Related papers: Fence - An Efficient Parser with Ambiguity Support…

Numerical applications and, more recently, machine learning applications rely on high-dimensional data that is typically organized into multi-dimensional tensors. Many existing frameworks, libraries, and domain-specific languages support…

Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a…

Natural language reasoning plays an increasingly important role in improving language models' ability to solve complex language understanding tasks. An interesting use case for reasoning is the resolution of context-dependent ambiguity. But…

Combining several embeddings typically improves performance in downstream tasks as different embeddings encode different information. It has been shown that even models using embeddings from transformers still benefit from the inclusion of…

Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. Towards this task, two main architectures have been applied, namely single-encoder (based on concatenation) and…

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby coupling the model to that compressor. This work introduces…

Large Language Model (LLM) inference is growing increasingly complex with the rise of Mixture-of-Experts (MoE) models and disaggregated architectures that decouple components like prefill/decode (PD) or attention/FFN (AF) for heterogeneous…

We train one multilingual model for dependency parsing and use it to parse sentences in several languages. The parsing model uses (i) multilingual word clusters and embeddings; (ii) token-level language information; and (iii)…

Recent advances in language models (LMs) have driven significant progress in various software engineering tasks. However, existing LMs still struggle with complex programming scenarios due to limitations in data quality, model architecture,…

The paper presents an approach to semantic grounding of language models (LMs) that conceptualizes the LM as a conditional model generating text given a desired semantic message formalized as a set of entity-relationship triples. It embeds…

We describe an efficient bottom-up parser that interleaves syntactic and semantic structure building. Two techniques are presented for reducing search by reducing local ambiguity: Limited left-context constraints are used to reduce local…

Blended modeling is an emerging paradigm involving seamless interaction between multiple notations for the same underlying modeling language. We focus on a model-driven engineering (MDE) approach based on meta-models to develop textual…

Programming by Example (PBE) is the task of inducing computer programs from input-output examples. It can be seen as a type of machine learning where the hypothesis space is the set of legal programs in some programming language. Recent…

The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations…

Large Language Models (LLMs) have demonstrated remarkable capabilities on various tasks, while the further evolvement is limited to the lack of high-quality training data. In addition, traditional training approaches rely too much on…

Tourists and Wild-life photographers are often hindered in capturing their cherished images or videos by a fence that limits accessibility to the scene of interest. The situation has been exacerbated by growing concerns of security at…

Image captioning has so far been explored mostly in English, as most available datasets are in this language. However, the application of image captioning should not be restricted by language. Only few studies have been conducted for image…

We are concerned with dependency-oriented morphosyntactic parsing of running text. While a parsing grammar should avoid introducing structurally unresolvable distinctions in order to optimise on the accuracy of the parser, it also is…

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word…

Cache coherence protocols based on self-invalidation and self-downgrade have recently seen increased popularity due to their simplicity, potential performance efficiency, and low energy consumption. However, such protocols result in memory…