Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSeeing Things from a Different Angle: Discovering Diverse Perspectives about Claims
74
0
0.0
(
0
)
Added by
Sihao Chen
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
One key consequence of the information revolution is a significant increase and a contamination of our information supply. The practice of fact checking wont suffice to eliminate the biases in text data we observe, as the degree of factuality alone does not determine whether biases exist in the spectrum of opinions visible to us. To better understand controversial issues, one needs to view them from a diverse yet comprehensive set of perspectives. For example, there are many ways to respond to a claim such as animals should have lawful rights, and these responses form a spectrum of perspectives, each with a stance relative to this claim and, ideally, with evidence supporting it. Inherently, this is a natural language understanding task, and we propose to address it as such. Specifically, we propose the task of substantiated perspective discovery where, given a claim, a system is expected to discover a diverse set of well-corroborated perspectives that take a stance with respect to the claim. Each perspective should be substantiated by evidence paragraphs which summarize pertinent results and facts. We construct PERSPECTRUM, a dataset of claims, perspectives and evidence, making use of online debate websites to create the initial data collection, and augmenting it using search engines in order to expand and diversify our dataset. We use crowd-sourcing to filter out noise and ensure high-quality data. Our dataset contains 1k claims, accompanied with pools of 10k and 8k perspective sentences and evidence paragraphs, respectively. We provide a thorough analysis of the dataset to highlight key underlying language understanding challenges, and show that human baselines across multiple subtasks far outperform ma-chine baselines built upon state-of-the-art NLP techniques. This poses a challenge and opportunity for the NLP community to address.
rate research
Read More
This work presents PerspectroScope, a web-based system which lets users query a discussion-worthy natural language claim, and extract and visualize various perspectives in support or against the claim, along with evidence supporting each perspective. The system thus lets users explore various perspectives that could touch upon aspects of the issue at hand.The system is built as a combination of retrieval engines and learned textual-entailment-like classifiers built using a few recent developments in natural language understanding. To make the system more adaptive, expand its coverage, and improve its decisions over time, our platform employs various mechanisms to get corrections from the users. PerspectroScope is available at github.com/CogComp/perspectroscope.
We present the analysis of 12 high-resolution galactic rotation curves from The HI Nearby Galaxy Survey (THINGS) in the context of modified Newtonian dynamics (MOND). These rotation curves were selected to be the most reliable for mass modelling, and they are the highest quality rotation curves currently available for a sample of galaxies spanning a wide range of luminosities. We fit the rotation curves with the simple and standard interpolating functions of MOND, and we find that the simple function yields better results. We also redetermine the value of a0, and find a median value very close to the one determined in previous studies, a0 = (1.22 +- 0.33) x 10^{-8} cm/s^2. Leaving the distance as a free parameter within the uncertainty of its best independently determined value leads to excellent quality fits for 75% of the sample. Among the three exceptions, two are also known to give relatively poor fits also in Newtonian dynamics plus dark matter. The remaining case (NGC 3198), presents some tension between the observations and the MOND fit, which might however be explained by the presence of non-circular motions, by a small distance, or by a value of a0 at the lower end of our best-fit interval, 0.9 x 10^{-8} cm/s^2. The best-fit stellar M/L ratios are generally in remarkable agreement with the predictions of stellar population synthesis models. We also show that the narrow range of gravitational accelerations found to be generated by dark matter in galaxies is consistent with the narrow range of additional gravity predicted by MOND.
Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a further pre-training phase between pre-training and fine-tuning phases to adapt the model on the domain-specific unlabeled data can bring positive effects. However, most of these further pre-training works just keep running the conventional pre-training task, e.g., masked language model, which can be regarded as the domain adaptation to bridge the data distribution gap. After observing diverse downstream tasks, we suggest that different tasks may also need a further pre-training phase with appropriate training tasks to bridge the task formulation gap. To investigate this, we carry out a study for improving multiple task-oriented dialogue downstream tasks through designing various tasks at the further pre-training phase. The experiment shows that different downstream tasks prefer different further pre-training tasks, which have intrinsic correlation and most further pre-training tasks significantly improve certain target tasks rather than all. Our investigation indicates that it is of great importance and effectiveness to design appropriate further pre-training tasks modeling specific information that benefit downstream tasks. Besides, we present multiple constructive empirical conclusions for enhancing task-oriented dialogues.
A massive current research effort focuses on combining pre-existing Intranets of Things into one Internet of Things. However, this unification is not a panacea; it will expose new attack surfaces and vectors, just as it enables new applications. We therefore urgently need a model of security in the Internet of Things. In this regard, we note that IoT descends directly from pre-existing research (in embedded Internet and pervasive intelligence), so there exist several bodies of related work: security in RFID, sensor networks, cyber-physical systems, and so on. In this paper, we survey the existing literature on RFID and WSN security, as a step to compiling all known attacks and defenses relevant to the Internet of Things.
We introduce a set of nine challenge tasks that test for the understanding of function words. These tasks are created by structurally mutating sentences from existing datasets to target the comprehension of specific types of function words (e.g., prepositions, wh-words). Using these probing tasks, we explore the effects of various pretraining objectives for sentence encoders (e.g., language modeling, CCG supertagging and natural language inference (NLI)) on the learned representations. Our results show that pretraining on language modeling performs the best on average across our probing tasks, supporting its widespread use for pretraining state-of-the-art NLP models, and CCG supertagging and NLI pretraining perform comparably. Overall, no pretraining objective dominates across the board, and our function word probing tasks highlight several intuitive differences between pretraining objectives, e.g., that NLI helps the comprehension of negation.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
