Related papers: An improved parser for data-oriented lexical-funct…
Data-Oriented Parsing (dop) ranks among the best parsing schemes, pairing state-of-the art parsing accuracy to the psycholinguistic insight that larger chunks of syntactic structures are relevant grammatical and probabilistic units. Parsing…
In Data-Oriented Parsing (DOP), an annotated language corpus is used as a stochastic grammar. The most probable analysis of a new input sentence is constructed by combining sub-analyses from the corpus in the most probable way. This…
Excellent results have been reported for Data-Oriented Parsing (DOP) of natural language texts (Bod, 1993). Unfortunately, existing algorithms are both computationally intensive and difficult to implement. Previous algorithms are expensive…
In this paper I present ongoing work on the data-oriented parsing (DOP) model. In previous work, DOP was tested on a cleaned-up set of analyzed part-of-speech strings from the Penn Treebank, achieving excellent test results. This left,…
During the last few years, a new approach to language processing has started to emerge, which has become known under various labels such as "data-oriented parsing", "corpus-based interpretation", and "tree-bank grammar" (cf. van den Berg et…
This dissertation analyses the computational properties of current performance-models of natural language parsing, in particular Data Oriented Parsing (DOP), points out some of their major shortcomings and suggests suitable solutions. It…
Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they often require more than 10 times the computational resources…
Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic…
Research into the automatic acquisition of lexical information from corpora is starting to produce large-scale computational lexicons containing data on the relative frequencies of subcategorisation alternatives for individual verbal…
Deep learning approaches are superior in NLP due to their ability to extract informative features and patterns from languages. The two most successful neural architectures are LSTM and transformers, used in large pretrained language models…
We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process inspired by the successful strategy employed by AlphaZero. Our work leverages Monte…
In this paper we examine how the differences in modelling between different data driven systems performing the same NLP task can be exploited to yield a higher accuracy than the best individual system. We do this by means of an experiment…
Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph…
This paper examines efficient predictive broad-coverage parsing without dynamic programming. In contrast to bottom-up methods, depth-first top-down parsing produces partial parses that are fully connected trees spanning the entire left…
Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence…
In this paper, we consider the extent to which the transformer-based Dense Passage Retrieval (DPR) algorithm, developed by (Karpukhin et. al. 2020), can be optimized without further pre-training. Our method involves two particular insights:…
Lexical analysis is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end lexical analysis models with recurrent neural networks have gained increasing attention. In this…
Given a previously unseen form that is morphologically n-ways ambiguous, what is the best estimator for the lexical prior probabilities for the various functions of the form? We argue that the best estimator is provided by computing the…
We use a Dynamic Bayesian Network to represent compactly a variety of sublexical and contextual features relevant to Part-of-Speech (PoS) tagging. The outcome is a flexible tagger (LegoTag) with state-of-the-art performance (3.6% error on a…
The success of large-scale language models like GPT can be attributed to their ability to efficiently predict the next token in a sequence. However, these models rely on constant computational effort regardless of the complexity of the…