An ideal integration of autonomous agents in a human world implies that they are able to collaborate on human terms. In particular, theory of mind plays an important role in maintaining common ground during human collaboration and communication. To e
nable theory of mind modeling in situated interactions, we introduce a fine-grained dataset of collaborative tasks performed by pairs of human subjects in the 3D virtual blocks world of Minecraft. It provides information that captures partners' beliefs of the world and of each other as an interaction unfolds, bringing abundant opportunities to study human collaborative behaviors in situated language communication. As a first step towards our goal of developing embodied AI agents able to infer belief states of collaborative partners in situ, we build and present results on computational models for several theory of mind tasks.
Much of the progress in contemporary NLP has come from learning representations, such as masked language model (MLM) contextual embeddings, that turn challenging problems into simple classification tasks. But how do we quantify and explain this effec
t? We adapt general tools from computational learning theory to fit the specific characteristics of text datasets and present a method to evaluate the compatibility between representations and tasks. Even though many tasks can be easily solved with simple bag-of-words (BOW) representations, BOW does poorly on hard natural language inference tasks. For one such task we find that BOW cannot distinguish between real and randomized labelings, while pre-trained MLM representations show 72x greater distinction between real and random labelings than BOW. This method provides a calibrated, quantitative measure of the difficulty of a classification-based NLP task, enabling comparisons between representations without requiring empirical evaluations that may be sensitive to initializations and hyperparameters. The method provides a fresh perspective on the patterns in a dataset and the alignment of those patterns with specific labels.
Starting from an existing account of semantic classification and learning from interaction formulated in a Probabilistic Type Theory with Records, encompassing Bayesian inference and learning with a frequentist flavour, we observe some problems with
this account and provide an alternative account of classification learning that addresses the observed problems. The proposed account is also broadly Bayesian in nature but instead uses a linear transformation model for classification and learning.
Statements that are intentionally misstated (or manipulated) are of considerable interest to researchers, government, security, and financial systems. According to deception literature, there are reliable cues for detecting deception and the belief t
hat liars give off cues that may indicate their deception is near-universal. Therefore, given that deceiving actions require advanced cognitive development that honesty simply does not require, as well as people's cognitive mechanisms have promising guidance for deception detection, in this Ph.D. ongoing research, we propose to examine discourse structure patterns in multilingual deceptive news corpora using the Rhetorical Structure Theory framework. Considering that our work is the first to exploit multilingual discourse-aware strategies for fake news detection, the research community currently lacks multilingual deceptive annotated corpora. Accordingly, this paper describes the current progress in this thesis, including (i) the construction of the first multilingual deceptive corpus, which was annotated by specialists according to the Rhetorical Structure Theory framework, and (ii) the introduction of two new proposed rhetorical relations: INTERJECTION and IMPERATIVE, which we assume to be relevant for the fake news detection task.
We propose a probabilistic account of semantic inference and classification formulated in terms of probabilistic type theory with records, building on Cooper et. al. (2014) and Cooper et. al. (2015). We suggest probabilistic type theoretic formulatio
ns of Naive Bayes Classifiers and Bayesian Networks. A central element of these constructions is a type-theoretic version of a random variable. We illustrate this account with a simple language game combining probabilistic classification of perceptual input with probabilistic (semantic) inference.
The Moral Foundation Theory suggests five moral foundations that can capture the view of a user on a particular issue. It is widely used to identify sentence-level sentiment. In this paper, we study the Moral Foundation Theory in tweets by US politic
ians on two politically divisive issues - Gun Control and Immigration. We define the nuanced stance of politicians on these two topics by the grades given by related organizations to the politicians. First, we identify moral foundations in tweets from a huge corpus using deep relational learning. Then, qualitative and quantitative evaluations using the corpus show that there is a strong correlation between the moral foundation usage and the politicians' nuanced stance on a particular topic. We also found substantial differences in moral foundation usage by different political parties when they address different entities. All of these results indicate the need for more intense research in this area.
Natural language processing (NLP) applications are now more powerful and ubiquitous than ever before. With rapidly developing (neural) models and ever-more available data, current NLP models have access to more information than any human speaker duri
ng their life. Still, it would be hard to argue that NLP models have reached human-level capacity. In this position paper, we argue that the reason for the current limitations is a focus on information content while ignoring language's social factors. We show that current NLP systems systematically break down when faced with interpreting the social factors of language. This limits applications to a subset of information-related tasks and prevents NLP from reaching human-level performance. At the same time, systems that incorporate even a minimum of social factors already show remarkable improvements. We formalize a taxonomy of seven social factors based on linguistic theory and exemplify current failures and emerging successes for each of them. We suggest that the NLP community address social factors to get closer to the goal of human-like language understanding.
Neural language models, including transformer-based models, that are pre-trained on very large corpora became a common way to represent text in various tasks, including recognition of textual semantic relations, e.g. Cross-document Structure Theory.
Pre-trained models are usually fine tuned to downstream tasks and the obtained vectors are used as an input for deep neural classifiers. No linguistic knowledge obtained from resources and tools is utilised. In this paper we compare such universal approaches with a combination of rich graph-based linguistically motivated sentence representation and a typical neural network classifier applied to a task of recognition of CST relation in Polish. The representation describes selected levels of the sentence structure including description of lexical meanings on the basis of the wordnet (plWordNet) synsets and connected SUMO concepts. The obtained results show that in the case of difficult relations and medium size training corpus semantically enriched text representation leads to significantly better results.
This research sought to illuminate the skills of self-learning as one of the requirements of the knowledge society today. A fundamental aspect is that the student of Riyadh must be able to form the personality of the researcher, reader and evaluator to make them achieve their objectives and solve their concerns towards the experience of change and innovation.
The current random behavior of stakeholders within the Al-Abrash river basin in Syrian coastal region, the lake and the river, threatens more than ever to pollute the whole basin. The goal of this paper is to address the state of shared management of
water resources among local players through game theory application based on two self-interest strategies for each player to reach a balance point taking into consideration the government intervention as the organizer of the game. Therefore, non-cooperative game theory NCGT adopted as an analytical approach for modeling planning assets conflicts. ArcGIS software adopted to define different areas according to its risk/land-use types. The result shows that the equilibrium point "non-cooperate-non-cooperate" strategy between the players could lean towards "cooperative-cooperative" strategy in the light of the provincial government effect, adopting innovating competitive planning policies. That will lead to an interactive economical-environmental balance in the river basin and helps to reach rational decisions. Therefore, this paper could be classified as one of the studies seeking to apply the participatory planning approach toward sustainable development. Index Terms-Al-Abrash river basin, environmental protection strategy, game theory, participatory approach.
