Related papers: Efficient Semiring-Weighted Earley Parsing

Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources during inference. However, this paradigm is inherently…

Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prompt can cause significant discrepancies in model performance.…

In this article, we present a new approach to averaging in non-Hamiltonian systems with periodic forcing. The results here do not depend on the existence of a small parameter. In fact, we show that our averaging method fits into an…

We study a classical iterative algorithm for balancing matrices in the $L_\infty$ norm via a scaling transformation. This algorithm, which goes back to Osborne and Parlett \& Reinsch in the 1960s, is implemented as a standard preconditioner…

Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an…

Classical translation models constrain the space of possible outputs by selecting a subset of translation rules based on the input sentence. Recent work on improving the efficiency of neural translation models adopted a similar strategy by…

Data-intensive applications, ranging from large-scale retrieval systems to advanced data pipelines, are increasingly bottlenecked by the processing of highly redundant text corpora. We present Merlin, a local-first, agnostic,…

We present importance aligned key iterative algorithm for extractive summarization that is faster than conventional algorithms keeping its accuracy. The computational complexity of our algorithm is O($SNlogN$) to summarize original $N$…

Pre-trained language models have led to a new state-of-the-art in many NLP tasks. However, for topic modeling, statistical generative models such as LDA are still prevalent, which do not easily allow incorporating contextual word vectors.…

With the blooming of various Pre-trained Language Models (PLMs), Machine Reading Comprehension (MRC) has embraced significant improvements on various benchmarks and even surpass human performances. However, the existing works only target on…

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…

In this paper, we introduce a divide-and-conquer algorithm to improve sentence alignment speed. We utilize external bilingual sentence embeddings to find accurate hard delimiters for the parallel texts to be aligned. We use Monte Carlo…

A simple linear-time algorithm for constructing a linear context-free tree grammar of size O(rg + r g log (n/r g))for a given input tree T of size n is presented, where g is the size of a minimal linear context-free tree grammar for T, and…

This technical report is an appendix to Eisner (1996): it gives superior experimental results that were reported only in the talk version of that paper. Eisner (1996) trained three probability models on a small set of about 4,000…

Large Language Models (LLMs) are often asked to generate structured outputs that obey precise syntactic rules, such as code snippets or formatted data. Grammar-constrained decoding (GCD) can guarantee that LLM outputs matches such rules by…

Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to abstract structured data to ease the subsequent acquisition of rich semantic knowledge, much…

Many problems that can be solved in quadratic time have bit-parallel speed-ups with factor $w$, where $w$ is the computer word size. For example, edit distance of two strings of length $n$ can be solved in $O(n^2/w)$ time. In a reasonable…

AM dependency parsing is a linguistically principled method for neural semantic parsing with high accuracy across multiple graphbanks. It relies on a type system that models semantic valency but makes existing parsers slow. We describe an…

As model context lengths continue to grow, concerns about whether models effectively use the full context length have persisted. While several carefully designed long-context evaluations have recently been released, these evaluations tend…

In this paper, a fully compressed pattern matching problem is studied. The compression is represented by straight-line programs (SLPs), i.e. a context-free grammars generating exactly one string; the term fully means that both the pattern…