In this paper we propose a new algorithm for solving general two-player turn-taking games that performs symbolic search utilizing binary decision diagrams (BDDs). It consists of two stages: First, it determines all breadth-first search (BFS) layers using forward search and omitting duplicate detection, next, the solving process operates in backward direction only within these BFS layers thereby partitioning all BDDs according to the layers the states reside in. We provide experimental results for selected games and compare to a previous approach. This comparison shows that in most cases the new algorithm outperforms the existing one in terms of runtime and used memory so that it can solve games that could not be solved before with a general approach.
Argument mining is a rising area of Natural Language Pro- cessing (NLP) concerned with the automatic recognition and interpretation of argument components and their relations. Neural models are by now mature technologies to be ex- ploited for automating the argument mining tasks, despite the issue of data sparseness. This could ease much of the man- ual effort involved in these tasks, taking into account hetero- geneous types of texts and topics. In this work, we evaluate different attention mechanisms applied over a state-of-the-art architecture for sequence labeling. We assess the impact of different flavors of attention in the task of argument compo- nent detection over two datasets: essays and legal domain. We show that attention not models the problem better but also supports interpretability.
Dutta, Ayan (University of North Florida) | Bhattacharya, Amitabh (University of North Florida) | Kreidl, O. Patrick (University of North Florida) | Ghosh, Anirban (University of North Florida) | Dasgupta, Prithviraj (University of Nebraska at Omaha)
Information collection is an important application of multi-robot systems especially in environments that are difficult to operate for humans. The objective of the robots is to maximize information collection from the environment while remaining in their path-length budgets. In this paper, we propose a novel multi-robot information collection algorithm that uses a continuous region partitioning approach to efficiently divide an unknown environment among the robots based on the discovered obstacles in the area, for better load-balancing. Our algorithm gracefully handles situations when some of the robots cannot communicate with other robots due to limited communication ranges.
A hybrid recommender system fuses multiple data sources, usually with static and nonadjustable weightings, to deliver recommendations. One limitation of this approach is the problem to match user preference in all situations. In this paper, we present two user-controllable hybrid recommender interfaces, which offer a set of sliders to dynamically tune the impact of different sources of relevance on the final ranking. Two user studies were performed to design and evaluate the proposed interfaces.
Reasoning in the context of a conditional knowledge base containing rules of the form'If A then usually B' can be defined in terms of preference relations on possible worlds. These preference relations can be modeled by ranking functions that assign a degree of disbelief to each possible world. In general, there are multiple ranking functions that accept a given knowledge base. Several nonmonotonic inference relations have been proposed using c-representations, a subset of all ranking functions. These inference relations take subsets of all c-representations based on various notions of minimality into account, and they operate in different inference modes, i.e., skeptical, weakly skeptical, or credulous. For nonmonotonic inference relations, weaker versions of monotonicity like rational monotony (RM) and weak rational monotony (WRM) have been developed. In this paper, we investigate which of the inference relations induced by sets of minimal c-representations satisfy rational monotony or weak rational monotony.
The representation of semantic meaning of sentences using neural network has recently gained popularity, due to the fact that there is no need to specifically extract lexical syntactic and semantic features. A major problem with this approach is that it requires large human annotated corpora. In order to reduce human annotation effort, in recent years, researchers made several attempts to find universal sentence representation methods, aiming to obtain general-purpose sentence em-beddings that could be widely adopted to a wide range of NLP tasks without training directly from the specific datasets. InferSent, a supervised universal sentence representation model proposed by Facebook research, implements 8 popular neural network sentence encoding structures trained on natural language inference datasets, and apply to 12 different NLP tasks. However, the relation classification task was not one of these. In this paper, we retrain these 8 sentence encoding structures and use them as the starting points on relation classification task. Experiments using SemEval-2010 datasets show that our models could achieve comparable results to the state-of-the-art relation classification systems.
This paper presents experimental results showing that discourse structure is a useful element in identifying the focus of negation. We define features extracted from RST-like discourse trees. We experiment with the largest publicly available corpus and an off-the-shelf discourse parser. Results show that discourse structure is especially beneficial when predicting the focus of negations in long sentences.
Zhao, Ran (Carnegie Mellon University) | Deng, Yuntian (Harvard University) | Dredze, Mark (Johns Hopkins University) | Verma, Arun (Bloomberg) | Rosenberg, David (Bloomberg) | Stent, Amanda (Bloomberg)
Technical and fundamental analysis are traditional tools used to analyze individual stocks; however, the finance literature has shown that the price movement of each individual stock correlates heavily with other stocks, especially those within the same sector. In this paper we propose a general-purpose market representation that incorporates fundamental and technical indicators and relationships between individual stocks. We treat the daily stock market as a ‘market image’ where rows (grouped by market sector) represent individual stocks and columns represent indicators. We apply a convolutional neural network over this market image to build market features in a hierarchical way. We use a recurrent neural network, with an attention mechanism over the market feature maps, to model temporal dynamics in the market. We show that our proposed model outperforms strong baselines in both short-term and long-term stock return prediction tasks. We also show another use for our market image: to construct concise and dense market embeddings suitable for downstream prediction tasks.