Related papers: Chunked Lists versus Extensible Arrays for Text In…
Temporal-difference (TD) methods learn state and action values efficiently by bootstrapping from their own future value predictions, but such a self-bootstrapping mechanism is prone to bootstrapping bias, where the errors in the value…
Recent techniques for the task of short text clustering often rely on word embeddings as a transfer learning component. This paper shows that sentence vector representations from Transformers in conjunction with different clustering methods…
Speculative decoding and quantization effectively accelerate memory-bound inference of large language models. Speculative decoding mitigates the memory bandwidth bottleneck by verifying multiple tokens within a single forward pass, which…
Leveraging query variants (QVs), i.e., queries with potentially similar information needs to the target query, has been shown to improve the effectiveness of query performance prediction (QPP) approaches. Existing QV-based QPP methods…
Despite the success of Transformers, handling long contexts remains challenging due to the limited length generalization and quadratic complexity of self-attention. Thus Transformers often require post-training with a larger attention…
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…
Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs). As recent studies introduced fast weights only to regular RNNs, it is…
Spiking Neural Networks (SNNs) have garnered attention over recent years due to their increased energy efficiency and advantages in terms of operational complexity compared to traditional Artificial Neural Networks (ANNs). Two important…
Skiplists are used in a variety of applications for storing data subject to order criteria. In this article we discuss the design, analysis and performance of a concurrent deterministic skiplist on many-core NUMA nodes. We also evaluate the…
Answer selection is an important research problem, with applications in many areas. Previous deep learning based approaches for the task mainly adopt the Compare-Aggregate architecture that performs word-level comparison followed by…
The lock-free, ordered, linked list is an important, standard example of a concurrent data structure. An obvious, practical drawback of textbook implementations is that failed compare-and-swap (CAS) operations lead to retraversal of the…
Question Answering (QA) is fundamental to natural language processing in that most nlp problems can be phrased as QA (Kumar et al., 2015). Current weakly supervised memory network models that have been proposed so far struggle at answering…
Directly reading documents and being able to answer questions from them is an unsolved challenge. To avoid its inherent difficulty, question answering (QA) has been directed towards using Knowledge Bases (KBs) instead, which has proven…
This paper describes a new approach, called Terminological Bucket Indexing (TBI), for efficient indexing and retrieval of both nested and super terms using a single method. We propose a hybrid data structure for facilitating faster indexing…
We test iterative algorithms, MR, QMR$\gamma_5$ and BiCG$\gamma_5$, to compare their efficiency in matrix inversion with multi-quarks (shifted matrices) within one iteration process. Our results on the 8^3 x 12 and 16^3 x 24 show that MR…
Our paper presents solutions that can significantly improve the delay performance of putting and retrieving data in and out of cloud storage. We first focus on measuring the delay performance of a very popular cloud storage service Amazon…
Representing visual data using compact binary codes is attracting increasing attention as binary codes are used as direct indices into hash table(s) for fast non-exhaustive search. Recent methods show that ranking binary codes using…
We engineer a self-index based retrieval system capable of rank-safe evaluation of top-k queries. The framework generalizes the GREEDY approach of Culpepper et al. (ESA 2010) to handle multi-term queries, including over phrases. We propose…
We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and…
Learned sparse representations form an attractive class of contextual embeddings for text retrieval. That is so because they are effective models of relevance and are interpretable by design. Despite their apparent compatibility with…