Abstract

Modelling and understanding time remains a challenge in contemporary video understanding models. Time also appears in language through temporal relations. Video-language models can benefit from having a sense of time, especially since language provides an interface for generalization. In this paper, we consider a specific aspect of temporal understanding: consistency of time order as elicited by before/after relations. We construct a simple synthetic dataset to measure such temporal understanding in video-language models and find that six existing models struggle to understand even such simple relations. We then posit whether it is feasible to equip these foundation models with temporal awareness without re-training them from scratch. Towards this, we propose a temporal adaptation recipe on top of one such model, VideoCLIP, based on postpretraining on a small amount of video-text data. Our work serves as a first step towards probing and instilling a sense of time in existing video-language models without needing data- and compute-intense training from scratch. Project page:

Abstract

We introduce an SSMT (Speech to Speech Machine Translation, aka Speech to Speech Video Translation) Pipeline1 , as a web application for translating videos from one language to another by cascading multiple language modules. Our speech translation system combines highly accurate speech to text (ASR) for Indian English, pre-possessing modules to bridge ASRMT gaps such as spoken disfluency and punctuation, robust machine translation (MT) systems for multiple language pairs, SRT module for translated text, text to speech (TTS) module and a module to render translated synthesized audio on the original video. It is user-friendly, flexible, and easily accessible system. We aim to provide a complete configurable speech translation experience to users and researchers with this system. It also supports human intervention where users can edit outputs of different modules and the edited output can then be used for subsequent processing to improve overall output quality. By adopting a human-in-theloop approach, the aim is to configure technology in such a way where it can assist humans and help to reduce the involved human efforts in speech translation involving English and Indian languages. As per our understanding, this is the first fully integrated system for English to Indian languages (Hindi, Telugu, Gujarati, Marathi, and Punjabi) video translation. Our evaluation shows that one can get 3.5+ MOS score using the developed pipeline with human intervention for English to Hindi. A short video demonstrating our system is available at https://youtu.be/MVftzoeRg48.

Abstract

This paper introduces PMIndiaSum, a new multilingual and massively parallel headline summarization corpus focused on languages in India. Our corpus covers four language families, 14 languages, and the largest to date, 196 language pairs. It provides a testing ground for all cross-lingual pairs. We detail our workflow to construct the corpus, including data acquisition, processing, and quality assurance. Furthermore, we publish benchmarks for monolingual, cross-lingual, and multilingual summarization by fine-tuning, prompting, as well as translate-and-summarize. Experimental results confirm the crucial role of our data in aiding the summarization of Indian texts. Our dataset is publicly available and can be freely modified and re-distributed.

Abstract

Augmenting Wikidata with spatial relations specific to Geography can be useful for increasing its utility in multiple applications. In this paper, we aim to extract orientation of borders between countries in the world, from their Wikipedia text and suggest its use to augment the shares_borders_with relation in Wikidata. We propose the use of Natural Language Inference (NLI) for extracting the orientation relations from text and show that when combined with contextual lexical patterns, the performance becomes better than the standard NLI setting.

Abstract

One of the widely used peak reduction methods in smart grids is demand response, where one analyzes the shift in customers’ (agents’) usage patterns in response to the signal from the distribution company. Often, these signals are in the form of incentives offered to agents. This work studies the effect of incentives on the probabilities of accepting such offers in a real-world smart grid simulator, PowerTAC. We first show that there exists a function that depicts the probability of an agent reducing its load as a function of the discounts offered to them. We call it reduction probability (RP). RP function is further parametrized by the rate of reduction (RR), which can differ for each agent. We provide an optimal algorithm, MJS–EXPRESPONSE, that outputs the discounts to each agent by maximizing the expected reduction under a budget constraint. When RRs are unknown, we propose a Multi-Armed Bandit (MAB) based online algorithm, namely MJSUCB–EXPRESPONSE, to learn RRs. Experimentally we show that it exhibits sublinear regret. Finally, we showcase the efficacy of the proposed algorithm in mitigating demand peaks in a real-world smart grid system using the PowerTAC simulator as a test bed.

Abstract

A system and method for generating a table-driven mutable blockchain are provided. The system includes one or more users 102A-102N associated with one or more nodes 104A-104N, a distributed file unit 106, a distributed ledger 108. The distributed file unit 106 stores a Lineage Table 200 and a global variable P 112, to keep count on the total number of blockchains in the system. The distributed ledger 108 stores one or more blockchains. The node 104A receives transaction details of transaction provided by user 102A through network 110, and defines transaction. The node 104 initializes linked list structure and creates a transaction of which a plurality of modifications is performed on it. The node 104 creates modified transaction in subsequent blockchains and then links these versions by adding sequence of elements in Linked List. The node 104 authenticates new transactions in main blockchain and the modified transactions in subsequent blockchains.

Abstract

Residential energy feedback refers to is about providing personalized information on household energy use to consumers to encourage energy savings. This paper conducts a review of field-based studies that have evaluated the impact of energy feedback on residential energy consumption. The review includes studies in real occupied homes that have deployed feedback intervention(s) and measured energy savings. Our study builds a taxonomy for energy feedback studies based on different characteristics of feedback such as frequency, type, presentation style, and methods of access. Energy savings from similar feedback types were found to differ depending on how the study was conducted. The reviewed studies deployed a range of feedback information including energy units, energy cost and tailored information conducted across diverse audiences (ethnicity, geographical positioning), varying experimental

Abstract

Fact-to-text generation can allow for the generation of high-quality, informative texts such as Wikipedia articles. Cross-lingual fact-to-text generation (XF2T) involves using facts available in a language, typically English, and generating texts in a different language based on these facts. This is particularly relevant for low and medium-resource languages, which have relatively structured informative content. This work explores the problem of XF2T for generating long text from given facts with a specific focus on generating factually grounded content. Unfortunately, previous work either focuses on cross-lingual facts to short text or monolingual graph to text generation. In this paper, we propose a novel solution to the multi-sentence XF2T task, which addresses these challenges by training multilingual Transformer-based models with coverage prompts and rebalanced beam search, and further improving the quality by defining task-specific reward functions and training on them using reinforcement learning. Keywords: XF2T, text generation, cross-lingual, NLG evaluation, low resource NLG

Abstract

The thermodynamics of the hydrophobic effect, as measured primarily through the temperature dependence of solubility, is reviewed, and then a class of models that incorporate the basic mechanism of hydrophobicity is described. These models predict a quantitative relation between the free energy of hydrophobic hydration and the strength of the solvent-mediated attraction between pairs of solute molecules. It is remarked that the free energy of attraction being just of the order of the thermal energy kT may be important for the effective operation of the hydrophobic effect in proteins. Deviations from pairwise additivity of hydrophobic forces are also briefly discussed.

Abstract

The liver plays a vital role in maintaining whole-body metabolic homeostasis, compound detoxification and has the unique ability to regenerate itself post-injury. Ageing leads to functional impairment of the liver and predisposes the liver to non-alcoholic fatty liver disease (NAFLD) and hepatocellular carcinoma (HCC). Mapping the molecular changes of the liver with ageing may help to understand the crosstalk of ageing with different liver diseases. A systems-level analysis of the ageing-induced liver changes and its crosstalk with liver-associated conditions is lacking. In the present study, we performed network-level analyses of the ageing liver using mouse transcriptomic data and a protein–protein interaction (PPI) network. A sample-wise analysis using network entropy measure was performed, which showed an increasing trend with ageing and helped to identify ageing genes based on local entropy changes. To