Related papers: Many Languages, One Parser
We present the Uppsala system for the CoNLL 2018 Shared Task on universal dependency parsing. Our system is a pipeline consisting of three components: the first performs joint word and sentence segmentation; the second predicts part-of-…
The popularity of applying machine learning methods to computational linguistics problems has produced a large supply of trainable natural language processing systems. Most problems of interest have an array of off-the-shelf products or…
Treebank translation is a promising method for cross-lingual transfer of syntactic dependency knowledge. The basic idea is to map dependency arcs from a source treebank to its target translation according to word alignments. This method,…
In this work, we provide a systematic and comprehensive empirical comparison of pretrained multilingual language models versus their monolingual counterparts with regard to their monolingual task performance. We study a set of nine…
Incorporating stronger syntactic biases into neural language models (LMs) is a long-standing goal, but research in this area often focuses on modeling English text, where constituent treebanks are readily available. Extending constituent…
We explore whether it is possible to leverage eye-tracking data in an RNN dependency parser (for English) when such information is only available during training, i.e., no aggregated or token-level gaze features are used at inference time.…
We provide a comprehensive analysis of the interactions between pre-trained word embeddings, character models and POS tags in a transition-based dependency parser. While previous studies have shown POS information to be less important in…
In this paper we propose and carefully evaluate a sequence labeling framework which solely utilizes sparse indicator features derived from dense distributed word representations. The proposed model obtains (near) state-of-the art…
We demonstrate that a dependency parser can be built using a credit assignment compiler which removes the burden of worrying about low-level machine learning details from the parser implementation. The result is a simple parser which…
Previous Part-Of-Speech (POS) induction models usually assume certain independence assumptions (e.g., Markov, unidirectional, local dependency) that do not hold in real languages. For example, the subject-verb agreement can be both…
This thesis presents a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The parser builds fully connected derivations incrementally, in a single pass from…
In Natural Language Processing (NLP), one traditionally considers a single task (e.g. part-of-speech tagging) for a single language (e.g. English) at a time. However, recent work has shown that it can be beneficial to take advantage of…
Learning word embeddings using distributional information is a task that has been studied by many researchers, and a lot of studies are reported in the literature. On the contrary, less studies were done for the case of multiple languages.…
We describe a cross-lingual adaptation method based on syntactic parse trees obtained from the Universal Dependencies (UD), which are consistent across languages, to develop classifiers in low-resource languages. The idea of UD parsing is…
This paper describes the functioning of a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The paper first introduces key notions in language modeling and…
Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them for crosslingual transfer from a language…
Traditional syntax models typically leverage part-of-speech (POS) information by constructing features from hand-tuned templates. We demonstrate that a better approach is to utilize POS tags as a regularizer of learned representations. We…
We present an approach for assessing how multilingual large language models (LLMs) learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent and dependency structures by casting parsing as sequence…
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…
We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to…