相关论文: ARISE: Iterative Rule Induction and Synthetic Data…
Event Extraction (EE) involves automatically identifying and extracting structured information about events from unstructured text, including triggers, event types, and arguments. Traditional discriminative models demonstrate high precision…
We consider the problem of creating document representations in which inter-document similarity measurements correspond to semantic similarity. We first present a novel subspace-based framework for formalizing this task. Using this…
The choice of input-data used to train algorithm-selection models is recognised as being a critical part of the model success. Recently, feature-free methods for algorithm-selection that use short trajectories obtained from running a solver…
Many critical applications, from autonomous scientific discovery to personalized medicine, demand systems that can both strategically acquire the most informative data and instantaneously perform inference based upon it. While amortized…
We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two…
The grammars of natural languages may be learned by using genetic algorithms that reproduce and mutate grammatical rules and part-of-speech tags, improving the quality of later generations of grammatical components. Syntactic rules are…
Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models. Nevertheless,…
In this paper, we argue that database systems be augmented with an automated data exploration service that methodically steers users through the data in a meaningful way. Such an automated system is crucial for deriving insights from…
From a young age humans learn to use grammatical principles to hierarchically combine words into sentences. Action grammars is the parallel idea, that there is an underlying set of rules (a "grammar") that govern how we hierarchically…
Automatically synthesizing verifiable code from natural language requirements ensures software correctness and reliability while significantly lowering the barrier to adopting the techniques of formal methods. With the rise of large…
Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investigated the…
The artificial intelligence (AI) world is running out of real data for training increasingly large generative models, resulting in accelerating pressure to train on synthetic data. Unfortunately, training new generative models with…
Causal inference is essential for developing and evaluating medical interventions, yet real-world medical datasets are often difficult to access due to regulatory barriers. This makes synthetic data a potentially valuable asset that enables…
Creating challenging tabular inference data is essential for learning complex reasoning. Prior work has mostly relied on two data generation strategies. The first is human annotation, which yields linguistically diverse data but is…
Robust content moderation requires classification systems that can quickly adapt to evolving policies without costly retraining. We present classification using Retrieval-Augmented Generation (RAG), which shifts traditional classification…
The scarcity of large-scale classroom speech data has hindered the development of AI-driven speech models for education. Classroom datasets remain limited and not publicly available, and the absence of dedicated classroom noise or Room…
We present the architecture and the evaluation of a new system for recognizing textual entailment (RTE). In RTE we want to identify automatically the type of a logical relation between two input texts. In particular, we are interested in…
Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such…
In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution.…
Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems. However, the evaluation of neural IR has so far been limited to…