, increased social disconnect, and reliance on technology. Understanding these perceptions is crucial for effectively managing the challenges and opportunities associated with AI in the evolving digital landscape.
Task-oriented dialogue (TOD) models have great progress in the past few years. However, these studies primarily focus on datasets written by annotators, which has resulted in a gap between academic research and more realistic spoken conversation scenarios. While a few small-scale spoken TOD datasets are proposed to address robustness issues, e.g., ASR errors, they fail to identify the unique challenges in spoken conversation. To tackle the limitations, we introduce SpokenWOZ, a large-scale speech-text dataset for spoken TOD, which consists of 8 domains, 203k turns, 5.7k dialogues and 249 hours of audios from human-to-human spoken conversations. SpokenWOZ incorporates common spoken characteristics such as word-by-word processing and commonsense reasoning. We also present cross-turn slot and reasoning slot detection as new challenges based on the spoken linguistic phenomena. We conduct comprehensive experiments on various models, including text-modal baselines, newly proposed dual-modal baselines and LLMs. The results show the current models still has substantial areas for improvement in spoken conversation, including fine-tuned models and LLMs, i.e., ChatGPT.
A Bill of Materials (BoM) is a list of all components on a printed circuit board (PCB). Since BoMs are useful for hardware assurance, automatic BoM extraction (AutoBoM) is of great interest to the government and electronics industry. To achieve a high-accuracy AutoBoM process, domain knowledge of PCB text and logos must be utilized. In this study, we discuss the challenges associated with automatic PCB marking extraction and propose 1) a plan for collecting salient PCB marking data, and 2) a framework for incorporating this data for automatic PCB assurance. Given the proposed dataset plan and framework, subsequent future work, implications, and open research possibilities are detailed.
In natural language generation (NLG), insight mining is seen as a data-to-text task, where data is mined for interesting patterns and verbalised into 'insight' statements. An 'over-generate and rank' paradigm is intuitively used to generate such insights. The multidimensionality and subjectivity of this process make it challenging. This paper introduces a schema-driven method to generate actionable insights from data to drive growth and change. It also introduces a technique to rank the insights to align with user interests based on their feedback. We show preliminary qualitative results of the insights generated using our technique and demonstrate its ability to adapt to feedback.